chore: import upstream snapshot with attribution

2026-07-13 12:19:01 +08:00
commit 3b90d1192f
2172 changed files with 594509 additions and 0 deletions
@@ -0,0 +1,56 @@
+{
+ "<h1><a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a> evaluation/sampling</h1>\n<p>This is the code to generate images and create interpolations between given images.</p>\n": "<h1><a href=\"index.html\">\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM) \u306e\u8a55\u4fa1/\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0</a></h1>\n<p>\u3053\u308c\u306f\u3001\u753b\u50cf\u3092\u751f\u6210\u3057\u3001\u4e0e\u3048\u3089\u308c\u305f\u753b\u50cf\u9593\u306e\u88dc\u9593\u3092\u884c\u3046\u30b3\u30fc\u30c9\u3067\u3059\u3002</p>\n",
+ "<h2>Sampler class</h2>\n": "<h2>\u30b5\u30f3\u30d7\u30e9\u30fc\u30af\u30e9\u30b9</h2>\n",
+ "<h4>Estimate <span translate=no>_^_0_^_</span></h4>\n<p><span translate=no>_^_1_^_</span></p>\n": "<h4>\u898b\u7a4d\u3082\u308a <span translate=no>_^_0_^_</span></h4>\n<p><span translate=no>_^_1_^_</span></p>\n",
+ "<h4>Generate images</h4>\n": "<h4>\u753b\u50cf\u3092\u751f\u6210</h4>\n",
+ "<h4>Interpolate two images <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span> and make a video</h4>\n<ul><li><span translate=no>_^_2_^_</span> is <span translate=no>_^_3_^_</span> </li>\n<li><span translate=no>_^_4_^_</span> is <span translate=no>_^_5_^_</span> </li>\n<li><span translate=no>_^_6_^_</span> is the number of frames for the image </li>\n<li><span translate=no>_^_7_^_</span> is <span translate=no>_^_8_^_</span> </li>\n<li><span translate=no>_^_9_^_</span> specifies whether to make a video or to show each frame</li></ul>\n": "<h4><span translate=no>_^_0_^_</span><span translate=no>_^_1_^_</span>2\u679a\u306e\u753b\u50cf\u3092\u88dc\u9593\u3057\u3066\u52d5\u753b\u3092\u4f5c\u6210</h4>\n<ul><li><span translate=no>_^_2_^_</span>\u306f <span translate=no>_^_3_^_</span></li>\n<li><span translate=no>_^_4_^_</span>\u306f <span translate=no>_^_5_^_</span></li>\n<li><span translate=no>_^_6_^_</span>\u753b\u50cf\u306e\u30d5\u30ec\u30fc\u30e0\u6570\u3067\u3059</li>\n<li><span translate=no>_^_7_^_</span>\u306f <span translate=no>_^_8_^_</span></li>\n<li><span translate=no>_^_9_^_</span>\u30d3\u30c7\u30aa\u3092\u4f5c\u6210\u3059\u308b\u304b\u3001\u5404\u30d5\u30ec\u30fc\u30e0\u3092\u8868\u793a\u3059\u308b\u304b\u3092\u6307\u5b9a\u3057\u307e\u3059</li></ul>\n",
+ "<h4>Interpolate two images <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span></h4>\n<p>We get <span translate=no>_^_2_^_</span> and <span translate=no>_^_3_^_</span>.</p>\n<p>Then interpolate to  <span translate=no>_^_4_^_</span></p>\n<p>Then get  <span translate=no>_^_5_^_</span></p>\n<ul><li><span translate=no>_^_6_^_</span> is <span translate=no>_^_7_^_</span> </li>\n<li><span translate=no>_^_8_^_</span> is <span translate=no>_^_9_^_</span> </li>\n<li><span translate=no>_^_10_^_</span> is <span translate=no>_^_11_^_</span> </li>\n<li><span translate=no>_^_12_^_</span> is <span translate=no>_^_13_^_</span></li></ul>\n": "<h4>2 \u3064\u306e\u753b\u50cf\u3092\u88dc\u9593\u3057\u3001<span translate=no>_^_0_^_</span> <span translate=no>_^_1_^_</span></h4>\n<p><span translate=no>_^_2_^_</span><span translate=no>_^_3_^_</span>\u3068\u53d6\u5f97\u3057\u307e\u3059.</p>\n<p>\u6b21\u306b\u3001\u6b21\u306e\u3088\u3046\u306b\u88dc\u9593\u3057\u307e\u3059 <span translate=no>_^_4_^_</span></p>\n<p>\u6b21\u306b\u3001\u53d6\u5f97 <span translate=no>_^_5_^_</span></p>\n<ul><li><span translate=no>_^_6_^_</span>\u306f <span translate=no>_^_7_^_</span></li>\n<li><span translate=no>_^_8_^_</span>\u306f <span translate=no>_^_9_^_</span></li>\n<li><span translate=no>_^_10_^_</span>\u306f <span translate=no>_^_11_^_</span></li>\n</ul><li><span translate=no>_^_12_^_</span>\u306f <span translate=no>_^_13_^_</span></li>\n",
+ "<h4>Sample an image step-by-step using <span translate=no>_^_0_^_</span></h4>\n<p>We sample an image step-by-step using <span translate=no>_^_1_^_</span> and at each step show the estimate <span translate=no>_^_2_^_</span></p>\n": "<h4>\u3092\u4f7f\u7528\u3057\u3066\u753b\u50cf\u3092\u6bb5\u968e\u7684\u306b\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3059\u308b <span translate=no>_^_0_^_</span></h4>\n<p><span translate=no>_^_1_^_</span>\u3092\u4f7f\u7528\u3057\u3066\u753b\u50cf\u3092\u6bb5\u968e\u7684\u306b\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3001\u5404\u30b9\u30c6\u30c3\u30d7\u3067\u898b\u7a4d\u3082\u308a\u3092\u8868\u793a\u3057\u307e\u3059 <span translate=no>_^_2_^_</span></p>\n",
+ "<h4>Sample an image using <span translate=no>_^_0_^_</span></h4>\n<ul><li><span translate=no>_^_1_^_</span> is <span translate=no>_^_2_^_</span> </li>\n<li><span translate=no>_^_3_^_</span> is <span translate=no>_^_4_^_</span></li></ul>\n": "<h4>\u3092\u4f7f\u7528\u3057\u3066\u753b\u50cf\u3092\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3059\u308b <span translate=no>_^_0_^_</span></h4>\n<ul><li><span translate=no>_^_1_^_</span>\u306f <span translate=no>_^_2_^_</span></li>\n</ul><li><span translate=no>_^_3_^_</span>\u306f <span translate=no>_^_4_^_</span></li>\n",
+ "<h4>Sample from <span translate=no>_^_0_^_</span></h4>\n<span translate=no>_^_1_^_</span>": "<h4>\u304b\u3089\u306e\u30b5\u30f3\u30d7\u30eb <span translate=no>_^_0_^_</span></h4>\n<span translate=no>_^_1_^_</span>",
+ "<p> </p>\n": "<p></p>\n",
+ "<p>20 second video </p>\n": "<p>20 \u79d2\u306e\u30d3\u30c7\u30aa</p>\n",
+ "<p><a href=\"utils.html\">gather</a> <span translate=no>_^_0_^_</span> </p>\n": "<p><a href=\"utils.html\">\u96c6\u307e\u308b</a> <span translate=no>_^_0_^_</span></p>\n",
+ "<p><span translate=no>_^_0_^_</span> </p>\n": "<p><span translate=no>_^_0_^_</span></p>\n",
+ "<p><span translate=no>_^_0_^_</span> in a tensor </p>\n": "<p><span translate=no>_^_0_^_</span>\u30c6\u30f3\u30bd\u30eb\u3067</p>\n",
+ "<p><span translate=no>_^_0_^_</span> tensor </p>\n": "<p><span translate=no>_^_0_^_</span>\u30c6\u30f3\u30bd\u30eb</p>\n",
+ "<p>Add batch dimension </p>\n": "<p>\u30d0\u30c3\u30c1\u30c7\u30a3\u30e1\u30f3\u30b7\u30e7\u30f3\u3092\u8ffd\u52a0</p>\n",
+ "<p>Add each image </p>\n": "<p>\u5404\u753b\u50cf\u3092\u8ffd\u52a0</p>\n",
+ "<p>Add to frames </p>\n": "<p>\u30d5\u30ec\u30fc\u30e0\u306b\u8ffd\u52a0</p>\n",
+ "<p>Create an interpolation animation </p>\n": "<p>\u88dc\u9593\u30a2\u30cb\u30e1\u30fc\u30b7\u30e7\u30f3\u306e\u4f5c\u6210</p>\n",
+ "<p>Create configs </p>\n": "<p>\u30b3\u30f3\u30d5\u30a3\u30b0\u306e\u4f5c\u6210</p>\n",
+ "<p>Create sampler </p>\n": "<p>\u30b5\u30f3\u30d7\u30e9\u30fc\u306e\u4f5c\u6210</p>\n",
+ "<p>Frames for video </p>\n": "<p>\u30d3\u30c7\u30aa\u7528\u30d5\u30ec\u30fc\u30e0</p>\n",
+ "<p>Generate samples </p>\n": "<p>\u30b5\u30f3\u30d7\u30eb\u3092\u751f\u6210</p>\n",
+ "<p>Get <span translate=no>_^_0_^_</span> and add to frames </p>\n": "<p><span translate=no>_^_0_^_</span>\u30d5\u30ec\u30fc\u30e0\u306e\u53d6\u5f97\u3068\u8ffd\u52a0</p>\n",
+ "<p>Get frames with different <span translate=no>_^_0_^_</span> </p>\n": "<p>\u7570\u306a\u308b\u30d5\u30ec\u30fc\u30e0\u3092\u53d6\u5f97 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Get some images fro data </p>\n": "<p>\u30c7\u30fc\u30bf\u304b\u3089\u3044\u304f\u3064\u304b\u306e\u753b\u50cf\u3092\u53d6\u5f97</p>\n",
+ "<p>Helper function to create a video </p>\n": "<p>\u52d5\u753b\u3092\u4f5c\u6210\u3059\u308b\u305f\u3081\u306e\u30d8\u30eb\u30d1\u30fc\u6a5f\u80fd</p>\n",
+ "<p>Helper function to display an image </p>\n": "<p>\u753b\u50cf\u3092\u8868\u793a\u3059\u308b\u30d8\u30eb\u30d1\u30fc\u95a2\u6570</p>\n",
+ "<p>Initialize </p>\n": "<p>[\u521d\u671f\u5316]</p>\n",
+ "<p>Interval to log <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30ed\u30b0\u306b\u8a18\u9332\u3059\u308b\u9593\u9694 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Iterate until <span translate=no>_^_0_^_</span> steps </p>\n": "<p><span translate=no>_^_0_^_</span>\u30b9\u30c6\u30c3\u30d7\u307e\u3067\u7e70\u308a\u8fd4\u3059</p>\n",
+ "<p>Load custom configuration of the training run </p>\n": "<p>\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30e9\u30f3\u306e\u30ab\u30b9\u30bf\u30e0\u69cb\u6210\u3092\u30ed\u30fc\u30c9</p>\n",
+ "<p>Load training experiment </p>\n": "<p>\u8ca0\u8377\u8a13\u7df4\u5b9f\u9a13</p>\n",
+ "<p>Make video </p>\n": "<p>\u52d5\u753b\u3092\u4f5c\u308b</p>\n",
+ "<p>No gradients </p>\n": "<p>\u30b0\u30e9\u30c7\u30fc\u30b7\u30e7\u30f3\u306a\u3057</p>\n",
+ "<p>Number of sampels </p>\n": "<p>\u30b5\u30f3\u30d7\u30eb\u6570</p>\n",
+ "<p>Number of samples </p>\n": "<p>\u30b5\u30f3\u30d7\u30eb\u6570</p>\n",
+ "<p>Return <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30ea\u30bf\u30fc\u30f3 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Sample </p>\n": "<p>[\u30b5\u30f3\u30d7\u30eb]</p>\n",
+ "<p>Sample <span translate=no>_^_0_^_</span> steps </p>\n": "<p><span translate=no>_^_0_^_</span>\u30b5\u30f3\u30d7\u30eb\u30b9\u30c6\u30c3\u30d7</p>\n",
+ "<p>Sample an image with an denoising animation </p>\n": "<p>\u30ce\u30a4\u30ba\u9664\u53bb\u30a2\u30cb\u30e1\u30fc\u30b7\u30e7\u30f3\u306b\u3088\u308b\u753b\u50cf\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0</p>\n",
+ "<p>Sample from <span translate=no>_^_0_^_</span> </p>\n": "<p>\u304b\u3089\u306e\u30b5\u30f3\u30d7\u30eb <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Set PyTorch modules for saving and loading </p>\n": "<p>\u4fdd\u5b58\u3068\u8aad\u307f\u8fbc\u307f\u7528\u306e PyTorch \u30e2\u30b8\u30e5\u30fc\u30eb\u306e\u8a2d\u5b9a</p>\n",
+ "<p>Set configurations </p>\n": "<p>\u69cb\u6210\u3092\u8a2d\u5b9a</p>\n",
+ "<p>Show frame </p>\n": "<p>\u30d5\u30ec\u30fc\u30e0\u3092\u8868\u793a</p>\n",
+ "<p>Show images </p>\n": "<p>\u753b\u50cf\u3092\u8868\u793a</p>\n",
+ "<p>Show original images </p>\n": "<p>\u5143\u306e\u753b\u50cf\u3092\u8868\u793a</p>\n",
+ "<p>Start an evaluation </p>\n": "<p>\u8a55\u4fa1\u3092\u958b\u59cb\u3059\u308b</p>\n",
+ "<p>Start evaluation </p>\n": "<p>\u8a55\u4fa1\u3092\u958b\u59cb\u3059\u308b</p>\n",
+ "<p>To calculate</p>\n<span translate=no>_^_0_^_</span><p> </p>\n": "<p>\u8a08\u7b97\u3059\u308b\u306b\u306f</p>\n<span translate=no>_^_0_^_</span><p></p>\n",
+ "<p>Training experiment run UUID </p>\n": "<p>\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u5b9f\u9a13\u5b9f\u884c UUID</p>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the <span translate=no>_^_1_^_</span> instance </li>\n<li><span translate=no>_^_2_^_</span> is the number of channels in the image </li>\n<li><span translate=no>_^_3_^_</span> is the image size </li>\n<li><span translate=no>_^_4_^_</span> is the device of the model</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span><span translate=no>_^_1_^_</span>\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u3067\u3059</li>\n<li><span translate=no>_^_2_^_</span>\u306f\u753b\u50cf\u5185\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</li>\n<li><span translate=no>_^_3_^_</span>\u306f\u753b\u50cf\u30b5\u30a4\u30ba\u3067\u3059</li>\n<li><span translate=no>_^_4_^_</span>\u30e2\u30c7\u30eb\u306e\u30c7\u30d0\u30a4\u30b9\u3067\u3059</li></ul>\n",
+ "Code to generate samples from a trained Denoising Diffusion Probabilistic Model.": "\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u6e08\u307f\u306e\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb\u304b\u3089\u30b5\u30f3\u30d7\u30eb\u3092\u751f\u6210\u3059\u308b\u30b3\u30fc\u30c9\u3002",
+ "Denoising Diffusion Probabilistic Models (DDPM) evaluation/sampling": "\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM) \u306e\u8a55\u4fa1/\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0"
+}
@@ -0,0 +1,56 @@
+{
+ "<h1><a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a> evaluation/sampling</h1>\n<p>This is the code to generate images and create interpolations between given images.</p>\n": "<h1><a href=\"index.html\">\u0dc0\u0dd2\u0dc3\u0dbb\u0dab \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf\u0dc0 \u0d86\u0d9a\u0dd8\u0dad\u0dd2 (DDPM)</a> \u0d87\u0d9c\u0dba\u0dd3\u0db8/\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd3\u0db8</h1>\n<p>\u0dbb\u0dd6\u0db4\u0d8b\u0dad\u0dca\u0db4\u0dcf\u0daf\u0db1\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0da7 \u0dc3\u0dc4 \u0dbd\u0db6\u0dcf \u0daf\u0dd3 \u0d87\u0dad\u0dd2 \u0dbb\u0dd6\u0db4 \u0d85\u0dad\u0dbb \u0d85\u0db1\u0dca\u0dad\u0dbb\u0dca\u0d9a\u0dca\u0dbb\u0dd2\u0dba\u0dcf\u0d9a\u0dcf\u0dbb\u0dd2\u0dad\u0dca\u0dc0\u0dba\u0db1\u0dca \u0db1\u0dd2\u0dbb\u0dca\u0db8\u0dcf\u0dab\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dda \u0d9a\u0dda\u0dad\u0dba \u0db8\u0dd9\u0dba\u0dba\u0dd2. </p>\n",
+ "<h2>Sampler class</h2>\n": "<h2>\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd2\u0db4\u0db1\u0dca\u0dad\u0dd2\u0dba</h2>\n",
+ "<h4>Estimate <span translate=no>_^_0_^_</span></h4>\n<p><span translate=no>_^_1_^_</span></p>\n": "<h4>\u0d87\u0dc3\u0dca\u0dad\u0db8\u0dda\u0db1\u0dca\u0dad\u0dd4\u0dc0 <span translate=no>_^_0_^_</span></h4>\n<p><span translate=no>_^_1_^_</span></p>\n",
+ "<h4>Generate images</h4>\n": "<h4>\u0dbb\u0dd6\u0db4\u0da2\u0db1\u0db1\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1</h4>\n",
+ "<h4>Interpolate two images <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span> and make a video</h4>\n<ul><li><span translate=no>_^_2_^_</span> is <span translate=no>_^_3_^_</span> </li>\n<li><span translate=no>_^_4_^_</span> is <span translate=no>_^_5_^_</span> </li>\n<li><span translate=no>_^_6_^_</span> is the number of frames for the image </li>\n<li><span translate=no>_^_7_^_</span> is <span translate=no>_^_8_^_</span> </li>\n<li><span translate=no>_^_9_^_</span> specifies whether to make a video or to show each frame</li></ul>\n": "<h4>\u0dbb\u0dd6\u0db4\u0daf\u0dd9\u0d9a\u0d9a\u0dca \u0d85\u0db1\u0dca\u0dad\u0dbb\u0dca\u0d9c\u0dca\u0dbb\u0dc4\u0dab\u0dba <span translate=no>_^_0_^_</span> <span translate=no>_^_1_^_</span> \u0d9a\u0dbb \u0dc0\u0dd3\u0da9\u0dd2\u0dba\u0ddd\u0dc0\u0d9a\u0dca \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1</h4>\n<ul><li><span translate=no>_^_2_^_</span> \u0dc0\u0dda <span translate=no>_^_3_^_</span> </li>\n<li><span translate=no>_^_4_^_</span> \u0dc0\u0dda <span translate=no>_^_5_^_</span> </li>\n<li><span translate=no>_^_6_^_</span> \u0dba\u0db1\u0dd4 \u0dbb\u0dd6\u0db4\u0dba \u0dc3\u0db3\u0dc4\u0dcf \u0dbb\u0dcf\u0db8\u0dd4 \u0d9c\u0dab\u0db1 </li>\n<li><span translate=no>_^_7_^_</span> \u0dc0\u0dda <span translate=no>_^_8_^_</span> </li>\n<li><span translate=no>_^_9_^_</span> \u0dc0\u0dd3\u0da9\u0dd2\u0dba\u0ddd\u0dc0\u0d9a\u0dca \u0dc3\u0dd1\u0daf\u0dd2\u0dba \u0dba\u0dd4\u0dad\u0dd4\u0daf \u0db1\u0dd0\u0dad\u0dc4\u0ddc\u0dad\u0dca \u0d91\u0d9a\u0dca \u0d91\u0d9a\u0dca \u0dbb\u0dcf\u0db8\u0dd4\u0dc0 \u0db4\u0dd9\u0db1\u0dca\u0dc0\u0dd2\u0dba \u0dba\u0dd4\u0dad\u0dd4\u0daf \u0dba\u0db1\u0dca\u0db1 \u0db1\u0dd2\u0dba\u0db8 \u0d9a\u0dbb\u0dba\u0dd2</li></ul>\n",
+ "<h4>Interpolate two images <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span></h4>\n<p>We get <span translate=no>_^_2_^_</span> and <span translate=no>_^_3_^_</span>.</p>\n<p>Then interpolate to  <span translate=no>_^_4_^_</span></p>\n<p>Then get  <span translate=no>_^_5_^_</span></p>\n<ul><li><span translate=no>_^_6_^_</span> is <span translate=no>_^_7_^_</span> </li>\n<li><span translate=no>_^_8_^_</span> is <span translate=no>_^_9_^_</span> </li>\n<li><span translate=no>_^_10_^_</span> is <span translate=no>_^_11_^_</span> </li>\n<li><span translate=no>_^_12_^_</span> is <span translate=no>_^_13_^_</span></li></ul>\n": "<h4>\u0dbb\u0dd6\u0db4\u0daf\u0dd9\u0d9a\u0d9a\u0dca \u0d85\u0db1\u0dca\u0dad\u0dbb\u0dca\u0d9c\u0dca\u0dbb\u0dc4\u0dab\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span> \u0dc3\u0dc4 <span translate=no>_^_1_^_</span></h4>\n<p>\u0d85\u0db4\u0dd2\u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1 <span translate=no>_^_2_^_</span> \u0dc3\u0dc4 <span translate=no>_^_3_^_</span>. </p>\n<p>\u0d89\u0db1\u0dca\u0db4\u0dc3\u0dd4\u0d85\u0db1\u0dca\u0dad\u0dbb\u0dca\u0db4\u0ddc\u0dbd\u0dda\u0da7\u0dca \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_4_^_</span></p>\n<p>\u0d89\u0db1\u0dca\u0db4\u0dc3\u0dd4\u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1 <span translate=no>_^_5_^_</span></p>\n<ul><li><span translate=no>_^_6_^_</span> \u0dc0\u0dda <span translate=no>_^_7_^_</span> </li>\n<li><span translate=no>_^_8_^_</span> \u0dc0\u0dda <span translate=no>_^_9_^_</span> </li>\n<li><span translate=no>_^_10_^_</span> \u0dc0\u0dda <span translate=no>_^_11_^_</span> </li>\n</ul><li><span translate=no>_^_12_^_</span> \u0dc0\u0dda <span translate=no>_^_13_^_</span></li>\n",
+ "<h4>Sample an image step-by-step using <span translate=no>_^_0_^_</span></h4>\n<p>We sample an image step-by-step using <span translate=no>_^_1_^_</span> and at each step show the estimate <span translate=no>_^_2_^_</span></p>\n": "<h4>\u0db4\u0dd2\u0dba\u0dc0\u0dbb\u0dd9\u0db1\u0dca\u0db4\u0dd2\u0dba\u0dc0\u0dbb \u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0d9a\u0dbb\u0db8\u0dd2\u0db1\u0dca \u0dbb\u0dd6\u0db4\u0dba\u0d9a\u0dca \u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span></h4>\n<p>\u0d85\u0db4\u0dd2\u0db4\u0dd2\u0dba\u0dc0\u0dbb\u0dd9\u0db1\u0dca \u0db4\u0dd2\u0dba\u0dc0\u0dbb \u0dbb\u0dd6\u0db4\u0dba\u0d9a\u0dca \u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd \u0d9a\u0dbb \u0d87\u0dad\u0dd2 <span translate=no>_^_1_^_</span> \u0d85\u0dad\u0dbb \u0dc3\u0dd1\u0db8 \u0db4\u0dd2\u0dba\u0dc0\u0dbb\u0d9a\u0daf\u0dd3\u0db8 \u0d87\u0dc3\u0dca\u0dad\u0db8\u0dda\u0db1\u0dca\u0dad\u0dd4\u0dc0 \u0db4\u0dd9\u0db1\u0dca\u0dc0\u0dba\u0dd2 <span translate=no>_^_2_^_</span></p>\n",
+ "<h4>Sample an image using <span translate=no>_^_0_^_</span></h4>\n<ul><li><span translate=no>_^_1_^_</span> is <span translate=no>_^_2_^_</span> </li>\n<li><span translate=no>_^_3_^_</span> is <span translate=no>_^_4_^_</span></li></ul>\n": "<h4>\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf\u0d9a\u0dbb\u0db8\u0dd2\u0db1\u0dca \u0dbb\u0dd6\u0db4\u0dba\u0d9a\u0dca \u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span></h4>\n<ul><li><span translate=no>_^_1_^_</span> \u0dc0\u0dda <span translate=no>_^_2_^_</span> </li>\n</ul><li><span translate=no>_^_3_^_</span> \u0dc0\u0dda <span translate=no>_^_4_^_</span></li>\n",
+ "<h4>Sample from <span translate=no>_^_0_^_</span></h4>\n<span translate=no>_^_1_^_</span>": "<h4>\u0dc0\u0dd9\u0dad\u0dd2\u0db1\u0dca\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd2\u0dba <span translate=no>_^_0_^_</span></h4>\n<span translate=no>_^_1_^_</span>",
+ "<p> </p>\n": "<p> </p>\n",
+ "<p>20 second video </p>\n": "<p>20\u0daf\u0dd9\u0dc0\u0db1 \u0dc0\u0dd3\u0da9\u0dd2\u0dba\u0ddd\u0dc0 </p>\n",
+ "<p><a href=\"utils.html\">gather</a> <span translate=no>_^_0_^_</span> </p>\n": "<p><a href=\"utils.html\">\u0dbb\u0dd0\u0dc3\u0dca \u0d9a\u0dbb\u0db1\u0dca\u0db1</a> <span translate=no>_^_0_^_</span> </p>\n",
+ "<p><span translate=no>_^_0_^_</span> </p>\n": "<p><span translate=no>_^_0_^_</span> </p>\n",
+ "<p><span translate=no>_^_0_^_</span> in a tensor </p>\n": "<p><span translate=no>_^_0_^_</span> \u0d91\u0dba tensor \u0daf\u0dd3 </p>\n",
+ "<p><span translate=no>_^_0_^_</span> tensor </p>\n": "<p><span translate=no>_^_0_^_</span> \u0da7\u0dd9\u0db1\u0dca\u0dc3\u0dbb\u0dca </p>\n",
+ "<p>Add batch dimension </p>\n": "<p>\u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca\u0db8\u0dcf\u0db1\u0dba \u0d91\u0d9a\u0dca \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Add each image </p>\n": "<p>\u0d91\u0d9a\u0dca\u0d91\u0d9a\u0dca \u0dbb\u0dd6\u0db4\u0dba \u0d91\u0d9a\u0dad\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Add to frames </p>\n": "<p>\u0dbb\u0dcf\u0db8\u0dd4\u0dc0\u0dbd\u0da7 \u0d91\u0d9a\u0dad\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Create an interpolation animation </p>\n": "<p>\u0d85\u0db1\u0dca\u0dad\u0dbb\u0dca\u0db1\u0dd2\u0dc0\u0dda\u0dc2\u0dab\u0dba\u0dc3\u0da2\u0dd3\u0dc0\u0dd2\u0d9a\u0dbb\u0dab\u0dba\u0d9a\u0dca \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Create configs </p>\n": "<p>\u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Create sampler </p>\n": "<p>\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd2\u0dba\u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Frames for video </p>\n": "<p>\u0dc0\u0dd3\u0da9\u0dd2\u0dba\u0ddd\u0dc3\u0db3\u0dc4\u0dcf \u0dbb\u0dcf\u0db8\u0dd4 </p>\n",
+ "<p>Generate samples </p>\n": "<p>\u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd\u0da2\u0db1\u0db1\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Get <span translate=no>_^_0_^_</span> and add to frames </p>\n": "<p>\u0dbb\u0dcf\u0db8\u0dd4\u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span> \u0dc3\u0dc4 \u0d91\u0d9a\u0dad\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Get frames with different <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0dc0\u0dd2\u0dc0\u0dd2\u0db0\u0dbb\u0dcf\u0db8\u0dd4 \u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Get some images fro data </p>\n": "<p>\u0daf\u0dad\u0dca\u0dad\u0dc0\u0dbd\u0dd2\u0db1\u0dca \u0db4\u0dd2\u0db1\u0dca\u0dad\u0dd6\u0dbb \u0d9a\u0dd2\u0dc4\u0dd2\u0db4\u0dba\u0d9a\u0dca \u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Helper function to create a video </p>\n": "<p>\u0dc0\u0dd3\u0da9\u0dd2\u0dba\u0ddd\u0dc0\u0d9a\u0dca\u0db1\u0dd2\u0dbb\u0dca\u0db8\u0dcf\u0dab\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0d8b\u0db4\u0d9a\u0dcf\u0dbb\u0d9a \u0d9a\u0dcf\u0dbb\u0dca\u0dba\u0dba </p>\n",
+ "<p>Helper function to display an image </p>\n": "<p>\u0dbb\u0dd6\u0db4\u0dba\u0d9a\u0dca\u0db4\u0dca\u0dbb\u0daf\u0dbb\u0dca\u0dc1\u0db1\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0d8b\u0db4\u0d9a\u0dcf\u0dbb\u0d9a \u0d9a\u0dcf\u0dbb\u0dca\u0dba\u0dba </p>\n",
+ "<p>Initialize </p>\n": "<p>\u0d86\u0dbb\u0db8\u0dca\u0db7\u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Interval to log <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0dbd\u0ddc\u0d9c\u0dca\u0dc0\u0dd3\u0db8\u0da7 \u0db4\u0dbb\u0dad\u0dbb\u0dba <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Iterate until <span translate=no>_^_0_^_</span> steps </p>\n": "<p><span translate=no>_^_0_^_</span> \u0db4\u0dd2\u0dba\u0dc0\u0dbb \u0d9c\u0db1\u0dca\u0db1\u0dcf \u0dad\u0dd9\u0d9a\u0dca \u0db1\u0dd0\u0dc0\u0dad \u0d9a\u0dca\u0dbb\u0dd2\u0dba\u0dcf\u0dad\u0dca\u0db8\u0d9a \u0dc0\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Load custom configuration of the training run </p>\n": "<p>\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4\u0db0\u0dcf\u0dc0\u0db1\u0dba\u0dda \u0d85\u0db7\u0dd2\u0dbb\u0dd4\u0da0\u0dd2 \u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0dba \u0db4\u0dd6\u0dbb\u0dab\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Load training experiment </p>\n": "<p>\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4\u0d85\u0dad\u0dca\u0dc4\u0daf\u0dcf \u0db6\u0dd0\u0dbd\u0dd3\u0db8 </p>\n",
+ "<p>Make video </p>\n": "<p>\u0dc0\u0dd3\u0da9\u0dd2\u0dba\u0ddd\u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
+ "<p>No gradients </p>\n": "<p>\u0d9a\u0dd2\u0dc3\u0dd2\u0daf\u0dd4\u0d85\u0db1\u0dd4\u0d9a\u0dca\u0dbb\u0db8\u0dd2\u0d9a </p>\n",
+ "<p>Number of sampels </p>\n": "<p>\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd2\u0d9c\u0dab\u0db1 </p>\n",
+ "<p>Number of samples </p>\n": "<p>\u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd\u0d9c\u0dab\u0db1 </p>\n",
+ "<p>Return <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0d86\u0db4\u0dc3\u0dd4 <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Sample </p>\n": "<p>\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd2\u0dba </p>\n",
+ "<p>Sample <span translate=no>_^_0_^_</span> steps </p>\n": "<p>\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd2 <span translate=no>_^_0_^_</span> \u0db4\u0dd2\u0dba\u0dc0\u0dbb </p>\n",
+ "<p>Sample an image with an denoising animation </p>\n": "<p>\u0db1\u0dd2\u0dbb\u0dd6\u0db4\u0dab\u0dba\u0d9a\u0dbb\u0db1 \u0dc3\u0da2\u0dd3\u0dc0\u0dd2\u0d9a\u0dbb\u0dab\u0dba\u0d9a\u0dca \u0dc3\u0dc4\u0dd2\u0dad \u0dbb\u0dd6\u0db4\u0dba\u0d9a\u0dca \u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Sample from <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0dc0\u0dd9\u0dad\u0dd2\u0db1\u0dca\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd2\u0dba <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Set PyTorch modules for saving and loading </p>\n": "<p>\u0d89\u0dad\u0dd2\u0dbb\u0dd2\u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0dc4 \u0db4\u0dd0\u0da7\u0dc0\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0db4\u0dba\u0dd2\u0da7\u0ddd\u0da0\u0dca \u0db8\u0ddc\u0da9\u0dd2\u0dba\u0dd4\u0dbd \u0dc3\u0d9a\u0dc3\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Set configurations </p>\n": "<p>\u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0dba\u0db1\u0dca\u0dc3\u0d9a\u0dc3\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Show frame </p>\n": "<p>\u0dbb\u0dcf\u0db8\u0dd4\u0dc0\u0db4\u0dd9\u0db1\u0dca\u0dc0\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Show images </p>\n": "<p>\u0db4\u0dd2\u0db1\u0dca\u0dad\u0dd6\u0dbb\u0db4\u0dd9\u0db1\u0dca\u0dc0\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Show original images </p>\n": "<p>\u0db8\u0dd4\u0dbd\u0dca\u0dbb\u0dd6\u0db4 \u0db4\u0dd9\u0db1\u0dca\u0dc0\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Start an evaluation </p>\n": "<p>\u0d87\u0d9c\u0dba\u0dd3\u0db8\u0d9a\u0dca\u0d86\u0dbb\u0db8\u0dca\u0db7 \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Start evaluation </p>\n": "<p>\u0d87\u0d9c\u0dba\u0dd3\u0db8\u0d86\u0dbb\u0db8\u0dca\u0db7 \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>To calculate</p>\n<span translate=no>_^_0_^_</span><p> </p>\n": "<p>\u0d9c\u0dab\u0db1\u0dba\u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0da7</p>\n<span translate=no>_^_0_^_</span><p> </p>\n",
+ "<p>Training experiment run UUID </p>\n": "<p>\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4\u0d85\u0dad\u0dca\u0dc4\u0daf\u0dcf \u0db6\u0dd0\u0dbd\u0dd3\u0db8 UUID </p>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the <span translate=no>_^_1_^_</span> instance </li>\n<li><span translate=no>_^_2_^_</span> is the number of channels in the image </li>\n<li><span translate=no>_^_3_^_</span> is the image size </li>\n<li><span translate=no>_^_4_^_</span> is the device of the model</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span> <span translate=no>_^_1_^_</span> \u0d8b\u0daf\u0dcf\u0dc4\u0dbb\u0dab\u0dba\u0d9a\u0dca \u0dc0\u0dda </li>\n<li><span translate=no>_^_2_^_</span> \u0dba\u0db1\u0dd4 \u0dbb\u0dd6\u0db4\u0dba\u0dda \u0d87\u0dad\u0dd2 \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1 </li>\n<li><span translate=no>_^_3_^_</span> \u0dba\u0db1\u0dd4 \u0dbb\u0dd6\u0db4\u0dba\u0dda \u0db4\u0dca\u0dbb\u0db8\u0dcf\u0dab\u0dba\u0dba\u0dd2 </li>\n</ul><li><span translate=no>_^_4_^_</span> \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0dda \u0d8b\u0db4\u0dcf\u0d82\u0d9c\u0dba \u0dc0\u0dda</li>\n",
+ "Code to generate samples from a trained Denoising Diffusion Probabilistic Model.": "\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4\u0dc0 \u0dbd\u0dad\u0dca \u0da9\u0dd9\u0db1\u0ddc\u0dba\u0dd2\u0dc3\u0dd2\u0d82 \u0dc0\u0dd2\u0dc3\u0dbb\u0dab\u0dba \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dd2\u0db1\u0dca \u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd \u0da2\u0db1\u0db1\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0d9a\u0dda\u0dad\u0dba.",
+ "Denoising Diffusion Probabilistic Models (DDPM) evaluation/sampling": "\u0dc0\u0dd2\u0dc3\u0dbb\u0dab \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf\u0dc0 \u0d86\u0d9a\u0dd8\u0dad\u0dd2 (DDPM) \u0d87\u0d9c\u0dba\u0dd3\u0db8/\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd3\u0db8"
+}
@@ -0,0 +1,56 @@
+{
+ "<h1><a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a> evaluation/sampling</h1>\n<p>This is the code to generate images and create interpolations between given images.</p>\n": "<h1><a href=\"index.html\">\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM)</a> \u8bc4\u4f30/\u91c7\u6837</h1>\n<p>\u8fd9\u662f\u751f\u6210\u56fe\u50cf\u5e76\u5728\u7ed9\u5b9a\u56fe\u50cf\u4e4b\u95f4\u521b\u5efa\u63d2\u503c\u7684\u4ee3\u7801\u3002</p>\n",
+ "<h2>Sampler class</h2>\n": "<h2>\u91c7\u6837\u5668\u7c7b</h2>\n",
+ "<h4>Estimate <span translate=no>_^_0_^_</span></h4>\n<p><span translate=no>_^_1_^_</span></p>\n": "<h4>\u4f30\u8ba1<span translate=no>_^_0_^_</span></h4>\n<p><span translate=no>_^_1_^_</span></p>\n",
+ "<h4>Generate images</h4>\n": "<h4>\u751f\u6210\u56fe\u50cf</h4>\n",
+ "<h4>Interpolate two images <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span> and make a video</h4>\n<ul><li><span translate=no>_^_2_^_</span> is <span translate=no>_^_3_^_</span> </li>\n<li><span translate=no>_^_4_^_</span> is <span translate=no>_^_5_^_</span> </li>\n<li><span translate=no>_^_6_^_</span> is the number of frames for the image </li>\n<li><span translate=no>_^_7_^_</span> is <span translate=no>_^_8_^_</span> </li>\n<li><span translate=no>_^_9_^_</span> specifies whether to make a video or to show each frame</li></ul>\n": "<h4>\u63d2\u503c\u4e24\u5f20\u56fe\u50cf<span translate=no>_^_0_^_</span><span translate=no>_^_1_^_</span>\u7136\u540e\u5236\u4f5c\u89c6\u9891</h4>\n<ul><li><span translate=no>_^_2_^_</span>\u662f<span translate=no>_^_3_^_</span></li>\n<li><span translate=no>_^_4_^_</span>\u662f<span translate=no>_^_5_^_</span></li>\n<li><span translate=no>_^_6_^_</span>\u662f\u56fe\u50cf\u7684\u5e27\u6570</li>\n<li><span translate=no>_^_7_^_</span>\u662f<span translate=no>_^_8_^_</span></li>\n<li><span translate=no>_^_9_^_</span>\u6307\u5b9a\u662f\u5236\u4f5c\u89c6\u9891\u8fd8\u662f\u663e\u793a\u6bcf\u4e00\u5e27</li></ul>\n",
+ "<h4>Interpolate two images <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span></h4>\n<p>We get <span translate=no>_^_2_^_</span> and <span translate=no>_^_3_^_</span>.</p>\n<p>Then interpolate to  <span translate=no>_^_4_^_</span></p>\n<p>Then get  <span translate=no>_^_5_^_</span></p>\n<ul><li><span translate=no>_^_6_^_</span> is <span translate=no>_^_7_^_</span> </li>\n<li><span translate=no>_^_8_^_</span> is <span translate=no>_^_9_^_</span> </li>\n<li><span translate=no>_^_10_^_</span> is <span translate=no>_^_11_^_</span> </li>\n<li><span translate=no>_^_12_^_</span> is <span translate=no>_^_13_^_</span></li></ul>\n": "<h4>\u63d2\u503c\u4e24\u5f20\u56fe\u50cf<span translate=no>_^_0_^_</span>\u548c<span translate=no>_^_1_^_</span></h4>\n<p>\u6211\u4eec\u5f97\u5230<span translate=no>_^_2_^_</span>\u548c<span translate=no>_^_3_^_</span>\u3002</p>\n<p>\u7136\u540e\u63d2\u5165<span translate=no>_^_4_^_</span></p>\n<p>\u7136\u540e\u5f97\u5230<span translate=no>_^_5_^_</span></p>\n<ul><li><span translate=no>_^_6_^_</span>\u662f<span translate=no>_^_7_^_</span></li>\n<li><span translate=no>_^_8_^_</span>\u662f<span translate=no>_^_9_^_</span></li>\n<li><span translate=no>_^_10_^_</span>\u662f<span translate=no>_^_11_^_</span></li>\n</ul><li><span translate=no>_^_12_^_</span>\u662f<span translate=no>_^_13_^_</span></li>\n",
+ "<h4>Sample an image step-by-step using <span translate=no>_^_0_^_</span></h4>\n<p>We sample an image step-by-step using <span translate=no>_^_1_^_</span> and at each step show the estimate <span translate=no>_^_2_^_</span></p>\n": "<h4>\u4f7f\u7528\u9010\u6b65\u5bf9\u56fe\u50cf\u8fdb\u884c\u91c7\u6837<span translate=no>_^_0_^_</span></h4>\n<p>\u6211\u4eec\u4f7f\u7528\u9010\u6b65\u5bf9\u56fe\u50cf\u8fdb\u884c\u91c7\u6837\uff0c<span translate=no>_^_1_^_</span>\u5e76\u5728\u6bcf\u4e00\u6b65\u663e\u793a\u4f30\u7b97\u503c<span translate=no>_^_2_^_</span></p>\n",
+ "<h4>Sample an image using <span translate=no>_^_0_^_</span></h4>\n<ul><li><span translate=no>_^_1_^_</span> is <span translate=no>_^_2_^_</span> </li>\n<li><span translate=no>_^_3_^_</span> is <span translate=no>_^_4_^_</span></li></ul>\n": "<h4>\u4f7f\u7528\u5bf9\u56fe\u50cf\u8fdb\u884c\u91c7\u6837<span translate=no>_^_0_^_</span></h4>\n<ul><li><span translate=no>_^_1_^_</span>\u662f<span translate=no>_^_2_^_</span></li>\n</ul><li><span translate=no>_^_3_^_</span>\u662f<span translate=no>_^_4_^_</span></li>\n",
+ "<h4>Sample from <span translate=no>_^_0_^_</span></h4>\n<span translate=no>_^_1_^_</span>": "<h4>\u6837\u672c\u6765\u81ea<span translate=no>_^_0_^_</span></h4>\n<span translate=no>_^_1_^_</span>",
+ "<p> </p>\n": "<p></p>\n",
+ "<p>20 second video </p>\n": "<p>20 \u79d2\u89c6\u9891</p>\n",
+ "<p><a href=\"utils.html\">gather</a> <span translate=no>_^_0_^_</span> </p>\n": "<p><a href=\"utils.html\">\u6536\u96c6</a><span translate=no>_^_0_^_</span></p>\n",
+ "<p><span translate=no>_^_0_^_</span> </p>\n": "<p><span translate=no>_^_0_^_</span></p>\n",
+ "<p><span translate=no>_^_0_^_</span> in a tensor </p>\n": "<p><span translate=no>_^_0_^_</span>\u5728\u5f20\u91cf\u4e2d</p>\n",
+ "<p><span translate=no>_^_0_^_</span> tensor </p>\n": "<p><span translate=no>_^_0_^_</span>\u5f20\u91cf</p>\n",
+ "<p>Add batch dimension </p>\n": "<p>\u6dfb\u52a0\u6279\u91cf\u7ef4\u5ea6</p>\n",
+ "<p>Add each image </p>\n": "<p>\u6dfb\u52a0\u6bcf\u5f20\u56fe\u7247</p>\n",
+ "<p>Add to frames </p>\n": "<p>\u6dfb\u52a0\u5230\u76f8\u6846</p>\n",
+ "<p>Create an interpolation animation </p>\n": "<p>\u521b\u5efa\u63d2\u503c\u52a8\u753b</p>\n",
+ "<p>Create configs </p>\n": "<p>\u521b\u5efa\u914d\u7f6e</p>\n",
+ "<p>Create sampler </p>\n": "<p>\u521b\u5efa\u91c7\u6837\u5668</p>\n",
+ "<p>Frames for video </p>\n": "<p>\u7528\u4e8e\u89c6\u9891\u7684\u5e27</p>\n",
+ "<p>Generate samples </p>\n": "<p>\u751f\u6210\u6837\u672c</p>\n",
+ "<p>Get <span translate=no>_^_0_^_</span> and add to frames </p>\n": "<p>\u83b7\u53d6<span translate=no>_^_0_^_</span>\u5e76\u6dfb\u52a0\u5230\u5e27</p>\n",
+ "<p>Get frames with different <span translate=no>_^_0_^_</span> </p>\n": "<p>\u83b7\u53d6\u4e0d\u540c\u7684\u5e27<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Get some images fro data </p>\n": "<p>\u4ece\u6570\u636e\u4e2d\u83b7\u53d6\u4e00\u4e9b\u56fe\u50cf</p>\n",
+ "<p>Helper function to create a video </p>\n": "<p>\u521b\u5efa\u89c6\u9891\u7684\u52a9\u624b\u51fd\u6570</p>\n",
+ "<p>Helper function to display an image </p>\n": "<p>\u663e\u793a\u56fe\u50cf\u7684\u8f85\u52a9\u51fd\u6570</p>\n",
+ "<p>Initialize </p>\n": "<p>\u521d\u59cb\u5316</p>\n",
+ "<p>Interval to log <span translate=no>_^_0_^_</span> </p>\n": "<p>\u8bb0\u5f55\u95f4\u9694<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Iterate until <span translate=no>_^_0_^_</span> steps </p>\n": "<p>\u8fed\u4ee3\u76f4\u81f3<span translate=no>_^_0_^_</span>\u6b65\u9aa4</p>\n",
+ "<p>Load custom configuration of the training run </p>\n": "<p>\u52a0\u8f7d\u8bad\u7ec3\u8fd0\u884c\u7684\u81ea\u5b9a\u4e49\u914d\u7f6e</p>\n",
+ "<p>Load training experiment </p>\n": "<p>\u8d1f\u8377\u8bad\u7ec3\u5b9e\u9a8c</p>\n",
+ "<p>Make video </p>\n": "<p>\u5236\u4f5c\u89c6\u9891</p>\n",
+ "<p>No gradients </p>\n": "<p>\u6ca1\u6709\u6e10\u53d8</p>\n",
+ "<p>Number of sampels </p>\n": "<p>\u6837\u672c\u6570\u91cf</p>\n",
+ "<p>Number of samples </p>\n": "<p>\u6837\u672c\u6570\u91cf</p>\n",
+ "<p>Return <span translate=no>_^_0_^_</span> </p>\n": "<p>\u8fd4\u56de<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Sample </p>\n": "<p>\u6837\u672c</p>\n",
+ "<p>Sample <span translate=no>_^_0_^_</span> steps </p>\n": "<p><span translate=no>_^_0_^_</span>\u6b65\u9aa4\u793a\u4f8b</p>\n",
+ "<p>Sample an image with an denoising animation </p>\n": "<p>\u4f7f\u7528\u964d\u566a\u52a8\u753b\u5bf9\u56fe\u50cf\u8fdb\u884c\u91c7\u6837</p>\n",
+ "<p>Sample from <span translate=no>_^_0_^_</span> </p>\n": "<p>\u6837\u672c\u6765\u81ea<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Set PyTorch modules for saving and loading </p>\n": "<p>\u8bbe\u7f6e\u7528\u4e8e\u4fdd\u5b58\u548c\u52a0\u8f7d\u7684 PyTorch \u6a21\u5757</p>\n",
+ "<p>Set configurations </p>\n": "<p>\u8bbe\u7f6e\u914d\u7f6e</p>\n",
+ "<p>Show frame </p>\n": "<p>\u663e\u793a\u6846\u67b6</p>\n",
+ "<p>Show images </p>\n": "<p>\u663e\u793a\u56fe\u7247</p>\n",
+ "<p>Show original images </p>\n": "<p>\u663e\u793a\u539f\u59cb\u56fe\u50cf</p>\n",
+ "<p>Start an evaluation </p>\n": "<p>\u5f00\u59cb\u8bc4\u4f30</p>\n",
+ "<p>Start evaluation </p>\n": "<p>\u5f00\u59cb\u8bc4\u4f30</p>\n",
+ "<p>To calculate</p>\n<span translate=no>_^_0_^_</span><p> </p>\n": "<p>\u8981\u8ba1\u7b97</p>\n<span translate=no>_^_0_^_</span><p></p>\n",
+ "<p>Training experiment run UUID </p>\n": "<p>\u8bad\u7ec3\u5b9e\u9a8c\u8fd0\u884c UUID</p>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the <span translate=no>_^_1_^_</span> instance </li>\n<li><span translate=no>_^_2_^_</span> is the number of channels in the image </li>\n<li><span translate=no>_^_3_^_</span> is the image size </li>\n<li><span translate=no>_^_4_^_</span> is the device of the model</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u662f\u8fd9\u4e2a\u5b9e<span translate=no>_^_1_^_</span>\u4f8b</li>\n<li><span translate=no>_^_2_^_</span>\u662f\u56fe\u50cf\u4e2d\u7684\u901a\u9053\u6570</li>\n<li><span translate=no>_^_3_^_</span>\u662f\u56fe\u50cf\u5927\u5c0f</li>\n<li><span translate=no>_^_4_^_</span>\u662f\u8be5\u578b\u53f7\u7684\u8bbe\u5907</li></ul>\n",
+ "Code to generate samples from a trained Denoising Diffusion Probabilistic Model.": "\u4ece\u7ecf\u8fc7\u8bad\u7ec3\u7684\u964d\u566a\u6269\u6563\u6982\u7387\u6a21\u578b\u751f\u6210\u6837\u672c\u7684\u4ee3\u7801\u3002",
+ "Denoising Diffusion Probabilistic Models (DDPM) evaluation/sampling": "\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM) \u8bc4\u4f30/\u91c7\u6837"
+}
@@ -0,0 +1,62 @@
+{
+ "<h1><a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a> training</h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>This trains a DDPM based model on CelebA HQ dataset. You can find the download instruction in this <a href=\"https://forums.fast.ai/t/download-celeba-hq-dataset/45873/3\">discussion on fast.ai</a>. Save the images inside <a href=\"#dataset_path\"><span translate=no>_^_1_^_</span> folder</a>.</p>\n<p>The paper had used a exponential moving average of the model with a decay of <span translate=no>_^_2_^_</span>. We have skipped this for simplicity.</p>\n": "<h1><a href=\"index.html\">\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb</a> (DDPM) \u30c8\u30ec\u30fc\u30cb\u30f3\u30b0</h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>\u3053\u308c\u306b\u3088\u308a\u3001CeleBA HQ \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067 DDPM \u30d9\u30fc\u30b9\u306e\u30e2\u30c7\u30eb\u304c\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3055\u308c\u307e\u3059\u3002\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u306e\u8aac\u660e\u306f\u3001<a href=\"https://forums.fast.ai/t/download-celeba-hq-dataset/45873/3\">fast.ai \u306e\u3053\u306e\u30c7\u30a3\u30b9\u30ab\u30c3\u30b7\u30e7\u30f3\u306b\u3042\u308a\u307e\u3059</a>\u3002<a href=\"#dataset_path\"><span translate=no>_^_1_^_</span>\u753b\u50cf\u3092\u30d5\u30a9\u30eb\u30c0\u30fc\u306b\u4fdd\u5b58\u3057\u307e\u3059</a>\u3002</p>\n<p>\u3053\u306e\u8ad6\u6587\u3067\u306f\u3001\u30e2\u30c7\u30eb\u306e\u6307\u6570\u79fb\u52d5\u5e73\u5747\u3092\u6e1b\u8870\u3055\u305b\u3066\u4f7f\u7528\u3057\u3066\u3044\u307e\u3057\u305f\u3002<span translate=no>_^_2_^_</span>\u7c21\u7565\u5316\u306e\u305f\u3081\u3001\u3053\u3053\u3067\u306f\u7701\u7565\u3057\u3066\u3044\u307e\u3059</p>\u3002\n",
+ "<h2>Configurations</h2>\n": "<h2>\u30b3\u30f3\u30d5\u30a3\u30ae\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3</h2>\n",
+ "<h3>CelebA HQ dataset</h3>\n": "<h3>CeleBA \u672c\u793e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8</h3>\n",
+ "<h3>MNIST dataset</h3>\n": "<h3>MNIST \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8</h3>\n",
+ "<h3>Sample images</h3>\n": "<h3>\u30b5\u30f3\u30d7\u30eb\u753b\u50cf</h3>\n",
+ "<h3>Train</h3>\n": "<h3>\u5217\u8eca</h3>\n",
+ "<h3>Training loop</h3>\n": "<h3>\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30eb\u30fc\u30d7</h3>\n",
+ "<p> </p>\n": "<p></p>\n",
+ "<p> Create CelebA dataset</p>\n": "<p>CeleBA \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u4f5c\u6210</p>\n",
+ "<p> Create MNIST dataset</p>\n": "<p>MNIST \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u4f5c\u6210</p>\n",
+ "<p> Get an image</p>\n": "<p>\u753b\u50cf\u3092\u53d6\u5f97</p>\n",
+ "<p> Size of the dataset</p>\n": "<p>\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u30b5\u30a4\u30ba</p>\n",
+ "<p><a href=\"index.html\">DDPM algorithm</a> </p>\n": "<p><a href=\"index.html\">DDPM \u30a2\u30eb\u30b4\u30ea\u30ba\u30e0</a></p>\n",
+ "<p><span translate=no>_^_0_^_</span> </p>\n": "<p><span translate=no>_^_0_^_</span></p>\n",
+ "<p>Adam optimizer </p>\n": "<p>\u30a2\u30c0\u30e0\u30fb\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc</p>\n",
+ "<p>Batch size </p>\n": "<p>\u30d0\u30c3\u30c1\u30b5\u30a4\u30ba</p>\n",
+ "<p>Calculate loss </p>\n": "<p>\u640d\u5931\u306e\u8a08\u7b97</p>\n",
+ "<p>CelebA images folder </p>\n": "<p>\u30bb\u30ec\u30d0\u753b\u50cf\u30d5\u30a9\u30eb\u30c0\u30fc</p>\n",
+ "<p>Compute gradients </p>\n": "<p>\u52fe\u914d\u306e\u8a08\u7b97</p>\n",
+ "<p>Create <a href=\"index.html\">DDPM class</a> </p>\n": "<p><a href=\"index.html\">DDPM \u30af\u30e9\u30b9\u306e\u4f5c\u6210</a></p>\n",
+ "<p>Create <span translate=no>_^_0_^_</span> model </p>\n": "<p><span translate=no>_^_0_^_</span>\u30e2\u30c7\u30eb\u4f5c\u6210</p>\n",
+ "<p>Create configurations </p>\n": "<p>\u69cb\u6210\u306e\u4f5c\u6210</p>\n",
+ "<p>Create dataloader </p>\n": "<p>\u30c7\u30fc\u30bf\u30ed\u30fc\u30c0\u30fc\u306e\u4f5c\u6210</p>\n",
+ "<p>Create experiment </p>\n": "<p>\u5b9f\u9a13\u3092\u4f5c\u6210</p>\n",
+ "<p>Create optimizer </p>\n": "<p>\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc\u3092\u4f5c\u6210</p>\n",
+ "<p>Dataloader </p>\n": "<p>\u30c7\u30fc\u30bf\u30ed\u30fc\u30c0\u30fc</p>\n",
+ "<p>Dataset </p>\n": "<p>\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8</p>\n",
+ "<p>Device to train the model on. <a href=\"https://docs.labml.ai/api/helpers.html#labml_helpers.device.DeviceConfigs\"><span translate=no>_^_0_^_</span></a>  picks up an available CUDA device or defaults to CPU. </p>\n": "<p>\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3059\u308b\u30c7\u30d0\u30a4\u30b9\u3002<a href=\"https://docs.labml.ai/api/helpers.html#labml_helpers.device.DeviceConfigs\"><span translate=no>_^_0_^_</span></a>\u4f7f\u7528\u53ef\u80fd\u306a CUDA \u30c7\u30d0\u30a4\u30b9\u3092\u9078\u629e\u3059\u308b\u304b\u3001\u30c7\u30d5\u30a9\u30eb\u30c8\u3067 CPU \u306b\u8a2d\u5b9a\u3057\u307e\u3059</p>\u3002\n",
+ "<p>Image logging </p>\n": "<p>\u753b\u50cf\u30ed\u30ae\u30f3\u30b0</p>\n",
+ "<p>Image size </p>\n": "<p>\u753b\u50cf\u30b5\u30a4\u30ba</p>\n",
+ "<p>Increment global step </p>\n": "<p>\u30b0\u30ed\u30fc\u30d0\u30eb\u30b9\u30c6\u30c3\u30d7\u3092\u30a4\u30f3\u30af\u30ea\u30e1\u30f3\u30c8</p>\n",
+ "<p>Initialize </p>\n": "<p>[\u521d\u671f\u5316]</p>\n",
+ "<p>Iterate through the dataset </p>\n": "<p>\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u53cd\u5fa9\u51e6\u7406</p>\n",
+ "<p>Learning rate </p>\n": "<p>\u5b66\u7fd2\u7387</p>\n",
+ "<p>List of files </p>\n": "<p>\u30d5\u30a1\u30a4\u30eb\u30ea\u30b9\u30c8</p>\n",
+ "<p>Log samples </p>\n": "<p>\u30ed\u30b0\u30b5\u30f3\u30d7\u30eb</p>\n",
+ "<p>Make the gradients zero </p>\n": "<p>\u30b0\u30e9\u30c7\u30fc\u30b7\u30e7\u30f3\u3092\u30bc\u30ed\u306b\u3059\u308b</p>\n",
+ "<p>Move data to device </p>\n": "<p>\u30c7\u30fc\u30bf\u3092\u30c7\u30d0\u30a4\u30b9\u306b\u79fb\u52d5</p>\n",
+ "<p>New line in the console </p>\n": "<p>\u30b3\u30f3\u30bd\u30fc\u30eb\u306e\u65b0\u3057\u3044\u884c</p>\n",
+ "<p>Number of channels in the image. <span translate=no>_^_0_^_</span> for RGB. </p>\n": "<p>\u753b\u50cf\u5185\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u3002<span translate=no>_^_0_^_</span>RGB \u7528\u3067\u3059\u3002</p>\n",
+ "<p>Number of channels in the initial feature map </p>\n": "<p>\u521d\u671f\u6a5f\u80fd\u30de\u30c3\u30d7\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</p>\n",
+ "<p>Number of samples to generate </p>\n": "<p>\u751f\u6210\u3059\u308b\u30b5\u30f3\u30d7\u30eb\u306e\u6570</p>\n",
+ "<p>Number of time steps <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30bf\u30a4\u30e0\u30b9\u30c6\u30c3\u30d7\u6570 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Number of training epochs </p>\n": "<p>\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30a8\u30dd\u30c3\u30af\u306e\u6570</p>\n",
+ "<p>Remove noise for <span translate=no>_^_0_^_</span> steps </p>\n": "<p><span translate=no>_^_0_^_</span>\u30b9\u30c6\u30c3\u30d7\u306e\u30ce\u30a4\u30ba\u9664\u53bb</p>\n",
+ "<p>Sample from <span translate=no>_^_0_^_</span> </p>\n": "<p>\u304b\u3089\u306e\u30b5\u30f3\u30d7\u30eb <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Sample some images </p>\n": "<p>\u3044\u304f\u3064\u304b\u306e\u753b\u50cf\u306e\u30b5\u30f3\u30d7\u30eb</p>\n",
+ "<p>Save the model </p>\n": "<p>\u30e2\u30c7\u30eb\u3092\u4fdd\u5b58\u3059\u308b</p>\n",
+ "<p>Set configurations. You can override the defaults by passing the values in the dictionary. </p>\n": "<p>\u69cb\u6210\u3092\u8a2d\u5b9a\u3057\u307e\u3059\u3002\u30c7\u30a3\u30af\u30b7\u30e7\u30ca\u30ea\u306b\u5024\u3092\u6e21\u3059\u3053\u3068\u3067\u30c7\u30d5\u30a9\u30eb\u30c8\u3092\u30aa\u30fc\u30d0\u30fc\u30e9\u30a4\u30c9\u3067\u304d\u307e\u3059\u3002</p>\n",
+ "<p>Set models for saving and loading </p>\n": "<p>\u4fdd\u5b58\u304a\u3088\u3073\u8aad\u307f\u8fbc\u307f\u7528\u306e\u30e2\u30c7\u30eb\u3092\u8a2d\u5b9a\u3059\u308b</p>\n",
+ "<p>Start and run the training loop </p>\n": "<p>\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30eb\u30fc\u30d7\u3092\u958b\u59cb\u3057\u3066\u5b9f\u884c\u3059\u308b</p>\n",
+ "<p>Take an optimization step </p>\n": "<p>\u6700\u9069\u5316\u306e\u4e00\u6b69\u3092\u8e0f\u307f\u51fa\u3059</p>\n",
+ "<p>The list of booleans that indicate whether to use attention at each resolution </p>\n": "<p>\u5404\u89e3\u50cf\u5ea6\u3067\u6ce8\u610f\u3092\u5411\u3051\u308b\u304b\u3069\u3046\u304b\u3092\u793a\u3059\u30d6\u30fc\u30ea\u30a2\u30f3\u306e\u30ea\u30b9\u30c8</p>\n",
+ "<p>The list of channel numbers at each resolution. The number of channels is <span translate=no>_^_0_^_</span> </p>\n": "<p>\u5404\u89e3\u50cf\u5ea6\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u756a\u53f7\u306e\u30ea\u30b9\u30c8\u3002\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u306f <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Track the loss </p>\n": "<p>\u640d\u5931\u3092\u30c8\u30e9\u30c3\u30ad\u30f3\u30b0</p>\n",
+ "<p>Train the model </p>\n": "<p>\u30e2\u30c7\u30eb\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0</p>\n",
+ "<p>Transformations to resize the image and convert to tensor </p>\n": "<p>\u753b\u50cf\u306e\u30b5\u30a4\u30ba\u3092\u5909\u66f4\u3057\u3066\u30c6\u30f3\u30bd\u30eb\u306b\u5909\u63db\u3059\u308b\u5909\u63db</p>\n",
+ "<p>U-Net model for <span translate=no>_^_0_^_</span> </p>\n": "<p>\u7528\u306e U-Net \u30e2\u30c7\u30eb <span translate=no>_^_0_^_</span></p>\n",
+ "Denoising Diffusion Probabilistic Models (DDPM) training": "\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM) \u30c8\u30ec\u30fc\u30cb\u30f3\u30b0",
+ "Training code for Denoising Diffusion Probabilistic Model.": "\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30b3\u30fc\u30c9"
+}
@@ -0,0 +1,62 @@
+{
+ "<h1><a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a> training</h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>This trains a DDPM based model on CelebA HQ dataset. You can find the download instruction in this <a href=\"https://forums.fast.ai/t/download-celeba-hq-dataset/45873/3\">discussion on fast.ai</a>. Save the images inside <a href=\"#dataset_path\"><span translate=no>_^_1_^_</span> folder</a>.</p>\n<p>The paper had used a exponential moving average of the model with a decay of <span translate=no>_^_2_^_</span>. We have skipped this for simplicity.</p>\n": "<h1><a href=\"index.html\">\u0dc0\u0dd2\u0dc3\u0dbb\u0dab \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2 (\u0da9\u0dd3\u0da9\u0dd3\u0db4\u0dd3\u0d91\u0db8\u0dca) \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4\u0dc0 \u0db1\u0dd2\u0dbb\u0dd6\u0db4\u0dab\u0dba</a> \u0d9a\u0dd2\u0dbb\u0dd3\u0db8</h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>\u0db8\u0dd9\u0dba \u0dc3\u0dd9\u0dbd\u0dd9\u0db6\u0dcf \u0d91\u0da0\u0dca\u0d9a\u0dd2\u0dba\u0dd4 \u0daf\u0dad\u0dca\u0dad \u0d9a\u0da7\u0dca\u0da7\u0dbd\u0dba \u0db8\u0dad \u0da9\u0dd3\u0da9\u0dd3\u0db4\u0dd3\u0d91\u0db8\u0dca \u0db4\u0daf\u0db1\u0db8\u0dca \u0d9a\u0dbb\u0d9c\u0dad\u0dca \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb\u0dba\u0dd2. <a href=\"https://forums.fast.ai/t/download-celeba-hq-dataset/45873/3\">fast.ai \u0dc4\u0dd2 \u0db8\u0dd9\u0db8 \u0dc3\u0dcf\u0d9a\u0da0\u0dca\u0da1\u0dcf\u0dc0\u0dda\u0daf\u0dd3</a> \u0db6\u0dcf\u0d9c\u0dad \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dda \u0d8b\u0db4\u0daf\u0dd9\u0dc3\u0dca \u0d94\u0db6\u0da7 \u0dc3\u0ddc\u0dba\u0dcf\u0d9c\u0dad \u0dc4\u0dd0\u0d9a\u0dd2\u0dba. <a href=\"#dataset_path\"><span translate=no>_^_1_^_</span>\u0dc6\u0ddd\u0dbd\u0dca\u0da9\u0dbb\u0dba</a> \u0dad\u0dd4\u0dc5 \u0db4\u0dd2\u0db1\u0dca\u0dad\u0dd6\u0dbb \u0dc3\u0dd4\u0dbb\u0d9a\u0dd2\u0db1\u0dca\u0db1.</p>\n<p>\u0d9a\u0da9\u0daf\u0dcf\u0dc3\u0dd2 \u0d9a \u0d9a\u0dca\u0dc2\u0dba \u0dc3\u0db8\u0d9c \u0d86\u0daf\u0dbb\u0dca\u0dc1 \u0d9d\u0dcf\u0dad\u0dd3\u0dba \u0dc0\u0dd9\u0db1\u0dc3\u0dca\u0dc0\u0db1 \u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0dba \u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0d9a\u0dbb<span translate=no>_^_2_^_</span> \u0d87\u0dad. \u0dc3\u0dbb\u0dbd \u0db6\u0dc0 \u0dc3\u0db3\u0dc4\u0dcf \u0d85\u0db4\u0dd2 \u0db8\u0dd9\u0dba \u0db8\u0d9f \u0dc4\u0dd0\u0dbb \u0d87\u0dad\u0dca\u0dad\u0dd9\u0db8\u0dd4.</p>\n",
+ "<h2>Configurations</h2>\n": "<h2>\u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dca</h2>\n",
+ "<h3>CelebA HQ dataset</h3>\n": "<h3>\u0dc3\u0dd9\u0dbd\u0dd9\u0db6\u0dcf\u0db8\u0dd6\u0dbd\u0dc3\u0dca\u0dae\u0dcf\u0db1\u0dba \u0daf\u0dad\u0dca\u0dad \u0d9a\u0da7\u0dca\u0da7\u0dbd\u0dba</h3>\n",
+ "<h3>MNIST dataset</h3>\n": "<h3>MNIST\u0daf\u0dad\u0dca\u0dad \u0d9a\u0da7\u0dca\u0da7\u0dbd\u0dba</h3>\n",
+ "<h3>Sample images</h3>\n": "<h3>\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd2\u0dbb\u0dd6\u0db4</h3>\n",
+ "<h3>Train</h3>\n": "<h3>\u0daf\u0dd4\u0db8\u0dca\u0dbb\u0dd2\u0dba</h3>\n",
+ "<h3>Training loop</h3>\n": "<h3>\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4\u0dbd\u0dd6\u0db4\u0dba</h3>\n",
+ "<p> </p>\n": "<p> </p>\n",
+ "<p> Create CelebA dataset</p>\n": "<p> \u0dc3\u0dd9\u0dbd\u0dd9\u0db6\u0dcf\u0daf\u0dad\u0dca\u0dad \u0d9a\u0da7\u0dca\u0da7\u0dbd\u0dba \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1</p>\n",
+ "<p> Create MNIST dataset</p>\n": "<p> MNIST\u0daf\u0dad\u0dca\u0dad \u0dc3\u0db8\u0dd4\u0daf\u0dcf\u0dba \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1</p>\n",
+ "<p> Get an image</p>\n": "<p> \u0dbb\u0dd6\u0db4\u0dba\u0d9a\u0dca\u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1</p>\n",
+ "<p> Size of the dataset</p>\n": "<p> \u0daf\u0dad\u0dca\u0dad\u0dc3\u0db8\u0dd4\u0daf\u0dcf\u0dba \u0db4\u0dca\u0dbb\u0db8\u0dcf\u0dab\u0dba</p>\n",
+ "<p><a href=\"index.html\">DDPM algorithm</a> </p>\n": "<p><a href=\"index.html\">\u0da9\u0dd3\u0da9\u0dd3\u0db4\u0dd3\u0d91\u0db8\u0dca \u0d87\u0dbd\u0dca\u0d9c\u0ddc\u0dbb\u0dd2\u0dad\u0db8</a> </p>\n",
+ "<p><span translate=no>_^_0_^_</span> </p>\n": "<p><span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Adam optimizer </p>\n": "<p>\u0d86\u0daf\u0db8\u0dca\u0db4\u0dca\u0dbb\u0dc1\u0dc3\u0dca\u0dad\u0d9a\u0dbb\u0dab\u0dba </p>\n",
+ "<p>Batch size </p>\n": "<p>\u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca\u0db4\u0dca\u0dbb\u0db8\u0dcf\u0dab\u0dba </p>\n",
+ "<p>Calculate loss </p>\n": "<p>\u0d85\u0dbd\u0dcf\u0db7\u0dba\u0d9c\u0dab\u0db1\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>CelebA images folder </p>\n": "<p>\u0dc3\u0dd9\u0dbd\u0dd9\u0db6\u0dcf\u0db4\u0dd2\u0db1\u0dca\u0dad\u0dd6\u0dbb \u0dc6\u0ddd\u0dbd\u0dca\u0da9\u0dbb\u0dba </p>\n",
+ "<p>Compute gradients </p>\n": "<p>\u0d85\u0db1\u0dd4\u0d9a\u0dca\u0dbb\u0db8\u0dd2\u0d9a\u0d9c\u0dab\u0db1\u0dba </p>\n",
+ "<p>Create <a href=\"index.html\">DDPM class</a> </p>\n": "<p><a href=\"index.html\">DDPM \u0db4\u0db1\u0dca\u0dad\u0dd2</a> \u0db1\u0dd2\u0dbb\u0dca\u0db8\u0dcf\u0dab\u0dba </p>\n",
+ "<p>Create <span translate=no>_^_0_^_</span> model </p>\n": "<p><span translate=no>_^_0_^_</span> \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Create configurations </p>\n": "<p>\u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0dba\u0db1\u0dca\u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Create dataloader </p>\n": "<p>\u0daf\u0dad\u0dca\u0dad\u0d9a\u0dcf\u0dbb\u0d9a\u0dba \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Create experiment </p>\n": "<p>\u0d85\u0dad\u0dca\u0dc4\u0daf\u0dcf\u0db6\u0dd0\u0dbd\u0dd3\u0db8 \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Create optimizer </p>\n": "<p>\u0db4\u0dca\u0dbb\u0dc1\u0dc3\u0dca\u0dad\u0d9a\u0dbb\u0dab\u0dba\u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Dataloader </p>\n": "<p>\u0daf\u0dad\u0dca\u0dad\u0d9a\u0dcf\u0dbb\u0d9a\u0dba </p>\n",
+ "<p>Dataset </p>\n": "<p>\u0daf\u0dad\u0dca\u0dad\u0d9a\u0da7\u0dca\u0da7\u0dbd\u0dba </p>\n",
+ "<p>Device to train the model on. <a href=\"https://docs.labml.ai/api/helpers.html#labml_helpers.device.DeviceConfigs\"><span translate=no>_^_0_^_</span></a>  picks up an available CUDA device or defaults to CPU. </p>\n": "<p>\u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dda \u0d8b\u0db4\u0d9a\u0dbb\u0dab\u0dba. <a href=\"https://docs.labml.ai/api/helpers.html#labml_helpers.device.DeviceConfigs\"><span translate=no>_^_0_^_</span></a> \u0dbd\u0db6\u0dcf \u0d9c\u0dad \u0dc4\u0dd0\u0d9a\u0dd2 CUDA \u0d8b\u0db4\u0dcf\u0d82\u0d9c\u0dba\u0d9a\u0dca \u0d85\u0dc4\u0dd4\u0dbd\u0db1\u0dc0\u0dcf \u0dc4\u0ddd CPU \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0da7 \u0db4\u0dd9\u0dbb\u0db1\u0dd2\u0db8\u0dd2. </p>\n",
+ "<p>Image logging </p>\n": "<p>\u0dbb\u0dd6\u0db4\u0dbd\u0ddc\u0d9c\u0dca \u0dc0\u0dd3\u0db8 </p>\n",
+ "<p>Image size </p>\n": "<p>\u0dbb\u0dd6\u0db4\u0db4\u0dca\u0dbb\u0db8\u0dcf\u0dab\u0dba </p>\n",
+ "<p>Increment global step </p>\n": "<p>\u0d9c\u0ddd\u0dbd\u0dd3\u0dba\u0db4\u0dd2\u0dba\u0dc0\u0dbb \u0dc0\u0dd0\u0da9\u0dd2 \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 </p>\n",
+ "<p>Initialize </p>\n": "<p>\u0d86\u0dbb\u0db8\u0dca\u0db7\u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Iterate through the dataset </p>\n": "<p>\u0daf\u0dad\u0dca\u0dad\u0dc3\u0db8\u0dd4\u0daf\u0dcf\u0dba \u0dc4\u0dbb\u0dc4\u0dcf \u0db1\u0dd0\u0dc0\u0dad \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Learning rate </p>\n": "<p>\u0d89\u0d9c\u0dd9\u0db1\u0dd4\u0db8\u0dca\u0d85\u0db1\u0dd4\u0db4\u0dcf\u0dad\u0dba </p>\n",
+ "<p>List of files </p>\n": "<p>\u0d9c\u0ddc\u0db1\u0dd4\u0dbd\u0dd0\u0dba\u0dd2\u0dc3\u0dca\u0dad\u0dd4\u0dc0 </p>\n",
+ "<p>Log samples </p>\n": "<p>\u0dbd\u0ddc\u0d9c\u0dca\u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd </p>\n",
+ "<p>Make the gradients zero </p>\n": "<p>\u0d85\u0db1\u0dd4\u0d9a\u0dca\u0dbb\u0db8\u0dd2\u0d9a\u0dc1\u0dd4\u0db1\u0dca\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Move data to device </p>\n": "<p>\u0d8b\u0db4\u0dcf\u0d82\u0d9c\u0dba\u0dc0\u0dd9\u0dad \u0daf\u0dad\u0dca\u0dad \u0d9c\u0dd9\u0db1\u0dba\u0db1\u0dca\u0db1 </p>\n",
+ "<p>New line in the console </p>\n": "<p>\u0d9a\u0ddc\u0db1\u0dca\u0dc3\u0ddd\u0dbd\u0dba\u0dda\u0db1\u0dc0 \u0dbb\u0dda\u0d9b\u0dcf\u0dc0\u0d9a\u0dca </p>\n",
+ "<p>Number of channels in the image. <span translate=no>_^_0_^_</span> for RGB. </p>\n": "<p>\u0dbb\u0dd6\u0db4\u0dba\u0dda\u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1. <span translate=no>_^_0_^_</span> RGB \u0dc3\u0db3\u0dc4\u0dcf. </p>\n",
+ "<p>Number of channels in the initial feature map </p>\n": "<p>\u0d86\u0dbb\u0db8\u0dca\u0db7\u0d9a\u0dc0\u0dd2\u0dc1\u0dda\u0dc2\u0dcf\u0d82\u0d9c \u0dc3\u0dd2\u0dad\u0dd2\u0dba\u0db8\u0dda \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1 </p>\n",
+ "<p>Number of samples to generate </p>\n": "<p>\u0d8b\u0dad\u0dca\u0db4\u0dcf\u0daf\u0db1\u0dba\u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0da7 \u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd \u0d9c\u0dab\u0db1 </p>\n",
+ "<p>Number of time steps <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0d9a\u0dcf\u0dbd\u0db4\u0dd2\u0dba\u0dc0\u0dbb \u0d9c\u0dab\u0db1 <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Number of training epochs </p>\n": "<p>\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4\u0d91\u0db4\u0ddc\u0da0\u0dca \u0d9c\u0dab\u0db1 </p>\n",
+ "<p>Remove noise for <span translate=no>_^_0_^_</span> steps </p>\n": "<p><span translate=no>_^_0_^_</span> \u0db4\u0dd2\u0dba\u0dc0\u0dbb \u0dc3\u0db3\u0dc4\u0dcf \u0dc1\u0db6\u0dca\u0daf\u0dba \u0d89\u0dc0\u0dad\u0dca \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Sample from <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0dc0\u0dd9\u0dad\u0dd2\u0db1\u0dca\u0db1\u0dd2\u0dba\u0dd0\u0daf\u0dd2\u0dba <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Sample some images </p>\n": "<p>\u0db4\u0dd2\u0db1\u0dca\u0dad\u0dd6\u0dbb\u0d9a\u0dd2\u0dc4\u0dd2\u0db4\u0dba\u0d9a\u0dca \u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Save the model </p>\n": "<p>\u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0dc3\u0dd4\u0dbb\u0d9a\u0dd2\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Set configurations. You can override the defaults by passing the values in the dictionary. </p>\n": "<p>\u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0dba\u0db1\u0dca\u0dc3\u0d9a\u0dc3\u0db1\u0dca\u0db1. \u0dc1\u0db6\u0dca\u0daf\u0d9a\u0ddd\u0dc2\u0dba\u0dda \u0d85\u0d9c\u0dba\u0db1\u0dca \u0dc3\u0db8\u0dca\u0db8\u0dad \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dd9\u0db1\u0dca \u0d94\u0db6\u0da7 \u0db4\u0dd9\u0dbb\u0db1\u0dd2\u0db8\u0dd2 \u0d85\u0db7\u0dd2\u0db6\u0dc0\u0dcf \u0dba\u0dcf \u0dc4\u0dd0\u0d9a\u0dd2\u0dba. </p>\n",
+ "<p>Set models for saving and loading </p>\n": "<p>\u0d89\u0dad\u0dd2\u0dbb\u0dd2\u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0dc4 \u0db4\u0dd0\u0da7\u0dc0\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2 \u0dc3\u0d9a\u0dc3\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Start and run the training loop </p>\n": "<p>\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4\u0dbd\u0dd6\u0db4\u0dba \u0d86\u0dbb\u0db8\u0dca\u0db7 \u0d9a\u0dbb \u0d9a\u0dca\u0dbb\u0dd2\u0dba\u0dcf\u0dad\u0dca\u0db8\u0d9a \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Take an optimization step </p>\n": "<p>\u0db4\u0dca\u0dbb\u0dc1\u0dc3\u0dca\u0dad\u0dd2\u0d9a\u0dbb\u0dab\u0db4\u0dd2\u0dba\u0dc0\u0dbb\u0d9a\u0dca \u0d9c\u0db1\u0dca\u0db1 </p>\n",
+ "<p>The list of booleans that indicate whether to use attention at each resolution </p>\n": "<p>\u0d91\u0d9a\u0dca\u0d91\u0d9a\u0dca \u0dba\u0ddd\u0da2\u0db1\u0dcf\u0dc0\u0dda\u0daf\u0dd3 \u0d85\u0dc0\u0db0\u0dcf\u0db1\u0dba \u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0d9a\u0dc5 \u0dba\u0dd4\u0dad\u0dd4\u0daf \u0dba\u0db1\u0dca\u0db1 \u0db4\u0dd9\u0db1\u0dca\u0dc0\u0db1 \u0db6\u0dd6\u0dbd\u0dd2\u0dba\u0db1\u0dca \u0dbd\u0dd0\u0dba\u0dd2\u0dc3\u0dca\u0dad\u0dd4\u0dc0 </p>\n",
+ "<p>The list of channel numbers at each resolution. The number of channels is <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0d91\u0d9a\u0dca\u0d91\u0d9a\u0dca \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0dda \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d85\u0d82\u0d9a \u0dbd\u0dd0\u0dba\u0dd2\u0dc3\u0dca\u0dad\u0dd4\u0dc0. \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1 \u0dc0\u0dda <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Track the loss </p>\n": "<p>\u0d85\u0dbd\u0dcf\u0db7\u0dba\u0dbd\u0dd4\u0dc4\u0dd4\u0db6\u0db3\u0dd2\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Train the model </p>\n": "<p>\u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Transformations to resize the image and convert to tensor </p>\n": "<p>\u0dbb\u0dd6\u0db4\u0dba\u0dc0\u0dd9\u0db1\u0dc3\u0dca \u0d9a\u0dbb \u0da7\u0dd9\u0db1\u0dca\u0dc3\u0dbb\u0dca \u0db6\u0dc0\u0da7 \u0db4\u0dbb\u0dd2\u0dc0\u0dbb\u0dca\u0dad\u0db1\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0db4\u0dbb\u0dd2\u0dc0\u0dbb\u0dca\u0dad\u0db1\u0dba\u0db1\u0dca </p>\n",
+ "<p>U-Net model for <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0dc3\u0db3\u0dc4\u0dcfU-Net \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba <span translate=no>_^_0_^_</span> </p>\n",
+ "Denoising Diffusion Probabilistic Models (DDPM) training": "\u0dc0\u0dd2\u0dc3\u0dbb\u0dab \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2 (\u0da9\u0dd3\u0da9\u0dd3\u0db4\u0dd3\u0d91\u0db8\u0dca) \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4\u0dc0 \u0db1\u0dd2\u0dbb\u0dd6\u0db4\u0dab\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8",
+ "Training code for Denoising Diffusion Probabilistic Model.": "Denoising Diffusion \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf\u0dc0 \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba \u0dc3\u0db3\u0dc4\u0dcf \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dda\u0dad\u0dba."
+}
@@ -0,0 +1,62 @@
+{
+ "<h1><a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a> training</h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>This trains a DDPM based model on CelebA HQ dataset. You can find the download instruction in this <a href=\"https://forums.fast.ai/t/download-celeba-hq-dataset/45873/3\">discussion on fast.ai</a>. Save the images inside <a href=\"#dataset_path\"><span translate=no>_^_1_^_</span> folder</a>.</p>\n<p>The paper had used a exponential moving average of the model with a decay of <span translate=no>_^_2_^_</span>. We have skipped this for simplicity.</p>\n": "<h1><a href=\"index.html\">\u964d\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM)</a> \u8bad\u7ec3</h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>\u8fd9\u5c06\u57fa\u4e8e CeleBA HQ \u6570\u636e\u96c6\u8bad\u7ec3\u57fa\u4e8e DDPM \u7684\u6a21\u578b\u3002\u4f60\u53ef\u4ee5\u5728 <a href=\"https://forums.fast.ai/t/download-celeba-hq-dataset/45873/3\">fast.ai \u7684\u8ba8\u8bba</a>\u4e2d\u627e\u5230\u4e0b\u8f7d\u8bf4\u660e\u3002\u5c06\u56fe\u50cf\u4fdd\u5b58\u5728<a href=\"#dataset_path\"><span translate=no>_^_1_^_</span>\u6587\u4ef6\u5939\u4e2d</a>\u3002</p>\n<p>\u8be5\u8bba\u6587\u4f7f\u7528\u4e86\u8be5\u6a21\u578b\u7684\u6307\u6570\u79fb\u52a8\u5e73\u5747\u7ebf\uff0c\u5176\u8870\u51cf\u91cf\u4e3a<span translate=no>_^_2_^_</span>\u3002\u4e3a\u7b80\u5355\u8d77\u89c1\uff0c\u6211\u4eec\u8df3\u8fc7\u4e86\u8fd9\u4e2a\u3002</p>\n",
+ "<h2>Configurations</h2>\n": "<h2>\u914d\u7f6e</h2>\n",
+ "<h3>CelebA HQ dataset</h3>\n": "<h3>CeleBA HQ \u6570\u636e\u96c6</h3>\n",
+ "<h3>MNIST dataset</h3>\n": "<h3>MNIST \u6570\u636e\u96c6</h3>\n",
+ "<h3>Sample images</h3>\n": "<h3>\u6837\u672c\u56fe\u7247</h3>\n",
+ "<h3>Train</h3>\n": "<h3>\u706b\u8f66</h3>\n",
+ "<h3>Training loop</h3>\n": "<h3>\u8bad\u7ec3\u5faa\u73af</h3>\n",
+ "<p> </p>\n": "<p></p>\n",
+ "<p> Create CelebA dataset</p>\n": "<p>\u521b\u5efa CeleBA \u6570\u636e\u96c6</p>\n",
+ "<p> Create MNIST dataset</p>\n": "<p>\u521b\u5efa MNIST \u6570\u636e\u96c6</p>\n",
+ "<p> Get an image</p>\n": "<p>\u83b7\u53d6\u4e00\u5f20\u56fe\u7247</p>\n",
+ "<p> Size of the dataset</p>\n": "<p>\u6570\u636e\u96c6\u7684\u5927\u5c0f</p>\n",
+ "<p><a href=\"index.html\">DDPM algorithm</a> </p>\n": "<p><a href=\"index.html\">DDPM \u7b97\u6cd5</a></p>\n",
+ "<p><span translate=no>_^_0_^_</span> </p>\n": "<p><span translate=no>_^_0_^_</span></p>\n",
+ "<p>Adam optimizer </p>\n": "<p>Adam \u4f18\u5316\u5668</p>\n",
+ "<p>Batch size </p>\n": "<p>\u6279\u91cf\u5927\u5c0f</p>\n",
+ "<p>Calculate loss </p>\n": "<p>\u8ba1\u7b97\u635f\u5931</p>\n",
+ "<p>CelebA images folder </p>\n": "<p>CeleBA \u56fe\u7247\u6587\u4ef6\u5939</p>\n",
+ "<p>Compute gradients </p>\n": "<p>\u8ba1\u7b97\u68af\u5ea6</p>\n",
+ "<p>Create <a href=\"index.html\">DDPM class</a> </p>\n": "<p>\u521b\u5efa <a href=\"index.html\">DDPM \u7c7b</a></p>\n",
+ "<p>Create <span translate=no>_^_0_^_</span> model </p>\n": "<p>\u521b\u5efa<span translate=no>_^_0_^_</span>\u6a21\u578b</p>\n",
+ "<p>Create configurations </p>\n": "<p>\u521b\u5efa\u914d\u7f6e</p>\n",
+ "<p>Create dataloader </p>\n": "<p>\u521b\u5efa\u6570\u636e\u52a0\u8f7d\u5668</p>\n",
+ "<p>Create experiment </p>\n": "<p>\u521b\u5efa\u5b9e\u9a8c</p>\n",
+ "<p>Create optimizer </p>\n": "<p>\u521b\u5efa\u4f18\u5316\u5668</p>\n",
+ "<p>Dataloader </p>\n": "<p>\u6570\u636e\u52a0\u8f7d\u5668</p>\n",
+ "<p>Dataset </p>\n": "<p>\u6570\u636e\u96c6</p>\n",
+ "<p>Device to train the model on. <a href=\"https://docs.labml.ai/api/helpers.html#labml_helpers.device.DeviceConfigs\"><span translate=no>_^_0_^_</span></a>  picks up an available CUDA device or defaults to CPU. </p>\n": "<p>\u7528\u4e8e\u8bad\u7ec3\u6a21\u578b\u7684\u8bbe\u5907\u3002<a href=\"https://docs.labml.ai/api/helpers.html#labml_helpers.device.DeviceConfigs\"><span translate=no>_^_0_^_</span></a>\u9009\u62e9\u53ef\u7528\u7684 CUDA \u8bbe\u5907\u6216\u9ed8\u8ba4\u4e3a CPU\u3002</p>\n",
+ "<p>Image logging </p>\n": "<p>\u56fe\u50cf\u65e5\u5fd7\u8bb0\u5f55</p>\n",
+ "<p>Image size </p>\n": "<p>\u56fe\u50cf\u5927\u5c0f</p>\n",
+ "<p>Increment global step </p>\n": "<p>\u9012\u589e\u5168\u5c40\u6b65\u957f</p>\n",
+ "<p>Initialize </p>\n": "<p>\u521d\u59cb\u5316</p>\n",
+ "<p>Iterate through the dataset </p>\n": "<p>\u904d\u5386\u6570\u636e\u96c6</p>\n",
+ "<p>Learning rate </p>\n": "<p>\u5b66\u4e60\u7387</p>\n",
+ "<p>List of files </p>\n": "<p>\u6587\u4ef6\u6e05\u5355</p>\n",
+ "<p>Log samples </p>\n": "<p>\u65e5\u5fd7\u6837\u672c</p>\n",
+ "<p>Make the gradients zero </p>\n": "<p>\u5c06\u6e10\u53d8\u8bbe\u4e3a\u96f6</p>\n",
+ "<p>Move data to device </p>\n": "<p>\u5c06\u6570\u636e\u79fb\u52a8\u5230\u8bbe\u5907</p>\n",
+ "<p>New line in the console </p>\n": "<p>\u63a7\u5236\u53f0\u4e2d\u7684\u65b0\u884c</p>\n",
+ "<p>Number of channels in the image. <span translate=no>_^_0_^_</span> for RGB. </p>\n": "<p>\u56fe\u50cf\u4e2d\u7684\u901a\u9053\u6570\u3002<span translate=no>_^_0_^_</span>\u5bf9\u4e8e RGB\u3002</p>\n",
+ "<p>Number of channels in the initial feature map </p>\n": "<p>\u521d\u59cb\u7279\u5f81\u56fe\u4e2d\u7684\u9891\u9053\u6570\u91cf</p>\n",
+ "<p>Number of samples to generate </p>\n": "<p>\u8981\u751f\u6210\u7684\u6837\u672c\u6570</p>\n",
+ "<p>Number of time steps <span translate=no>_^_0_^_</span> </p>\n": "<p>\u65f6\u95f4\u6b65\u6570<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Number of training epochs </p>\n": "<p>\u8bad\u7ec3\u5468\u671f\u7684\u6570\u91cf</p>\n",
+ "<p>Remove noise for <span translate=no>_^_0_^_</span> steps </p>\n": "<p>\u6d88\u9664<span translate=no>_^_0_^_</span>\u53f0\u9636\u566a\u97f3</p>\n",
+ "<p>Sample from <span translate=no>_^_0_^_</span> </p>\n": "<p>\u6837\u672c\u6765\u81ea<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Sample some images </p>\n": "<p>\u5bf9\u4e00\u4e9b\u56fe\u50cf\u8fdb\u884c\u91c7\u6837</p>\n",
+ "<p>Save the model </p>\n": "<p>\u4fdd\u5b58\u6a21\u578b</p>\n",
+ "<p>Set configurations. You can override the defaults by passing the values in the dictionary. </p>\n": "<p>\u8bbe\u7f6e\u914d\u7f6e\u3002\u60a8\u53ef\u4ee5\u901a\u8fc7\u5728\u5b57\u5178\u4e2d\u4f20\u9012\u503c\u6765\u8986\u76d6\u9ed8\u8ba4\u503c\u3002</p>\n",
+ "<p>Set models for saving and loading </p>\n": "<p>\u8bbe\u7f6e\u7528\u4e8e\u4fdd\u5b58\u548c\u52a0\u8f7d\u7684\u6a21\u578b</p>\n",
+ "<p>Start and run the training loop </p>\n": "<p>\u542f\u52a8\u5e76\u8fd0\u884c\u8bad\u7ec3\u5faa\u73af</p>\n",
+ "<p>Take an optimization step </p>\n": "<p>\u91c7\u53d6\u4f18\u5316\u6b65\u9aa4</p>\n",
+ "<p>The list of booleans that indicate whether to use attention at each resolution </p>\n": "<p>\u6307\u793a\u662f\u5426\u5728\u6bcf\u4e2a\u5206\u8fa8\u7387\u4e0b\u4f7f\u7528\u6ce8\u610f\u529b\u7684\u5e03\u5c14\u503c\u5217\u8868</p>\n",
+ "<p>The list of channel numbers at each resolution. The number of channels is <span translate=no>_^_0_^_</span> </p>\n": "<p>\u6bcf\u79cd\u5206\u8fa8\u7387\u4e0b\u7684\u901a\u9053\u7f16\u53f7\u5217\u8868\u3002\u9891\u9053\u7684\u6570\u91cf\u662f<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Track the loss </p>\n": "<p>\u8ffd\u8e2a\u635f\u5931</p>\n",
+ "<p>Train the model </p>\n": "<p>\u8bad\u7ec3\u6a21\u578b</p>\n",
+ "<p>Transformations to resize the image and convert to tensor </p>\n": "<p>\u7528\u4e8e\u8c03\u6574\u56fe\u50cf\u5927\u5c0f\u5e76\u8f6c\u6362\u4e3a\u5f20\u91cf\u7684\u8f6c\u6362</p>\n",
+ "<p>U-Net model for <span translate=no>_^_0_^_</span> </p>\n": "<p>U-Net \u6a21\u578b\u7528\u4e8e<span translate=no>_^_0_^_</span></p>\n",
+ "Denoising Diffusion Probabilistic Models (DDPM) training": "\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM) \u8bad\u7ec3",
+ "Training code for Denoising Diffusion Probabilistic Model.": "\u964d\u566a\u6269\u6563\u6982\u7387\u6a21\u578b\u7684\u8bad\u7ec3\u4ee3\u7801\u3002"
+}
@@ -0,0 +1,4 @@
+{
+ "<h1><a href=\"https://nn.labml.ai/diffusion/ddpm/index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a></h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>This is a <a href=\"https://pytorch.org\">PyTorch</a> implementation/tutorial of the paper <a href=\"https://arxiv.org/abs/2006.11239\">Denoising Diffusion Probabilistic Models</a>.</p>\n<p>In simple terms, we get an image from data and add noise step by step. Then We train a model to predict that noise at each step and use the model to generate images.</p>\n<p>Here is the <a href=\"https://nn.labml.ai/diffusion/ddpm/unet.html\">UNet model</a> that predicts the noise and <a href=\"https://nn.labml.ai/diffusion/ddpm/experiment.html\">training code</a>. <a href=\"https://nn.labml.ai/diffusion/ddpm/evaluate.html\">This file</a> can generate samples and interpolations from a trained model. </p>\n": "<h1><a href=\"https://nn.labml.ai/diffusion/ddpm/index.html\">\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM)</a></h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p><a href=\"https://arxiv.org/abs/2006.11239\">\u3053\u308c\u306f\u3001\u8ad6\u6587\u300c\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb\u300d<a href=\"https://pytorch.org\">\u306ePyTorch\u5b9f\u88c5/\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3067\u3059</a>\u3002</a></p>\n<p>\u7c21\u5358\u306b\u8a00\u3046\u3068\u3001\u30c7\u30fc\u30bf\u304b\u3089\u753b\u50cf\u3092\u53d6\u5f97\u3057\u3001\u6bb5\u968e\u7684\u306b\u30ce\u30a4\u30ba\u3092\u8ffd\u52a0\u3057\u307e\u3059\u3002\u6b21\u306b\u3001\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u3066\u5404\u30b9\u30c6\u30c3\u30d7\u3067\u305d\u306e\u30ce\u30a4\u30ba\u3092\u4e88\u6e2c\u3057\u3001\u305d\u306e\u30e2\u30c7\u30eb\u3092\u4f7f\u7528\u3057\u3066\u753b\u50cf\u3092\u751f\u6210\u3057\u307e\u3059\u3002</p>\n<p><a href=\"https://nn.labml.ai/diffusion/ddpm/unet.html\"><a href=\"https://nn.labml.ai/diffusion/ddpm/experiment.html\">\u30ce\u30a4\u30ba\u3068\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30b3\u30fc\u30c9\u3092\u4e88\u6e2c\u3059\u308b</a> uNet \u30e2\u30c7\u30eb\u3092\u6b21\u306b\u793a\u3057\u307e\u3059</a>\u3002<a href=\"https://nn.labml.ai/diffusion/ddpm/evaluate.html\">\u3053\u306e\u30d5\u30a1\u30a4\u30eb\u3067\u306f</a>\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u6e08\u307f\u306e\u30e2\u30c7\u30eb\u304b\u3089\u30b5\u30f3\u30d7\u30eb\u3068\u88dc\u9593\u3092\u751f\u6210\u3067\u304d\u307e\u3059</p>\u3002\n",
+ "Denoising Diffusion Probabilistic Models (DDPM)": "\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM)"
+}
@@ -0,0 +1,4 @@
+{
+ "<h1><a href=\"https://nn.labml.ai/diffusion/ddpm/index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a></h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>This is a <a href=\"https://pytorch.org\">PyTorch</a> implementation/tutorial of the paper <a href=\"https://arxiv.org/abs/2006.11239\">Denoising Diffusion Probabilistic Models</a>.</p>\n<p>In simple terms, we get an image from data and add noise step by step. Then We train a model to predict that noise at each step and use the model to generate images.</p>\n<p>Here is the <a href=\"https://nn.labml.ai/diffusion/ddpm/unet.html\">UNet model</a> that predicts the noise and <a href=\"https://nn.labml.ai/diffusion/ddpm/experiment.html\">training code</a>. <a href=\"https://nn.labml.ai/diffusion/ddpm/evaluate.html\">This file</a> can generate samples and interpolations from a trained model. </p>\n": "<h1><a href=\"https://nn.labml.ai/diffusion/ddpm/index.html\">\u0dc0\u0dd2\u0dc3\u0dbb\u0dab \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf\u0dc0 \u0d86\u0d9a\u0dd8\u0dad\u0dd2 \u0db1\u0dd2\u0dbb\u0dd6\u0db4\u0dab\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 (DDPM)</a></h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>\u0db8\u0dd9\u0dba <a href=\"https://pytorch.org\">PyTorch</a> \u0d9a\u0dca\u0dbb\u0dd2\u0dba\u0dcf\u0dad\u0dca\u0db8\u0d9a \u0d9a\u0dd2\u0dbb\u0dd3\u0db8/\u0db1\u0dd2\u0db6\u0db1\u0dca\u0db0\u0db1\u0dba\u0d9a\u0dd2 \u0d9a\u0da9\u0daf\u0dcf\u0dc3\u0dd2 <a href=\"https://arxiv.org/abs/2006.11239\">Denoising Diffusion Probilistic \u0d86\u0d9a\u0dd8\u0dad\u0dd2</a>.</p>\n<p>\u0dc3\u0dbb\u0dc5\u0dc0 \u0d9a\u0dd2\u0dc0\u0dc4\u0ddc\u0dad\u0dca, \u0d85\u0db4\u0dd2 \u0daf\u0dad\u0dca\u0dad \u0dc0\u0dbd\u0dd2\u0db1\u0dca \u0dbb\u0dd6\u0db4\u0dba\u0d9a\u0dca \u0dbd\u0db6\u0dcf\u0d9c\u0dd9\u0db1 \u0db4\u0dd2\u0dba\u0dc0\u0dbb\u0dd9\u0db1\u0dca \u0db4\u0dd2\u0dba\u0dc0\u0dbb \u0dc1\u0db6\u0dca\u0daf\u0dba \u0d91\u0d9a\u0dca \u0d9a\u0dbb\u0db8\u0dd4. \u0d89\u0db1\u0dca\u0db4\u0dc3\u0dd4 \u0d85\u0db4\u0dd2 \u0dc3\u0dd1\u0db8 \u0db4\u0dd2\u0dba\u0dc0\u0dbb\u0d9a\u0daf\u0dd3\u0db8 \u0d91\u0db8 \u0dc1\u0db6\u0dca\u0daf\u0dba \u0db4\u0dd4\u0dbb\u0ddd\u0d9a\u0dae\u0db1\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0da7 \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb \u0dbb\u0dd6\u0db4 \u0da2\u0db1\u0db1\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0da7 \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba \u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0d9a\u0dbb\u0db8\u0dd4.</p>\n<p>\u0dc1\u0db6\u0dca\u0daf\u0dba \u0dc3\u0dc4 <a href=\"https://nn.labml.ai/diffusion/ddpm/experiment.html\">\u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dda\u0dad\u0dba</a> \u0db4\u0dd4\u0dbb\u0ddd\u0d9a\u0dae\u0db1\u0dba \u0d9a\u0dbb\u0db1 <a href=\"https://nn.labml.ai/diffusion/ddpm/unet.html\">UNET \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba</a> \u0db8\u0dd9\u0db1\u0dca\u0db1. <a href=\"https://nn.labml.ai/diffusion/ddpm/evaluate.html\">\u0db8\u0dd9\u0db8 \u0d9c\u0ddc\u0db1\u0dd4\u0dc0\u0da7</a> \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dd2\u0db1\u0dca \u0dc3\u0dcf\u0db8\u0dca\u0db4\u0dbd \u0dc3\u0dc4 \u0d85\u0db1\u0dca\u0dad\u0dbb\u0dca\u0db1\u0dd2\u0dc0\u0dda\u0dc1\u0db1\u0dba\u0db1\u0dca \u0da2\u0db1\u0db1\u0dba \u0d9a\u0dc5 \u0dc4\u0dd0\u0d9a\u0dd2\u0dba.</p>\n",
+ "Denoising Diffusion Probabilistic Models (DDPM)": "\u0dc0\u0dd2\u0dc3\u0dbb\u0dab \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf\u0dc0 \u0d86\u0d9a\u0dd8\u0dad\u0dd2 \u0db1\u0dd2\u0dbb\u0dd6\u0db4\u0dab\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 (DDPM)"
+}
@@ -0,0 +1,4 @@
+{
+ "<h1><a href=\"https://nn.labml.ai/diffusion/ddpm/index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a></h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>This is a <a href=\"https://pytorch.org\">PyTorch</a> implementation/tutorial of the paper <a href=\"https://arxiv.org/abs/2006.11239\">Denoising Diffusion Probabilistic Models</a>.</p>\n<p>In simple terms, we get an image from data and add noise step by step. Then We train a model to predict that noise at each step and use the model to generate images.</p>\n<p>Here is the <a href=\"https://nn.labml.ai/diffusion/ddpm/unet.html\">UNet model</a> that predicts the noise and <a href=\"https://nn.labml.ai/diffusion/ddpm/experiment.html\">training code</a>. <a href=\"https://nn.labml.ai/diffusion/ddpm/evaluate.html\">This file</a> can generate samples and interpolations from a trained model. </p>\n": "<h1><a href=\"https://nn.labml.ai/diffusion/ddpm/index.html\">\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM)</a></h1>\n<p><a href=\"https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/diffusion/ddpm/experiment.ipynb\"><span translate=no>_^_0_^_</span></a></p>\n<p>\u8fd9\u662f\u300a<a href=\"https://arxiv.org/abs/2006.11239\">\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b</a>\u300b\u8bba\u6587\u7684 <a href=\"https://pytorch.org\">PyTorch</a> \u5b9e\u73b0/\u6559\u7a0b\u3002</p>\n<p>\u7b80\u800c\u8a00\u4e4b\uff0c\u6211\u4eec\u4ece\u6570\u636e\u4e2d\u83b7\u53d6\u56fe\u50cf\u5e76\u9010\u6b65\u6dfb\u52a0\u566a\u70b9\u3002\u7136\u540e\uff0c\u6211\u4eec\u8bad\u7ec3\u4e00\u4e2a\u6a21\u578b\u6765\u9884\u6d4b\u6bcf\u4e2a\u6b65\u9aa4\u7684\u566a\u58f0\uff0c\u5e76\u4f7f\u7528\u8be5\u6a21\u578b\u751f\u6210\u56fe\u50cf\u3002</p>\n<p>\u8fd9\u662f\u9884\u6d4b\u566a\u58f0\u548c<a href=\"https://nn.labml.ai/diffusion/ddpm/experiment.html\">\u8bad\u7ec3\u4ee3\u7801</a>\u7684 <a href=\"https://nn.labml.ai/diffusion/ddpm/unet.html\">UNet \u6a21\u578b</a>\u3002<a href=\"https://nn.labml.ai/diffusion/ddpm/evaluate.html\">\u6b64\u6587\u4ef6</a>\u53ef\u4ee5\u4ece\u7ecf\u8fc7\u8bad\u7ec3\u7684\u6a21\u578b\u751f\u6210\u6837\u672c\u548c\u63d2\u503c\u3002</p>\n",
+ "Denoising Diffusion Probabilistic Models (DDPM)": "\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM)"
+}
@@ -0,0 +1,76 @@
+{
+ "<h1>U-Net model for <a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a></h1>\n<p>This is a <a href=\"../../unet/index.html\">U-Net</a> based model to predict noise <span translate=no>_^_0_^_</span>.</p>\n<p>U-Net is a gets it&#x27;s name from the U shape in the model diagram. It processes a given image by progressively lowering (halving) the feature map resolution and then increasing the resolution. There are pass-through connection at each resolution.</p>\n<p><span translate=no>_^_1_^_</span></p>\n<p>This implementation contains a bunch of modifications to original U-Net (residual blocks, multi-head attention)  and also adds time-step embeddings <span translate=no>_^_2_^_</span>.</p>\n": "<h1><a href=\"index.html\">\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM</a>) \u7528\u306e U-Net \u30e2\u30c7\u30eb</h1>\n<p>\u3053\u308c\u306f <a href=\"../../unet/index.html\">U-Net</a> <span translate=no>_^_0_^_</span> \u30d9\u30fc\u30b9\u306e\u30ce\u30a4\u30ba\u4e88\u6e2c\u30e2\u30c7\u30eb\u3067\u3059\u3002</p>\n<p>U-Net\u306f\u3001\u30e2\u30c7\u30eb\u56f3\u306eU\u5b57\u5f62\u306b\u3061\u306a\u3093\u3067\u540d\u4ed8\u3051\u3089\u308c\u307e\u3057\u305f\u3002\u7279\u5fb4\u30de\u30c3\u30d7\u306e\u89e3\u50cf\u5ea6\u3092\u6bb5\u968e\u7684\u306b\u4f4e\u304f (\u534a\u5206\u306b)\u3001\u6b21\u306b\u89e3\u50cf\u5ea6\u3092\u4e0a\u3052\u308b\u3053\u3068\u306b\u3088\u3063\u3066\u3001\u7279\u5b9a\u306e\u753b\u50cf\u3092\u51e6\u7406\u3057\u307e\u3059\u3002\u5404\u89e3\u50cf\u5ea6\u306b\u306f\u30d1\u30b9\u30b9\u30eb\u30fc\u63a5\u7d9a\u304c\u3042\u308a\u307e\u3059</p>\u3002\n<p><span translate=no>_^_1_^_</span></p>\n<p>\u3053\u306e\u5b9f\u88c5\u306b\u306f\u3001\u30aa\u30ea\u30b8\u30ca\u30eb\u306e U-Net \u306b\u591a\u6570\u306e\u5909\u66f4\uff08\u6b8b\u7559\u30d6\u30ed\u30c3\u30af\u3001\u30de\u30eb\u30c1\u30d8\u30c3\u30c9\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\uff09\u304c\u542b\u307e\u308c\u3066\u304a\u308a\u3001\u30bf\u30a4\u30e0\u30b9\u30c6\u30c3\u30d7\u306e\u57cb\u3081\u8fbc\u307f\u3082\u8ffd\u52a0\u3055\u308c\u3066\u3044\u307e\u3059\u3002<span translate=no>_^_2_^_</span></p>\n",
+ "<h2>U-Net</h2>\n": "<h2>\u30e6\u30fc\u30cd\u30c3\u30c8</h2>\n",
+ "<h3>Attention block</h3>\n<p>This is similar to <a href=\"../../transformers/mha.html\">transformer multi-head attention</a>.</p>\n": "<h3>\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30d6\u30ed\u30c3\u30af</h3>\n<p><a href=\"../../transformers/mha.html\">\u3053\u308c\u306f\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u306e\u30de\u30eb\u30c1\u30d8\u30c3\u30c9\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u306b\u4f3c\u3066\u3044\u307e\u3059</a>\u3002</p>\n",
+ "<h3>Down block</h3>\n<p>This combines <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span>. These are used in the first half of U-Net at each resolution.</p>\n": "<h3>\u30c0\u30a6\u30f3\u30d6\u30ed\u30c3\u30af</h3>\n<p><span translate=no>_^_0_^_</span>\u3053\u308c\u306f\u3068\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u3082\u306e\u3067\u3059<span translate=no>_^_1_^_</span>\u3002\u3053\u308c\u3089\u306fU-Net\u306e\u524d\u534a\u3067\u305d\u308c\u305e\u308c\u306e\u89e3\u50cf\u5ea6\u3067\u4f7f\u308f\u308c\u3066\u3044\u307e\u3059</p>\u3002\n",
+ "<h3>Embeddings for <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u306e\u57cb\u3081\u8fbc\u307f <span translate=no>_^_0_^_</span></h3>\n",
+ "<h3>Middle block</h3>\n<p>It combines a <span translate=no>_^_0_^_</span>, <span translate=no>_^_1_^_</span>, followed by another <span translate=no>_^_2_^_</span>. This block is applied at the lowest resolution of the U-Net.</p>\n": "<h3>\u30df\u30c9\u30eb\u30d6\u30ed\u30c3\u30af</h3>\n<p>a \u3068<span translate=no>_^_0_^_</span><span translate=no>_^_1_^_</span>\u3001<span translate=no>_^_2_^_</span>\u306e\u5f8c\u306b\u7d9a\u304f\u5225\u306e\u3082\u306e\u3092\u7d44\u307f\u5408\u308f\u305b\u307e\u3059\u3002\u3053\u306e\u30d6\u30ed\u30c3\u30af\u306f U-Net \u306e\u6700\u4f4e\u89e3\u50cf\u5ea6\u3067\u9069\u7528\u3055\u308c\u307e\u3059</p>\u3002\n",
+ "<h3>Residual block</h3>\n<p>A residual block has two convolution layers with group normalization. Each resolution is processed with two residual blocks.</p>\n": "<h3>\u6b8b\u7559\u30d6\u30ed\u30c3\u30af</h3>\n<p>\u6b8b\u5dee\u30d6\u30ed\u30c3\u30af\u306b\u306f\u3001\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u3055\u308c\u305f 2 \u3064\u306e\u7573\u307f\u8fbc\u307f\u5c64\u304c\u3042\u308a\u307e\u3059\u3002\u5404\u89e3\u50cf\u5ea6\u306f 2 \u3064\u306e\u6b8b\u5dee\u30d6\u30ed\u30c3\u30af\u3067\u51e6\u7406\u3055\u308c\u307e\u3059</p>\u3002\n",
+ "<h3>Scale down the feature map by <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u30d5\u30a3\u30fc\u30c1\u30e3\u30de\u30c3\u30d7\u3092\u6b21\u306e\u65b9\u6cd5\u3067\u30b9\u30b1\u30fc\u30eb\u30c0\u30a6\u30f3\u3057\u307e\u3059\u3002<span translate=no>_^_0_^_</span></h3>\n",
+ "<h3>Scale up the feature map by <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u6b21\u306e\u65b9\u6cd5\u3067\u30d5\u30a3\u30fc\u30c1\u30e3\u30de\u30c3\u30d7\u3092\u30b9\u30b1\u30fc\u30eb\u30a2\u30c3\u30d7\u3057\u307e\u3059\u3002<span translate=no>_^_0_^_</span></h3>\n",
+ "<h3>Swish actiavation function</h3>\n<p><span translate=no>_^_0_^_</span></p>\n": "<h3>\u30b9\u30a4\u30c3\u30c1\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3\u6a5f\u80fd</h3>\n<p><span translate=no>_^_0_^_</span></p>\n",
+ "<h3>Up block</h3>\n<p>This combines <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span>. These are used in the second half of U-Net at each resolution.</p>\n": "<h3>\u30a2\u30c3\u30d7\u30d6\u30ed\u30c3\u30af</h3>\n<p><span translate=no>_^_0_^_</span>\u3053\u308c\u306f\u3068\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u3082\u306e\u3067\u3059<span translate=no>_^_1_^_</span>\u3002\u3053\u308c\u3089\u306fU-Net\u306e\u5f8c\u534a\u3067\u305d\u308c\u305e\u308c\u306e\u89e3\u50cf\u5ea6\u3067\u4f7f\u308f\u308c\u3066\u3044\u307e\u3059</p>\u3002\n",
+ "<h4>First half of U-Net - decreasing resolution</h4>\n": "<h4>U-Net\u306e\u524d\u534a-\u89e3\u50cf\u5ea6\u306e\u4f4e\u4e0b</h4>\n",
+ "<h4>Second half of U-Net - increasing resolution</h4>\n": "<h4>U-Net\u306e\u5f8c\u534a-\u89e3\u50cf\u5ea6\u306e\u5411\u4e0a</h4>\n",
+ "<p> </p>\n": "<p></p>\n",
+ "<p><span translate=no>_^_0_^_</span> at the same resolution </p>\n": "<p><span translate=no>_^_0_^_</span>\u540c\u3058\u89e3\u50cf\u5ea6\u3067</p>\n",
+ "<p><span translate=no>_^_0_^_</span> is not used, but it&#x27;s kept in the arguments because for the attention layer function signature to match with <span translate=no>_^_1_^_</span>. </p>\n": "<p><span translate=no>_^_0_^_</span>\u306f\u4f7f\u308f\u308c\u3066\u3044\u307e\u305b\u3093\u304c\u3001<span translate=no>_^_1_^_</span>\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30ec\u30a4\u30e4\u30fc\u306e\u95a2\u6570\u30b7\u30b0\u30cd\u30c1\u30e3\u3068\u306e\u30de\u30c3\u30c1\u30f3\u30b0\u306e\u305f\u3081\u5f15\u6570\u306b\u306f\u6b8b\u3055\u308c\u3066\u3044\u307e\u3059\u3002</p>\n",
+ "<p><span translate=no>_^_0_^_</span> will store outputs at each resolution for skip connection </p>\n": "<p><span translate=no>_^_0_^_</span>\u63a5\u7d9a\u3092\u30b9\u30ad\u30c3\u30d7\u3067\u304d\u308b\u3088\u3046\u306b\u3001\u51fa\u529b\u3092\u5404\u89e3\u50cf\u5ea6\u3067\u4fdd\u5b58\u3057\u307e\u3059</p>\n",
+ "<p>Activation </p>\n": "<p>\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3</p>\n",
+ "<p>Add <span translate=no>_^_0_^_</span> </p>\n": "<p>[\u8ffd\u52a0] <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Add skip connection </p>\n": "<p>\u30b9\u30ad\u30c3\u30d7\u63a5\u7d9a\u3092\u8ffd\u52a0</p>\n",
+ "<p>Add the shortcut connection and return </p>\n": "<p>\u30b7\u30e7\u30fc\u30c8\u30ab\u30c3\u30c8\u63a5\u7d9a\u3092\u8ffd\u52a0\u3057\u3066\u623b\u308b</p>\n",
+ "<p>Add time embeddings </p>\n": "<p>\u6642\u9593\u57cb\u3081\u8fbc\u307f\u3092\u8ffd\u52a0</p>\n",
+ "<p>Calculate scaled dot-product <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u3055\u308c\u305f\u30c9\u30c3\u30c8\u30d7\u30ed\u30c0\u30af\u30c8\u306e\u8a08\u7b97 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Change <span translate=no>_^_0_^_</span> to shape <span translate=no>_^_1_^_</span> </p>\n": "<p><span translate=no>_^_0_^_</span>\u5f62\u72b6\u306b\u5909\u66f4 <span translate=no>_^_1_^_</span></p>\n",
+ "<p>Change to shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u5f62\u72b6\u306b\u5909\u66f4 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Combine the set of modules </p>\n": "<p>\u30e2\u30b8\u30e5\u30fc\u30eb\u30bb\u30c3\u30c8\u3092\u7d44\u307f\u5408\u308f\u305b\u308b</p>\n",
+ "<p>Create sinusoidal position embeddings <a href=\"../../transformers/positional_encoding.html\">same as those from the transformer</a></p>\n<span translate=no>_^_0_^_</span><p>where <span translate=no>_^_1_^_</span> is <span translate=no>_^_2_^_</span> </p>\n": "<p><a href=\"../../transformers/positional_encoding.html\">\u5909\u5727\u5668\u3068\u540c\u3058\u6b63\u5f26\u6ce2\u4f4d\u7f6e\u57cb\u3081\u8fbc\u307f\u3092\u4f5c\u6210</a></p>\n<span translate=no>_^_0_^_</span><p><span translate=no>_^_1_^_</span>\u3069\u3053 <span translate=no>_^_2_^_</span></p>\n",
+ "<p>Default <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30c7\u30d5\u30a9\u30eb\u30c8 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Down sample at all resolutions except the last </p>\n": "<p>\u6700\u5f8c\u306e\u89e3\u50cf\u5ea6\u3092\u9664\u304f\u3059\u3079\u3066\u306e\u89e3\u50cf\u5ea6\u306e\u30c0\u30a6\u30f3\u30b5\u30f3\u30d7\u30eb</p>\n",
+ "<p>Final block to reduce the number of channels </p>\n": "<p>\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u3092\u6e1b\u3089\u3059\u305f\u3081\u306e\u6700\u5f8c\u306e\u30d6\u30ed\u30c3\u30af</p>\n",
+ "<p>Final normalization and convolution </p>\n": "<p>\u6700\u7d42\u7684\u306a\u6b63\u898f\u5316\u3068\u7573\u307f\u8fbc\u307f</p>\n",
+ "<p>Final normalization and convolution layer </p>\n": "<p>\u6700\u7d42\u6b63\u898f\u5316\u3068\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
+ "<p>First convolution layer </p>\n": "<p>\u6700\u521d\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
+ "<p>First half of U-Net </p>\n": "<p>\u30e6\u30fc\u30cd\u30c3\u30c8\u524d\u534a</p>\n",
+ "<p>First linear layer </p>\n": "<p>\u7b2c 1 \u7dda\u5f62\u30ec\u30a4\u30e4\u30fc</p>\n",
+ "<p>For each resolution </p>\n": "<p>\u5404\u89e3\u50cf\u5ea6\u306b\u3064\u3044\u3066</p>\n",
+ "<p>Get image projection </p>\n": "<p>\u30a4\u30e1\u30fc\u30b8\u30d7\u30ed\u30b8\u30a7\u30af\u30b7\u30e7\u30f3\u3092\u53d6\u5f97</p>\n",
+ "<p>Get query, key, and values (concatenated) and shape it to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30af\u30a8\u30ea\u3001\u30ad\u30fc\u3001\u5024 (\u9023\u7d50) \u3092\u53d6\u5f97\u3057\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u5f62\u3092\u6574\u3048\u307e\u3059 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Get shape </p>\n": "<p>\u30b7\u30a7\u30a4\u30d7\u3092\u53d6\u5f97</p>\n",
+ "<p>Get the skip connection from first half of U-Net and concatenate </p>\n": "<p>U-Net\u306e\u524d\u534a\u304b\u3089\u30b9\u30ad\u30c3\u30d7\u63a5\u7d9a\u3092\u53d6\u5f97\u3057\u3066\u9023\u7d50\u3059\u308b</p>\n",
+ "<p>Get time-step embeddings </p>\n": "<p>\u30bf\u30a4\u30e0\u30b9\u30c6\u30c3\u30d7\u306e\u57cb\u3081\u8fbc\u307f\u3092\u5165\u624b</p>\n",
+ "<p>Group normalization and the first convolution layer </p>\n": "<p>\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u3068\u6700\u521d\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
+ "<p>Group normalization and the second convolution layer </p>\n": "<p>\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u3068 2 \u756a\u76ee\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
+ "<p>If the number of input channels is not equal to the number of output channels we have to project the shortcut connection </p>\n": "<p>\u5165\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u306e\u6570\u304c\u51fa\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u306e\u6570\u3068\u7b49\u3057\u304f\u306a\u3044\u5834\u5408\u306f\u3001\u30b7\u30e7\u30fc\u30c8\u30ab\u30c3\u30c8\u63a5\u7d9a\u3092\u6295\u5f71\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002</p>\n",
+ "<p>Linear layer for final transformation </p>\n": "<p>\u6700\u7d42\u5909\u63db\u7528\u306e\u7dda\u5f62\u30ec\u30a4\u30e4\u30fc</p>\n",
+ "<p>Linear layer for time embeddings </p>\n": "<p>\u6642\u9593\u57cb\u3081\u8fbc\u307f\u7528\u306e\u7dda\u5f62\u30ec\u30a4\u30e4\u30fc</p>\n",
+ "<p>Middle (bottom) </p>\n": "<p>\u4e2d\u592e (\u4e0b\u90e8)</p>\n",
+ "<p>Middle block </p>\n": "<p>\u30df\u30c9\u30eb\u30d6\u30ed\u30c3\u30af</p>\n",
+ "<p>Multiply by values </p>\n": "<p>\u5024\u306b\u3088\u308b\u4e57\u7b97</p>\n",
+ "<p>Normalization layer </p>\n": "<p>\u6b63\u898f\u5316\u30ec\u30a4\u30e4\u30fc</p>\n",
+ "<p>Number of channels </p>\n": "<p>\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</p>\n",
+ "<p>Number of output channels at this resolution </p>\n": "<p>\u3053\u306e\u89e3\u50cf\u5ea6\u3067\u306e\u51fa\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</p>\n",
+ "<p>Number of resolutions </p>\n": "<p>\u89e3\u50cf\u5ea6\u306e\u6570</p>\n",
+ "<p>Project image into feature map </p>\n": "<p>\u753b\u50cf\u3092\u30d5\u30a3\u30fc\u30c1\u30e3\u30de\u30c3\u30d7\u306b\u6295\u5f71</p>\n",
+ "<p>Projections for query, key and values </p>\n": "<p>\u30af\u30a8\u30ea\u3001\u30ad\u30fc\u3001\u5024\u306e\u6295\u5f71</p>\n",
+ "<p>Reshape to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u5f62\u72b6\u3092\u6b21\u306e\u5f62\u5f0f\u306b\u5909\u66f4 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Scale for dot-product attention </p>\n": "<p>\u30c9\u30c3\u30c8\u30d7\u30ed\u30c0\u30af\u30c8\u30fb\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30fb\u30b9\u30b1\u30fc\u30eb</p>\n",
+ "<p>Second convolution layer </p>\n": "<p>2 \u756a\u76ee\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
+ "<p>Second half of U-Net </p>\n": "<p>\u30e6\u30fc\u30cd\u30c3\u30c8\u5f8c\u534a</p>\n",
+ "<p>Second linear layer </p>\n": "<p>2 \u756a\u76ee\u306e\u7dda\u5f62\u30ec\u30a4\u30e4\u30fc</p>\n",
+ "<p>Softmax along the sequence dimension <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30b7\u30fc\u30b1\u30f3\u30b9\u6b21\u5143\u306b\u6cbf\u3063\u305f\u30bd\u30d5\u30c8\u30de\u30c3\u30af\u30b9 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Split query, key, and values. Each of them will have shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30af\u30a8\u30ea\u3001\u30ad\u30fc\u3001\u5024\u3092\u5206\u5272\u3057\u307e\u3059\u3002\u305d\u308c\u305e\u308c\u306b\u5f62\u304c\u3042\u308a\u307e\u3059 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>The input has <span translate=no>_^_0_^_</span> because we concatenate the output of the same resolution from the first half of the U-Net </p>\n": "<p>\u5165\u529b\u306f\u3001<span translate=no>_^_0_^_</span> U-Net\u306e\u524d\u534a\u304b\u3089\u540c\u3058\u89e3\u50cf\u5ea6\u306e\u51fa\u529b\u3092\u9023\u7d50\u3057\u3066\u3044\u308b\u305f\u3081\u3067\u3059\u3002</p>\n",
+ "<p>Time embedding layer. Time embedding has <span translate=no>_^_0_^_</span> channels </p>\n": "<p>\u6642\u9593\u57cb\u3081\u8fbc\u307f\u30ec\u30a4\u30e4\u30fc\u3002\u6642\u9593\u57cb\u3081\u8fbc\u307f\u306b\u306f\u30c1\u30e3\u30f3\u30cd\u30eb\u304c\u3042\u308a\u307e\u3059 <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Transform to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u306b\u5909\u63db <span translate=no>_^_0_^_</span></p>\n",
+ "<p>Transform with the MLP </p>\n": "<p>MLP \u306b\u3088\u308b\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30e1\u30fc\u30b7\u30e7\u30f3</p>\n",
+ "<p>Up sample at all resolutions except last </p>\n": "<p>\u524d\u56de\u3092\u9664\u304f\u3059\u3079\u3066\u306e\u89e3\u50cf\u5ea6\u3067\u30b5\u30f3\u30d7\u30eb\u3092\u30a2\u30c3\u30d7</p>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> has shape <span translate=no>_^_1_^_</span> </li>\n<li><span translate=no>_^_2_^_</span> has shape <span translate=no>_^_3_^_</span></li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u5f62\u304c\u3042\u308b <span translate=no>_^_1_^_</span></li>\n<li><span translate=no>_^_2_^_</span>\u5f62\u304c\u3042\u308b <span translate=no>_^_3_^_</span></li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of channels in the image. <span translate=no>_^_1_^_</span> for RGB. </li>\n<li><span translate=no>_^_2_^_</span> is number of channels in the initial feature map that we transform the image into </li>\n<li><span translate=no>_^_3_^_</span> is the list of channel numbers at each resolution. The number of channels is <span translate=no>_^_4_^_</span> </li>\n<li><span translate=no>_^_5_^_</span> is a list of booleans that indicate whether to use attention at each resolution </li>\n<li><span translate=no>_^_6_^_</span> is the number of <span translate=no>_^_7_^_</span> at each resolution</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u753b\u50cf\u5185\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u3067\u3059\u3002<span translate=no>_^_1_^_</span>RGB \u7528\u3067\u3059\u3002</li>\n<li><span translate=no>_^_2_^_</span>\u753b\u50cf\u3092\u5909\u63db\u3059\u308b\u6700\u521d\u306e\u7279\u5fb4\u30de\u30c3\u30d7\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u3067\u3059</li>\n<li><span translate=no>_^_3_^_</span>\u306f\u3001\u5404\u89e3\u50cf\u5ea6\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u756a\u53f7\u306e\u30ea\u30b9\u30c8\u3067\u3059\u3002\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u306f <span translate=no>_^_4_^_</span></li>\n<li><span translate=no>_^_5_^_</span>\u305d\u308c\u305e\u308c\u306e\u89e3\u50cf\u5ea6\u3067\u6ce8\u610f\u3092\u5411\u3051\u308b\u3079\u304d\u304b\u3069\u3046\u304b\u3092\u793a\u3059\u30d6\u30fc\u30ea\u30a2\u30f3\u306e\u30ea\u30b9\u30c8\u3067\u3059</li>\n<li><span translate=no>_^_6_^_</span><span translate=no>_^_7_^_</span>\u306f\u5404\u89e3\u50cf\u5ea6\u3067\u306e\u306e\u6570\u3067\u3059</li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of channels in the input </li>\n<li><span translate=no>_^_1_^_</span> is the number of heads in multi-head attention </li>\n<li><span translate=no>_^_2_^_</span> is the number of dimensions in each head </li>\n<li><span translate=no>_^_3_^_</span> is the number of groups for <a href=\"../../normalization/group_norm/index.html\">group normalization</a></li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u306f\u5165\u529b\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</li>\n<li><span translate=no>_^_1_^_</span>\u30de\u30eb\u30c1\u30d8\u30c3\u30c9\u30fb\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u306e\u30d8\u30c3\u30c9\u6570\u3067\u3059</li>\n<li><span translate=no>_^_2_^_</span>\u306f\u5404\u30d8\u30c3\u30c9\u306e\u6b21\u5143\u6570\u3067\u3059</li>\n<li><span translate=no>_^_3_^_</span><a href=\"../../normalization/group_norm/index.html\">\u306f\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u306e\u5bfe\u8c61\u3068\u306a\u308b\u30b0\u30eb\u30fc\u30d7\u306e\u6570\u3067\u3059</a></li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of dimensions in the embedding</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u306f\u57cb\u3081\u8fbc\u307f\u306e\u6b21\u5143\u6570\u3067\u3059</li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of input channels </li>\n<li><span translate=no>_^_1_^_</span> is the number of input channels </li>\n<li><span translate=no>_^_2_^_</span> is the number channels in the time step (<span translate=no>_^_3_^_</span>) embeddings </li>\n<li><span translate=no>_^_4_^_</span> is the number of groups for <a href=\"../../normalization/group_norm/index.html\">group normalization</a> </li>\n<li><span translate=no>_^_5_^_</span> is the dropout rate</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u306f\u5165\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</li>\n<li><span translate=no>_^_1_^_</span>\u306f\u5165\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</li>\n<li><span translate=no>_^_2_^_</span>\u306f\u30bf\u30a4\u30e0\u30b9\u30c6\u30c3\u30d7 (<span translate=no>_^_3_^_</span>) \u57cb\u3081\u8fbc\u307f\u306e\u6570\u30c1\u30e3\u30f3\u30cd\u30eb\u3067\u3059</li>\n<li><span translate=no>_^_4_^_</span><a href=\"../../normalization/group_norm/index.html\">\u306f\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u306e\u5bfe\u8c61\u3068\u306a\u308b\u30b0\u30eb\u30fc\u30d7\u306e\u6570\u3067\u3059</a></li>\n<li><span translate=no>_^_5_^_</span>\u8131\u843d\u7387\u3067\u3059</li></ul>\n",
+ "U-Net model for Denoising Diffusion Probabilistic Models (DDPM)": "\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM) \u7528\u306e U-Net \u30e2\u30c7\u30eb",
+ "UNet model for Denoising Diffusion Probabilistic Models (DDPM)": "\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM) \u7528\u306e UNet \u30e2\u30c7\u30eb"
+}
@@ -0,0 +1,76 @@
+{
+ "<h1>U-Net model for <a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a></h1>\n<p>This is a <a href=\"../../unet/index.html\">U-Net</a> based model to predict noise <span translate=no>_^_0_^_</span>.</p>\n<p>U-Net is a gets it&#x27;s name from the U shape in the model diagram. It processes a given image by progressively lowering (halving) the feature map resolution and then increasing the resolution. There are pass-through connection at each resolution.</p>\n<p><span translate=no>_^_1_^_</span></p>\n<p>This implementation contains a bunch of modifications to original U-Net (residual blocks, multi-head attention)  and also adds time-step embeddings <span translate=no>_^_2_^_</span>.</p>\n": "<h1><a href=\"index.html\">\u0dc0\u0dd2\u0dc3\u0dbb\u0dab \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2 \u0db1\u0dd2\u0dbb\u0dd6\u0db4\u0dab\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba (\u0da9\u0dd3\u0da9\u0dd3\u0db4\u0dd3\u0d91\u0db8\u0dca)</a></h1>\n<p>\u0dc1\u0db6\u0dca\u0daf\u0dba\u0db4\u0dd4\u0dbb\u0ddd\u0d9a\u0dae\u0db1\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0db8\u0dd9\u0dba <a href=\"../../unet/index.html\">\u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca</a> \u0db4\u0daf\u0db1\u0db8\u0dca \u0d9a\u0dbb\u0d9c\u0dad\u0dca \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dd2 <span translate=no>_^_0_^_</span>. </p>\n<p>\u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca\u0dba\u0db1\u0dd4 \u0d86\u0daf\u0dbb\u0dca\u0dc1 \u0dbb\u0dd6\u0db4 \u0dc3\u0da7\u0dc4\u0db1\u0dda \u0dba\u0dd6 \u0dc4\u0dd0\u0da9\u0dba\u0dd9\u0db1\u0dca \u0d91\u0dba \u0db1\u0db8 \u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dd3. \u0dc0\u0dd2\u0dc1\u0dda\u0dc2\u0dcf\u0d82\u0d9c \u0dc3\u0dd2\u0dad\u0dd2\u0dba\u0db8\u0dca \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba \u0d9a\u0dca\u0dbb\u0db8\u0dba\u0dd9\u0db1\u0dca \u0d85\u0da9\u0dd4 \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dd9\u0db1\u0dca (\u0d85\u0da9\u0d9a\u0dca) \u0dc3\u0dc4 \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba \u0dc0\u0dd0\u0da9\u0dd2 \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dd9\u0db1\u0dca \u0d91\u0dba \u0dbd\u0db6\u0dcf \u0daf\u0dd3 \u0d87\u0dad\u0dd2 \u0dbb\u0dd6\u0db4\u0dba\u0d9a\u0dca \u0dc3\u0d9a\u0dc3\u0db1\u0dd4 \u0dbd\u0dd0\u0db6\u0dda. \u0dc3\u0dd1\u0db8 \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0d9a\u0daf\u0dd3\u0db8 \u0db4\u0dcf\u0dc3\u0dca-\u0dc4\u0dbb\u0dc4\u0dcf \u0dc3\u0db8\u0dca\u0db6\u0db1\u0dca\u0db0\u0dad\u0dcf\u0dc0\u0dba\u0d9a\u0dca \u0d87\u0dad. </p>\n<p><span translate=no>_^_1_^_</span></p>\n<p>\u0db8\u0dd9\u0db8\u0d9a\u0dca\u0dbb\u0dd2\u0dba\u0dcf\u0dad\u0dca\u0db8\u0d9a \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0db8\u0dd4\u0dbd\u0dca \u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca (\u0d85\u0dc0\u0dc1\u0dda\u0dc2 \u0d9a\u0dd4\u0da7\u0dca\u0da7\u0dd2, \u0db6\u0dc4\u0dd4-\u0dc4\u0dd2\u0dc3 \u0d85\u0dc0\u0db0\u0dcf\u0db1\u0dba) \u0dc3\u0db3\u0dc4\u0dcf \u0dc0\u0dd9\u0db1\u0dc3\u0dca \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dca \u0dbb\u0dcf\u0dc1\u0dd2\u0dba\u0d9a\u0dca \u0d85\u0da9\u0d82\u0d9c\u0dd4 \u0dc0\u0db1 \u0d85\u0dad\u0dbb \u0d9a\u0dcf\u0dbd-\u0db4\u0dd2\u0dba\u0dc0\u0dbb \u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8\u0dca \u0d91\u0d9a\u0dad\u0dd4 \u0d9a\u0dbb\u0dba\u0dd2 <span translate=no>_^_2_^_</span>. </p>\n",
+ "<h2>U-Net</h2>\n": "<h2>\u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca</h2>\n",
+ "<h3>Attention block</h3>\n<p>This is similar to <a href=\"../../transformers/mha.html\">transformer multi-head attention</a>.</p>\n": "<h3>\u0d85\u0dc0\u0db0\u0dcf\u0db1\u0dba\u0dc0\u0dcf\u0dbb\u0dab</h3>\n<p>\u0db8\u0dd9\u0dba <a href=\"../../transformers/mha.html\">\u0da7\u0dca\u0dbb\u0dcf\u0db1\u0dca\u0dc3\u0dca\u0dc6\u0ddd\u0db8\u0dbb\u0dca \u0db6\u0dc4\u0dd4-\u0dc4\u0dd2\u0dc3 \u0d85\u0dc0\u0db0\u0dcf\u0db1\u0dba\u0da7</a>\u0dc3\u0db8\u0dcf\u0db1 \u0dc0\u0dda. </p>\n",
+ "<h3>Down block</h3>\n<p>This combines <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span>. These are used in the first half of U-Net at each resolution.</p>\n": "<h3>\u0db6\u0dca\u0dbd\u0ddc\u0d9a\u0dca\u0da9\u0dc0\u0dd4\u0db1\u0dca</h3>\n<p>\u0db8\u0dd9\u0dba\u0d92\u0d9a\u0dcf\u0db6\u0daf\u0dca\u0db0 <span translate=no>_^_0_^_</span> \u0dc4\u0dcf <span translate=no>_^_1_^_</span>. \u0db8\u0dd9\u0db8 \u0d91\u0d9a\u0dca \u0d91\u0d9a\u0dca \u0dba\u0ddd\u0da2\u0db1\u0dcf\u0dc0 \u0daf\u0dd3 U-Net \u0db4\u0dc5\u0db8\u0dd4 \u0db7\u0dcf\u0d9c\u0dba\u0dda \u0daf\u0dd3 \u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0dc0\u0dda. </p>\n",
+ "<h3>Embeddings for <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8\u0dca\u0dc3\u0db3\u0dc4\u0dcf <span translate=no>_^_0_^_</span></h3>\n",
+ "<h3>Middle block</h3>\n<p>It combines a <span translate=no>_^_0_^_</span>, <span translate=no>_^_1_^_</span>, followed by another <span translate=no>_^_2_^_</span>. This block is applied at the lowest resolution of the U-Net.</p>\n": "<h3>\u0db8\u0dd0\u0daf\u0d9a\u0ddc\u0da7\u0dc3</h3>\n<p>\u0d91\u0dba\u0dad\u0dc0\u0dad\u0dca \u0d91\u0d9a\u0d9a\u0dca <span translate=no>_^_0_^_</span>\u0dc3\u0db8\u0d9f \u0d92\u0d9a\u0dcf\u0db6\u0daf\u0dca\u0db0 <span translate=no>_^_2_^_</span>\u0dc0\u0dda. <span translate=no>_^_1_^_</span> \u0db8\u0dd9\u0db8 \u0d9a\u0ddc\u0da7\u0dc3 U-Net \u0dc4\u0dd2 \u0d85\u0da9\u0dd4\u0db8 \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0dd9\u0db1\u0dca \u0dba\u0ddc\u0daf\u0db1\u0dd4 \u0dbd\u0dd0\u0db6\u0dda. </p>\n",
+ "<h3>Residual block</h3>\n<p>A residual block has two convolution layers with group normalization. Each resolution is processed with two residual blocks.</p>\n": "<h3>\u0d85\u0dc0\u0dc1\u0dda\u0dc2\u0d9a\u0ddc\u0da7\u0dc3</h3>\n<p>\u0d85\u0dc0\u0dc1\u0dda\u0dc2\u0d9a\u0ddc\u0da7\u0dc3\u0d9a\u0daf\u0dd3 \u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca \u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0db8\u0d9c convolution \u0dc3\u0dca\u0dae\u0dbb \u0daf\u0dd9\u0d9a\u0d9a\u0dca \u0d87\u0dad. \u0dc3\u0dd1\u0db8 \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0d9a\u0dca\u0db8 \u0d85\u0dc0\u0dc1\u0dda\u0dc2 \u0d9a\u0ddc\u0da7\u0dc3\u0dca \u0daf\u0dd9\u0d9a\u0d9a\u0dd2\u0db1\u0dca \u0dc3\u0d9a\u0dc3\u0db1\u0dd4 \u0dbd\u0dd0\u0db6\u0dda. </p>\n",
+ "<h3>Scale down the feature map by <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u0dc0\u0dd2\u0dc1\u0dda\u0dc2\u0dcf\u0d82\u0d9c\u0dc3\u0dd2\u0dad\u0dd2\u0dba\u0db8 \u0db4\u0dbb\u0dd2\u0db8\u0dcf\u0dab\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span></h3>\n",
+ "<h3>Scale up the feature map by <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u0dc0\u0dd2\u0dc1\u0dda\u0dc2\u0dcf\u0d82\u0d9c\u0dc3\u0dd2\u0dad\u0dd2\u0dba\u0db8 \u0db4\u0dbb\u0dd2\u0db8\u0dcf\u0dab\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span></h3>\n",
+ "<h3>Swish actiavation function</h3>\n<p><span translate=no>_^_0_^_</span></p>\n": "<h3>\u0dc3\u0dca\u0dc0\u0dd2\u0dc3\u0dca\u0dc2\u0dca\u0d9a\u0dca\u0dbb\u0dd2\u0dba\u0dcf\u0d9a\u0dcf\u0dbb\u0dd3 \u0dc1\u0dca\u0dbb\u0dd2\u0dad\u0dba</h3>\n<p><span translate=no>_^_0_^_</span></p>\n",
+ "<h3>Up block</h3>\n<p>This combines <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span>. These are used in the second half of U-Net at each resolution.</p>\n": "<h3>\u0db6\u0dca\u0dbd\u0ddc\u0d9a\u0dca\u0daf\u0d9a\u0dca\u0dc0\u0dcf</h3>\n<p>\u0db8\u0dd9\u0dba\u0d92\u0d9a\u0dcf\u0db6\u0daf\u0dca\u0db0 <span translate=no>_^_0_^_</span> \u0dc4\u0dcf <span translate=no>_^_1_^_</span>. \u0dc3\u0dd1\u0db8 \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0d9a\u0daf\u0dd3\u0db8 \u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca \u0dc4\u0dd2 \u0daf\u0dd9\u0dc0\u0db1 \u0db7\u0dcf\u0d9c\u0dba\u0dda\u0daf\u0dd3 \u0db8\u0dda\u0dc0\u0dcf \u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0dc0\u0dda. </p>\n",
+ "<h4>First half of U-Net - decreasing resolution</h4>\n": "<h4>U-Net\u0db4\u0dc5\u0db8\u0dd4 \u0db7\u0dcf\u0d9c\u0dba - \u0d85\u0da9\u0dd4 \u0dba\u0ddd\u0da2\u0db1\u0dcf\u0dc0</h4>\n",
+ "<h4>Second half of U-Net - increasing resolution</h4>\n": "<h4>\u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca\u0dc4\u0dd2 \u0daf\u0dd9\u0dc0\u0db1 \u0db7\u0dcf\u0d9c\u0dba - \u0dc0\u0dd0\u0da9\u0dd2 \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dda \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba</h4>\n",
+ "<p> </p>\n": "<p> </p>\n",
+ "<p><span translate=no>_^_0_^_</span> at the same resolution </p>\n": "<p><span translate=no>_^_0_^_</span> \u0d91\u0d9a\u0db8 \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0dda </p>\n",
+ "<p><span translate=no>_^_0_^_</span> is not used, but it&#x27;s kept in the arguments because for the attention layer function signature to match with <span translate=no>_^_1_^_</span>. </p>\n": "<p><span translate=no>_^_0_^_</span> \u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0db1\u0ddc\u0d9a\u0dd9\u0dbb\u0dda, \u0db1\u0db8\u0dd4\u0dad\u0dca \u0d91\u0dba \u0dad\u0dbb\u0dca\u0d9a\u0dc0\u0dbd \u0dad\u0db6\u0dcf \u0d87\u0dad\u0dca\u0dad\u0dda \u0d85\u0dc0\u0db0\u0dcf\u0db1\u0dba \u0dba\u0ddc\u0db8\u0dd4 \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dda \u0dc3\u0dca\u0dae\u0dbb \u0dc1\u0dca\u0dbb\u0dd2\u0dad\u0dba\u0dda \u0d85\u0dad\u0dca\u0dc3\u0db1 \u0dc3\u0db8\u0d9f \u0d9c\u0dd0\u0dbd\u0db4\u0dd9\u0db1 \u0db6\u0dd0\u0dc0\u0dd2\u0db1\u0dd2 <span translate=no>_^_1_^_</span>. </p>\n",
+ "<p><span translate=no>_^_0_^_</span> will store outputs at each resolution for skip connection </p>\n": "<p><span translate=no>_^_0_^_</span> \u0db8\u0d9f \u0dc4\u0dd0\u0dbb\u0dd3\u0db8\u0dda \u0dc3\u0db8\u0dca\u0db6\u0db1\u0dca\u0db0\u0dad\u0dcf\u0dc0\u0dba \u0dc3\u0db3\u0dc4\u0dcf \u0d91\u0d9a\u0dca \u0d91\u0d9a\u0dca \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0dda \u0db4\u0dca\u0dbb\u0dad\u0dd2\u0daf\u0dcf\u0db1\u0dba\u0db1\u0dca \u0d9c\u0db6\u0da9\u0dcf \u0d9a\u0dbb\u0db1\u0dd4 \u0d87\u0dad </p>\n",
+ "<p>Activation </p>\n": "<p>\u0dc3\u0d9a\u0dca\u200d\u0dbb\u0dd3\u0dba\u0d9a\u0dd2\u0dbb\u0dd3\u0db8 </p>\n",
+ "<p>Add <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0d91\u0d9a\u0dad\u0dd4\u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Add skip connection </p>\n": "<p>\u0db8\u0d9f\u0dc4\u0dd0\u0dbb\u0dd3\u0db8\u0dda \u0dc3\u0db8\u0dca\u0db6\u0db1\u0dca\u0db0\u0dad\u0dcf\u0dc0\u0dba \u0d91\u0d9a\u0dca \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Add the shortcut connection and return </p>\n": "<p>\u0d9a\u0dd9\u0da7\u0dd2\u0db8\u0d82\u0dc3\u0db8\u0dca\u0db6\u0db1\u0dca\u0db0\u0dad\u0dcf\u0dc0\u0dba \u0d91\u0d9a\u0dad\u0dd4 \u0d9a\u0dbb \u0d86\u0db4\u0dc3\u0dd4 \u0dba\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Add time embeddings </p>\n": "<p>\u0d9a\u0dcf\u0dbd\u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8\u0dca \u0d91\u0d9a\u0dad\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Calculate scaled dot-product <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0db4\u0dbb\u0dd2\u0db8\u0dcf\u0dab\u0dad\u0dd2\u0dad\u0dca \u0db1\u0dd2\u0dc2\u0dca\u0db4\u0dcf\u0daf\u0db1\u0dba\u0d9a\u0dca \u0d9c\u0dab\u0db1\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Change <span translate=no>_^_0_^_</span> to shape <span translate=no>_^_1_^_</span> </p>\n": "<p><span translate=no>_^_0_^_</span> \u0dc4\u0dd0\u0da9\u0dba\u0da7 \u0dc0\u0dd9\u0db1\u0dc3\u0dca \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_1_^_</span> </p>\n",
+ "<p>Change to shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0dc4\u0dd0\u0da9\u0dba\u0da7\u0dc0\u0dd9\u0db1\u0dc3\u0dca \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Combine the set of modules </p>\n": "<p>\u0db8\u0ddc\u0da9\u0dd2\u0dba\u0dd4\u0dbd\u0d9a\u0da7\u0dca\u0da7\u0dbd\u0dba \u0d92\u0d9a\u0dcf\u0db6\u0daf\u0dca\u0db0 \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Create sinusoidal position embeddings <a href=\"../../transformers/positional_encoding.html\">same as those from the transformer</a></p>\n<span translate=no>_^_0_^_</span><p>where <span translate=no>_^_1_^_</span> is <span translate=no>_^_2_^_</span> </p>\n": "<p><a href=\"../../transformers/positional_encoding.html\">\u0da7\u0dca\u0dbb\u0dcf\u0db1\u0dca\u0dc3\u0dca\u0dc6\u0ddd\u0db8\u0dbb\u0dba\u0da7 \u0dc3\u0db8\u0dcf\u0db1</a>\u0dc3\u0dba\u0dd2\u0db1\u0ddc\u0dc3\u0ddc\u0dba\u0dd2\u0da9\u0dbd\u0dca \u0dc3\u0dca\u0dae\u0dcf\u0db1 \u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8\u0dca \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1</p>\n<span translate=no>_^_0_^_</span><p><span translate=no>_^_1_^_</span> \u0d9a\u0ddc\u0dc4\u0dda\u0daf <span translate=no>_^_2_^_</span> </p>\n",
+ "<p>Default <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0db4\u0dd9\u0dbb\u0db1\u0dd2\u0db8\u0dd2 <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Down sample at all resolutions except the last </p>\n": "<p>\u0db4\u0dc3\u0dd4\u0d9c\u0dd2\u0dba\u0dc4\u0dd0\u0dbb \u0d85\u0db1\u0dd9\u0d9a\u0dd4\u0dad\u0dca \u0dc3\u0dd2\u0dba\u0dbd\u0dd4 \u0dba\u0ddd\u0da2\u0db1\u0dcf \u0daf\u0dd3 \u0d86\u0daf\u0dbb\u0dca\u0dc1 \u0db4\u0dc4\u0dc5 </p>\n",
+ "<p>Final block to reduce the number of channels </p>\n": "<p>\u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf\u0d9c\u0dab\u0db1 \u0d85\u0da9\u0dd4 \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0d85\u0dc0\u0dc3\u0dcf\u0db1 \u0d9a\u0ddc\u0da7\u0dc3 </p>\n",
+ "<p>Final normalization and convolution </p>\n": "<p>\u0d85\u0dc0\u0dc3\u0dcf\u0db1\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0dc4 \u0d9a\u0dd0\u0da7\u0dd2 \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 </p>\n",
+ "<p>Final normalization and convolution layer </p>\n": "<p>\u0d85\u0dc0\u0dc3\u0dcf\u0db1\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0dc4 \u0d9a\u0dd0\u0da7\u0dd2 \u0d9c\u0dd0\u0dc3\u0dd4\u0dab\u0dd4 \u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
+ "<p>First convolution layer </p>\n": "<p>\u0db4\u0dc5\u0db8\u0dd4\u0d9a\u0dd0\u0da7\u0dd2 \u0d9c\u0dd0\u0dc3\u0dd4\u0dab\u0dd4 \u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
+ "<p>First half of U-Net </p>\n": "<p>\u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca\u0dc4\u0dd2 \u0db4\u0dc5\u0db8\u0dd4 \u0db7\u0dcf\u0d9c\u0dba </p>\n",
+ "<p>First linear layer </p>\n": "<p>\u0db4\u0dc5\u0db8\u0dd4\u0dbb\u0dda\u0d9b\u0dd3\u0dba \u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
+ "<p>For each resolution </p>\n": "<p>\u0d91\u0d9a\u0dca\u0d91\u0d9a\u0dca \u0dba\u0ddd\u0da2\u0db1\u0dcf\u0dc0 \u0dc3\u0db3\u0dc4\u0dcf </p>\n",
+ "<p>Get image projection </p>\n": "<p>\u0dbb\u0dd6\u0db4\u0db4\u0dca\u0dbb\u0d9a\u0dca\u0dc2\u0dda\u0db4\u0dab\u0dba \u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Get query, key, and values (concatenated) and shape it to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0dc0\u0dd2\u0db8\u0dc3\u0dd4\u0db8\u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1, \u0dba\u0dad\u0dd4\u0dbb, \u0dc3\u0dc4 \u0d85\u0d9c\u0dba\u0db1\u0dca (concatenated) \u0dc3\u0dc4 \u0d91\u0dba \u0dc4\u0dd0\u0da9\u0d9c\u0dc3\u0dca\u0dc0\u0dcf <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Get shape </p>\n": "<p>\u0dc4\u0dd0\u0da9\u0dba\u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Get the skip connection from first half of U-Net and concatenate </p>\n": "<p>\u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca\u0dc4\u0dd2 \u0db4\u0dc5\u0db8\u0dd4 \u0db7\u0dcf\u0d9c\u0dba\u0dda \u0dc3\u0dd2\u0da7 \u0db8\u0d9f \u0dc4\u0dd0\u0dbb\u0dd3\u0db8\u0dda \u0dc3\u0db8\u0dca\u0db6\u0db1\u0dca\u0db0\u0dad\u0dcf\u0dc0\u0dba \u0dbd\u0db6\u0dcf\u0d9c\u0dd9\u0db1 \u0dc3\u0d82\u0dba\u0dd4\u0d9a\u0dca\u0dad \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Get time-step embeddings </p>\n": "<p>\u0d9a\u0dcf\u0dbd-\u0db4\u0dd2\u0dba\u0dc0\u0dbb\u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8\u0dca \u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Group normalization and the first convolution layer </p>\n": "<p>\u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0dc4 \u0db4\u0dc5\u0db8\u0dd4 \u0d9a\u0dd0\u0da7\u0dd2 \u0d9c\u0dd0\u0dc3\u0dd4\u0dab\u0dd4 \u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
+ "<p>Group normalization and the second convolution layer </p>\n": "<p>\u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0dc4 \u0daf\u0dd9\u0dc0\u0db1 \u0d9a\u0dd0\u0da7\u0dd2 \u0d9c\u0dd0\u0dc3\u0dd4\u0dab\u0dd4 \u0dc3\u0dca\u0dad\u0dbb\u0dba </p>\n",
+ "<p>If the number of input channels is not equal to the number of output channels we have to project the shortcut connection </p>\n": "<p>\u0d86\u0daf\u0dcf\u0db1\u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1 \u0db4\u0dca\u0dbb\u0dad\u0dd2\u0daf\u0dcf\u0db1 \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1\u0da7 \u0dc3\u0db8\u0dcf\u0db1 \u0db1\u0ddc\u0dc0\u0dda \u0db1\u0db8\u0dca \u0d9a\u0dd9\u0da7\u0dd2\u0db8\u0d82 \u0dc3\u0db8\u0dca\u0db6\u0db1\u0dca\u0db0\u0dad\u0dcf\u0dc0\u0dba \u0db4\u0dca\u0dbb\u0d9a\u0dca\u0dc2\u0dda\u0db4\u0dab\u0dba \u0d9a\u0dc5 \u0dba\u0dd4\u0dad\u0dd4\u0dba </p>\n",
+ "<p>Linear layer for final transformation </p>\n": "<p>\u0d85\u0dc0\u0dc3\u0dcf\u0db1\u0db4\u0dbb\u0dd2\u0dc0\u0dbb\u0dca\u0dad\u0db1\u0dba \u0dc3\u0db3\u0dc4\u0dcf \u0dbb\u0dda\u0d9b\u0dd3\u0dba \u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
+ "<p>Linear layer for time embeddings </p>\n": "<p>\u0d9a\u0dcf\u0dbd\u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8\u0dca \u0dc3\u0db3\u0dc4\u0dcf \u0dbb\u0dda\u0d9b\u0dd3\u0dba \u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
+ "<p>Middle (bottom) </p>\n": "<p>\u0db8\u0dd0\u0daf(\u0db4\u0dc4\u0dc5) </p>\n",
+ "<p>Middle block </p>\n": "<p>\u0db8\u0dd0\u0daf\u0d9a\u0ddc\u0da7\u0dc3 </p>\n",
+ "<p>Multiply by values </p>\n": "<p>\u0d85\u0d9c\u0dba\u0db1\u0dca\u0d85\u0db1\u0dd4\u0dc0 \u0d9c\u0dd4\u0dab \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Normalization layer </p>\n": "<p>\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba\u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
+ "<p>Number of channels </p>\n": "<p>\u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf\u0d9c\u0dab\u0db1 </p>\n",
+ "<p>Number of output channels at this resolution </p>\n": "<p>\u0db8\u0dd9\u0db8\u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0dda \u0db4\u0dca\u0dbb\u0dad\u0dd2\u0daf\u0dcf\u0db1 \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1 </p>\n",
+ "<p>Number of resolutions </p>\n": "<p>\u0dba\u0ddd\u0da2\u0db1\u0dcf\u0d9c\u0dab\u0db1 </p>\n",
+ "<p>Project image into feature map </p>\n": "<p>\u0dc0\u0dd2\u0dc1\u0dda\u0dc2\u0dcf\u0d82\u0d9c\u0dc3\u0dd2\u0dad\u0dd2\u0dba\u0db8\u0da7 \u0dc0\u0dca\u0dba\u0dcf\u0db4\u0dd8\u0dad\u0dd2 \u0dbb\u0dd6\u0db4\u0dba </p>\n",
+ "<p>Projections for query, key and values </p>\n": "<p>\u0dc0\u0dd2\u0db8\u0dc3\u0dd4\u0db8, \u0dba\u0dad\u0dd4\u0dbb \u0dc3\u0dc4 \u0d85\u0d9c\u0dba\u0db1\u0dca \u0dc3\u0db3\u0dc4\u0dcf \u0db4\u0dca\u0dbb\u0d9a\u0dca\u0dc2\u0dda\u0db4\u0dab </p>\n",
+ "<p>Reshape to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0db1\u0dd0\u0dc0\u0dad\u0dc4\u0dd0\u0da9\u0d9c\u0dc3\u0dca\u0dc0\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Scale for dot-product attention </p>\n": "<p>\u0dad\u0dd2\u0dad\u0dca\u0db1\u0dd2\u0dc2\u0dca\u0db4\u0dcf\u0daf\u0db1 \u0d85\u0dc0\u0db0\u0dcf\u0db1\u0dba \u0dc3\u0db3\u0dc4\u0dcf \u0db4\u0dbb\u0dd2\u0db8\u0dcf\u0dab\u0dba </p>\n",
+ "<p>Second convolution layer </p>\n": "<p>\u0daf\u0dd9\u0dc0\u0db1\u0d9a\u0dd0\u0da7\u0dd2 \u0d9c\u0dd0\u0dc3\u0dd4\u0dab\u0dd4 \u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
+ "<p>Second half of U-Net </p>\n": "<p>\u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca\u0dc4\u0dd2 \u0daf\u0dd9\u0dc0\u0db1 \u0db7\u0dcf\u0d9c\u0dba </p>\n",
+ "<p>Second linear layer </p>\n": "<p>\u0daf\u0dd9\u0dc0\u0db1\u0dbb\u0dda\u0d9b\u0dd3\u0dba \u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
+ "<p>Softmax along the sequence dimension <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0d85\u0db1\u0dd4\u0d9a\u0dca\u0dbb\u0db8\u0dd2\u0d9a\u0db8\u0dcf\u0db1\u0dba \u0d94\u0dc3\u0dca\u0dc3\u0dda \u0dc3\u0ddc\u0dc6\u0dca\u0da7\u0dca\u0db8\u0dd0\u0d9a\u0dca\u0dc3\u0dca <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Split query, key, and values. Each of them will have shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0dc0\u0dd2\u0db8\u0dc3\u0dd4\u0db8, \u0dba\u0dad\u0dd4\u0dbb \u0dc3\u0dc4 \u0d85\u0d9c\u0dba\u0db1\u0dca \u0db6\u0dd9\u0daf\u0dd3\u0db8\u0dca. \u0d94\u0dc0\u0dd4\u0db1\u0dca \u0d91\u0d9a\u0dca \u0d91\u0d9a\u0dca \u0dc4\u0dd0\u0da9\u0dba \u0d87\u0dad <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>The input has <span translate=no>_^_0_^_</span> because we concatenate the output of the same resolution from the first half of the U-Net </p>\n": "<p>\u0d86\u0daf\u0dcf\u0db1\u0dba\u0da7\u0d87\u0dad\u0dca\u0dad\u0dda \u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca \u0dc4\u0dd2 \u0db4\u0dc5\u0db8\u0dd4 \u0db7\u0dcf\u0d9c\u0dba\u0dda \u0dc3\u0dd2\u0da7 \u0d91\u0d9a\u0db8 \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0dda \u0db4\u0dca\u0dbb\u0dad\u0dd2\u0daf\u0dcf\u0db1\u0dba \u0d85\u0db4 \u0dc3\u0d82\u0dba\u0dd4\u0d9a\u0dca\u0dad \u0d9a\u0dbb\u0db1 <span translate=no>_^_0_^_</span> \u0db6\u0dd0\u0dc0\u0dd2\u0db1\u0dd2 </p>\n",
+ "<p>Time embedding layer. Time embedding has <span translate=no>_^_0_^_</span> channels </p>\n": "<p>\u0d9a\u0dcf\u0dbd\u0dba\u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8 \u0dc3\u0dca\u0dae\u0dbb\u0dba. \u0d9a\u0dcf\u0dbd \u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8 <span translate=no>_^_0_^_</span> \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d87\u0dad </p>\n",
+ "<p>Transform to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u0db6\u0dc0\u0da7\u0db4\u0dbb\u0dd2\u0dc0\u0dbb\u0dca\u0dad\u0db1\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 <span translate=no>_^_0_^_</span> </p>\n",
+ "<p>Transform with the MLP </p>\n": "<p>\u0d91\u0db8\u0dca\u0d91\u0dbd\u0dca\u0db4\u0dd3\u0dc3\u0db8\u0d9f \u0db4\u0dbb\u0dd2\u0dc0\u0dbb\u0dca\u0dad\u0db1\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "<p>Up sample at all resolutions except last </p>\n": "<p>\u0db4\u0dc3\u0dd4\u0d9c\u0dd2\u0dba\u0dc4\u0dd0\u0dbb \u0d85\u0db1\u0dd9\u0d9a\u0dd4\u0dad\u0dca \u0dc3\u0dd2\u0dba\u0dbd\u0dd4 \u0dba\u0ddd\u0da2\u0db1\u0dcf \u0daf\u0dd3 \u0d86\u0daf\u0dbb\u0dca\u0dc1 \u0daf\u0d9a\u0dca\u0dc0\u0dcf </p>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> has shape <span translate=no>_^_1_^_</span> </li>\n<li><span translate=no>_^_2_^_</span> has shape <span translate=no>_^_3_^_</span></li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span> \u0dc4\u0dd0\u0da9\u0dba \u0d87\u0dad <span translate=no>_^_1_^_</span> </li>\n<li><span translate=no>_^_2_^_</span> \u0dc4\u0dd0\u0da9\u0dba \u0d87\u0dad <span translate=no>_^_3_^_</span></li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of channels in the image. <span translate=no>_^_1_^_</span> for RGB. </li>\n<li><span translate=no>_^_2_^_</span> is number of channels in the initial feature map that we transform the image into </li>\n<li><span translate=no>_^_3_^_</span> is the list of channel numbers at each resolution. The number of channels is <span translate=no>_^_4_^_</span> </li>\n<li><span translate=no>_^_5_^_</span> is a list of booleans that indicate whether to use attention at each resolution </li>\n<li><span translate=no>_^_6_^_</span> is the number of <span translate=no>_^_7_^_</span> at each resolution</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span> \u0dba\u0db1\u0dd4 \u0dbb\u0dd6\u0db4\u0dba\u0dda \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1. <span translate=no>_^_1_^_</span> RGB \u0dc3\u0db3\u0dc4\u0dcf. </li>\n<li><span translate=no>_^_2_^_</span> \u0d86\u0dbb\u0db8\u0dca\u0db7\u0d9a \u0dc0\u0dd2\u0dc1\u0dda\u0dc2\u0dcf\u0d82\u0d9c \u0dc3\u0dd2\u0dad\u0dd2\u0dba\u0db8\u0dda \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1 \u0d85\u0db4\u0dd2 \u0dbb\u0dd6\u0db4\u0dba \u0db6\u0dc0\u0da7 \u0db4\u0dbb\u0dd2\u0dc0\u0dbb\u0dca\u0dad\u0db1\u0dba \u0d9a\u0dbb\u0db8\u0dd4 </li>\n<li><span translate=no>_^_3_^_</span> \u0dba\u0db1\u0dd4 \u0d91\u0d9a\u0dca \u0d91\u0d9a\u0dca \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0dda \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d85\u0d82\u0d9a \u0dbd\u0dd0\u0dba\u0dd2\u0dc3\u0dca\u0dad\u0dd4\u0dc0\u0dba\u0dd2. \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1 \u0dc0\u0dda <span translate=no>_^_4_^_</span> </li>\n<li><span translate=no>_^_5_^_</span> \u0dba\u0db1\u0dd4 \u0d91\u0d9a\u0dca \u0d91\u0d9a\u0dca \u0dc0\u0dd2\u0db7\u0dda\u0daf\u0db1\u0dba\u0dda \u0daf\u0dd3 \u0d85\u0dc0\u0db0\u0dcf\u0db1\u0dba \u0dba\u0ddc\u0db8\u0dd4 \u0d9a\u0dc5 \u0dba\u0dd4\u0dad\u0dd4\u0daf \u0dba\u0db1\u0dca\u0db1 \u0db4\u0dd9\u0db1\u0dca\u0db1\u0dd4\u0db8\u0dca \u0d9a\u0dbb\u0db1 \u0db6\u0dd6\u0dbd\u0dd2\u0dba\u0db1\u0dca \u0dbd\u0dd0\u0dba\u0dd2\u0dc3\u0dca\u0dad\u0dd4\u0dc0\u0d9a\u0dd2 </li>\n<li><span translate=no>_^_6_^_</span> \u0d91\u0d9a\u0dca \u0d91\u0d9a\u0dca \u0dba\u0ddd\u0da2\u0db1\u0dcf\u0dc0 <span translate=no>_^_7_^_</span> \u0daf\u0dd3 \u0dc3\u0d82\u0d9b\u0dca\u0dba\u0dcf\u0dc0 \u0dc0\u0dda</li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of channels in the input </li>\n<li><span translate=no>_^_1_^_</span> is the number of heads in multi-head attention </li>\n<li><span translate=no>_^_2_^_</span> is the number of dimensions in each head </li>\n<li><span translate=no>_^_3_^_</span> is the number of groups for <a href=\"../../normalization/group_norm/index.html\">group normalization</a></li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span> \u0dba\u0db1\u0dd4 \u0d86\u0daf\u0dcf\u0db1\u0dba\u0dda \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1 </li>\n<li><span translate=no>_^_1_^_</span> \u0db6\u0dc4\u0dd4-\u0dc4\u0dd2\u0dc3 \u0d85\u0dc0\u0db0\u0dcf\u0db1\u0dba \u0dba\u0ddc\u0db8\u0dd4 \u0db4\u0dca\u0dbb\u0db0\u0dcf\u0db1\u0dd3\u0db1\u0dca \u0dc3\u0d82\u0d9b\u0dca\u0dba\u0dcf\u0dc0 \u0dc0\u0dda </li>\n<li><span translate=no>_^_2_^_</span> \u0d91\u0d9a\u0dca \u0d91\u0d9a\u0dca \u0dc4\u0dd2\u0dc3\u0dd9\u0dc4\u0dd2 \u0db8\u0dcf\u0db1\u0dba\u0db1\u0dca \u0d9c\u0dab\u0db1 </li>\n</ul><li><span translate=no>_^_3_^_</span> \u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca <a href=\"../../normalization/group_norm/index.html\">\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0db3\u0dc4\u0dcf \u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca</a>\u0dc3\u0d82\u0d9b\u0dca\u0dba\u0dcf\u0dc0 \u0dc0\u0dda</li>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of dimensions in the embedding</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span> \u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8\u0dda \u0db8\u0dcf\u0db1\u0dba\u0db1\u0dca \u0d9c\u0dab\u0db1 \u0dc0\u0dda</li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of input channels </li>\n<li><span translate=no>_^_1_^_</span> is the number of input channels </li>\n<li><span translate=no>_^_2_^_</span> is the number channels in the time step (<span translate=no>_^_3_^_</span>) embeddings </li>\n<li><span translate=no>_^_4_^_</span> is the number of groups for <a href=\"../../normalization/group_norm/index.html\">group normalization</a> </li>\n<li><span translate=no>_^_5_^_</span> is the dropout rate</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u0d86\u0daf\u0dcf\u0db1 \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1</li>\n<li><span translate=no>_^_1_^_</span>\u0d86\u0daf\u0dcf\u0db1 \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0d9c\u0dab\u0db1</li>\n<li><span translate=no>_^_2_^_</span>\u0d9a\u0dcf\u0dbd\u0dba \u0db4\u0dd2\u0dba\u0dc0\u0dbb (<span translate=no>_^_3_^_</span>) \u0d9a\u0dcf\u0dc0\u0dd0\u0daf\u0dca\u0daf\u0dd3\u0db8\u0dca \u0dc3\u0d82\u0d9b\u0dca\u0dba\u0dcf\u0dc0 \u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf \u0dc0\u0dda</li>\n<li><span translate=no>_^_4_^_</span>\u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca <a href=\"../../normalization/group_norm/index.html\">\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0db3\u0dc4\u0dcf \u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca</a> \u0dc3\u0d82\u0d9b\u0dca\u0dba\u0dcf\u0dc0 \u0dc0\u0dda</li>\n</ul><li><span translate=no>_^_5_^_</span>\u0dc4\u0dd0\u0dbd\u0dc4\u0dd0\u0db4\u0dca\u0db8\u0dda \u0d85\u0db1\u0dd4\u0db4\u0dcf\u0dad\u0dba \u0dc0\u0dda</li>\n",
+ "U-Net model for Denoising Diffusion Probabilistic Models (DDPM)": "\u0dc0\u0dd2\u0dc3\u0dbb\u0dab \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2 \u0db1\u0dd2\u0dbb\u0dd6\u0db4\u0dab\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0dba\u0dd6-\u0db1\u0dd9\u0da7\u0dca \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba (\u0da9\u0dd3\u0da9\u0dd3\u0db4\u0dd3\u0d91\u0db8\u0dca)",
+ "UNet model for Denoising Diffusion Probabilistic Models (DDPM)": "Denoising Diffusion \u0dc3\u0db8\u0dca\u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf\u0dc0 \u0d86\u0d9a\u0dd8\u0dad\u0dd2 \u0dc3\u0db3\u0dc4\u0dcf UNET \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba (DDPM)"
+}
@@ -0,0 +1,76 @@
+{
+ "<h1>U-Net model for <a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a></h1>\n<p>This is a <a href=\"../../unet/index.html\">U-Net</a> based model to predict noise <span translate=no>_^_0_^_</span>.</p>\n<p>U-Net is a gets it&#x27;s name from the U shape in the model diagram. It processes a given image by progressively lowering (halving) the feature map resolution and then increasing the resolution. There are pass-through connection at each resolution.</p>\n<p><span translate=no>_^_1_^_</span></p>\n<p>This implementation contains a bunch of modifications to original U-Net (residual blocks, multi-head attention)  and also adds time-step embeddings <span translate=no>_^_2_^_</span>.</p>\n": "<h1>\u7528\u4e8e<a href=\"index.html\">\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM) \u7684 U-Net \u6a21\u578b</a></h1>\n<p>\u8fd9\u662f\u4e00\u4e2a\u57fa\u4e8e <a href=\"../../unet/index.html\">U-Net</a> \u7684\u6a21\u578b\uff0c\u7528\u4e8e\u9884\u6d4b\u566a\u58f0<span translate=no>_^_0_^_</span>\u3002</p>\n<p>U-Net \u662f\u4ece\u6a21\u578b\u56fe\u4e2d\u7684 U \u5f62\u4e2d\u83b7\u53d6\u5b83\u7684\u540d\u5b57\u3002\u5b83\u901a\u8fc7\u9010\u6b65\u964d\u4f4e\uff08\u51cf\u534a\uff09\u8981\u7d20\u56fe\u5206\u8fa8\u7387\uff0c\u7136\u540e\u63d0\u9ad8\u5206\u8fa8\u7387\u6765\u5904\u7406\u7ed9\u5b9a\u7684\u56fe\u50cf\u3002\u6bcf\u79cd\u5206\u8fa8\u7387\u90fd\u6709\u76f4\u901a\u8fde\u63a5\u3002</p>\n<p><span translate=no>_^_1_^_</span></p>\n<p>\u6b64\u5b9e\u73b0\u5305\u542b\u5bf9\u539f\u59cb U-Net\uff08\u6b8b\u5dee\u5757\u3001\u591a\u5934\u6ce8\u610f\uff09\u7684\u5927\u91cf\u4fee\u6539\uff0c\u8fd8\u6dfb\u52a0\u4e86\u65f6\u95f4\u6b65\u957f\u5d4c\u5165<span translate=no>_^_2_^_</span>\u3002</p>\n",
+ "<h2>U-Net</h2>\n": "<h2>U-Net</h2>\n",
+ "<h3>Attention block</h3>\n<p>This is similar to <a href=\"../../transformers/mha.html\">transformer multi-head attention</a>.</p>\n": "<h3>\u6ce8\u610f\u529b\u5757</h3>\n<p>\u8fd9\u7c7b\u4f3c\u4e8e<a href=\"../../transformers/mha.html\">\u53d8\u538b\u5668\u591a\u5934\u7684\u5173\u6ce8</a>\u3002</p>\n",
+ "<h3>Down block</h3>\n<p>This combines <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span>. These are used in the first half of U-Net at each resolution.</p>\n": "<h3>\u5411\u4e0b\u65b9\u5757</h3>\n<p>\u8fd9\u7ed3\u5408\u4e86<span translate=no>_^_0_^_</span>\u548c<span translate=no>_^_1_^_</span>.\u8fd9\u4e9b\u5728U-Net\u7684\u524d\u534a\u90e8\u5206\u4ee5\u6bcf\u79cd\u5206\u8fa8\u7387\u4f7f\u7528\u3002</p>\n",
+ "<h3>Embeddings for <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u5d4c\u5165\u7528\u4e8e<span translate=no>_^_0_^_</span></h3>\n",
+ "<h3>Middle block</h3>\n<p>It combines a <span translate=no>_^_0_^_</span>, <span translate=no>_^_1_^_</span>, followed by another <span translate=no>_^_2_^_</span>. This block is applied at the lowest resolution of the U-Net.</p>\n": "<h3>\u4e2d\u95f4\u65b9\u5757</h3>\n<p>\u5b83\u7ed3\u5408\u4e86<span translate=no>_^_0_^_</span>\u3001<span translate=no>_^_1_^_</span>\u3001\u540e\u8ddf\u53e6\u4e00\u4e2a<span translate=no>_^_2_^_</span>\u3002\u6b64\u5757\u5e94\u7528\u4e8e U-Net \u7684\u6700\u4f4e\u5206\u8fa8\u7387\u3002</p>\n",
+ "<h3>Residual block</h3>\n<p>A residual block has two convolution layers with group normalization. Each resolution is processed with two residual blocks.</p>\n": "<h3>\u5269\u4f59\u65b9\u5757</h3>\n<p>\u6b8b\u5dee\u5757\u5177\u6709\u4e24\u4e2a\u5177\u6709\u7ec4\u5f52\u4e00\u5316\u7684\u5377\u79ef\u5c42\u3002\u6bcf\u4e2a\u5206\u8fa8\u7387\u90fd\u4f7f\u7528\u4e24\u4e2a\u6b8b\u5dee\u5757\u8fdb\u884c\u5904\u7406\u3002</p>\n",
+ "<h3>Scale down the feature map by <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u6309\u6bd4\u4f8b\u7f29\u5c0f\u8981\u7d20\u5730\u56fe<span translate=no>_^_0_^_</span></h3>\n",
+ "<h3>Scale up the feature map by <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u6309\u6bd4\u4f8b\u653e\u5927\u8981\u7d20\u5730\u56fe<span translate=no>_^_0_^_</span></h3>\n",
+ "<h3>Swish activation function</h3>\n<p><span translate=no>_^_0_^_</span></p>\n": "<h3>Swish \u6fc0\u6d3b\u529f\u80fd</h3>\n<p><span translate=no>_^_0_^_</span></p>\n",
+ "<h3>Up block</h3>\n<p>This combines <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span>. These are used in the second half of U-Net at each resolution.</p>\n": "<h3>\u5411\u4e0a\u65b9\u5757</h3>\n<p>\u8fd9\u7ed3\u5408\u4e86<span translate=no>_^_0_^_</span>\u548c<span translate=no>_^_1_^_</span>.\u8fd9\u4e9b\u5728U-Net\u7684\u540e\u534a\u90e8\u5206\u4ee5\u6bcf\u79cd\u5206\u8fa8\u7387\u4f7f\u7528\u3002</p>\n",
+ "<h4>First half of U-Net - decreasing resolution</h4>\n": "<h4>U-Net \u7684\u524d\u534a\u90e8\u5206-\u5206\u8fa8\u7387\u964d\u4f4e</h4>\n",
+ "<h4>Second half of U-Net - increasing resolution</h4>\n": "<h4>U-Net \u7684\u540e\u534a\u90e8\u5206-\u63d0\u9ad8\u5206\u8fa8\u7387</h4>\n",
+ "<p> </p>\n": "<p></p>\n",
+ "<p><span translate=no>_^_0_^_</span> at the same resolution </p>\n": "<p><span translate=no>_^_0_^_</span>\u4ee5\u76f8\u540c\u7684\u5206\u8fa8\u7387</p>\n",
+ "<p><span translate=no>_^_0_^_</span> is not used, but it&#x27;s kept in the arguments because for the attention layer function signature to match with <span translate=no>_^_1_^_</span>. </p>\n": "<p><span translate=no>_^_0_^_</span>\u672a\u4f7f\u7528\uff0c\u4f46\u5b83\u4fdd\u7559\u5728\u53c2\u6570\u4e2d\uff0c\u56e0\u4e3a\u8981\u4e0e\u6ce8\u610f\u5c42\u51fd\u6570\u7b7e\u540d\u5339\u914d<span translate=no>_^_1_^_</span>\u3002</p>\n",
+ "<p><span translate=no>_^_0_^_</span> will store outputs at each resolution for skip connection </p>\n": "<p><span translate=no>_^_0_^_</span>\u5c06\u4ee5\u6bcf\u79cd\u5206\u8fa8\u7387\u5b58\u50a8\u8f93\u51fa\u4ee5\u8fdb\u884c\u8df3\u8fc7\u8fde\u63a5</p>\n",
+ "<p>Activation </p>\n": "<p>\u6fc0\u6d3b</p>\n",
+ "<p>Add <span translate=no>_^_0_^_</span> </p>\n": "<p>\u6dfb\u52a0<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Add skip connection </p>\n": "<p>\u6dfb\u52a0\u8df3\u8fc7\u8fde\u63a5</p>\n",
+ "<p>Add the shortcut connection and return </p>\n": "<p>\u6dfb\u52a0\u5feb\u6377\u65b9\u5f0f\u8fde\u63a5\u5e76\u8fd4\u56de</p>\n",
+ "<p>Add time embeddings </p>\n": "<p>\u6dfb\u52a0\u65f6\u95f4\u5d4c\u5165</p>\n",
+ "<p>Calculate scaled dot-product <span translate=no>_^_0_^_</span> </p>\n": "<p>\u8ba1\u7b97\u7f29\u653e\u7684\u70b9\u79ef<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Change <span translate=no>_^_0_^_</span> to shape <span translate=no>_^_1_^_</span> </p>\n": "<p>\u6539<span translate=no>_^_0_^_</span>\u6210\u5f62\u72b6<span translate=no>_^_1_^_</span></p>\n",
+ "<p>Change to shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u6539\u6210\u5f62\u72b6<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Combine the set of modules </p>\n": "<p>\u7ec4\u5408\u8fd9\u7ec4\u6a21\u5757</p>\n",
+ "<p>Create sinusoidal position embeddings <a href=\"../../transformers/positional_encoding.html\">same as those from the transformer</a></p>\n<span translate=no>_^_0_^_</span><p>where <span translate=no>_^_1_^_</span> is <span translate=no>_^_2_^_</span> </p>\n": "<p>\u521b\u5efa\u4e0e<a href=\"../../transformers/positional_encoding.html\">\u53d8\u538b\u5668\u76f8\u540c\u7684</a>\u6b63\u5f26\u4f4d\u7f6e\u5d4c\u5165</p>\n<span translate=no>_^_0_^_</span><p>\u5728\u54ea<span translate=no>_^_1_^_</span>\u91cc<span translate=no>_^_2_^_</span></p>\n",
+ "<p>Default <span translate=no>_^_0_^_</span> </p>\n": "<p>\u9ed8\u8ba4<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Down sample at all resolutions except the last </p>\n": "<p>\u9664\u6700\u540e\u4e00\u4e2a\u5206\u8fa8\u7387\u4e4b\u5916\u7684\u6240\u6709\u5206\u8fa8\u7387\u90fd\u5411\u4e0b\u91c7\u6837</p>\n",
+ "<p>Final block to reduce the number of channels </p>\n": "<p>\u51cf\u5c11\u4fe1\u9053\u6570\u91cf\u7684\u6700\u7ec8\u533a\u5757</p>\n",
+ "<p>Final normalization and convolution </p>\n": "<p>\u6700\u7ec8\u5f52\u4e00\u5316\u548c\u5377\u79ef</p>\n",
+ "<p>Final normalization and convolution layer </p>\n": "<p>\u6700\u7ec8\u5f52\u4e00\u5316\u548c\u5377\u79ef\u5c42</p>\n",
+ "<p>First convolution layer </p>\n": "<p>\u7b2c\u4e00\u4e2a\u5377\u79ef\u5c42</p>\n",
+ "<p>First half of U-Net </p>\n": "<p>U-Net \u7684\u4e0a\u534a\u5e74</p>\n",
+ "<p>First linear layer </p>\n": "<p>\u7b2c\u4e00\u4e2a\u7ebf\u6027\u5c42</p>\n",
+ "<p>For each resolution </p>\n": "<p>\u5bf9\u4e8e\u6bcf\u79cd\u5206\u8fa8\u7387</p>\n",
+ "<p>Get image projection </p>\n": "<p>\u83b7\u53d6\u56fe\u50cf\u6295\u5f71</p>\n",
+ "<p>Get query, key, and values (concatenated) and shape it to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u83b7\u53d6\u67e5\u8be2\u3001\u952e\u548c\u503c\uff08\u4e32\u8054\uff09\u5e76\u5c06\u5176\u8c03\u6574\u4e3a<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Get shape </p>\n": "<p>\u5851\u9020\u8eab\u6750</p>\n",
+ "<p>Get the skip connection from first half of U-Net and concatenate </p>\n": "<p>\u4ece U-Net \u7684\u524d\u534a\u90e8\u5206\u83b7\u53d6\u8df3\u8fc7\u8fde\u63a5\u5e76\u8fde\u63a5</p>\n",
+ "<p>Get time-step embeddings </p>\n": "<p>\u83b7\u53d6\u65f6\u95f4\u6b65\u957f\u5d4c\u5165</p>\n",
+ "<p>Group normalization and the first convolution layer </p>\n": "<p>\u7ec4\u5f52\u4e00\u5316\u548c\u7b2c\u4e00\u4e2a\u5377\u79ef\u5c42</p>\n",
+ "<p>Group normalization and the second convolution layer </p>\n": "<p>\u7ec4\u5f52\u4e00\u5316\u548c\u7b2c\u4e8c\u4e2a\u5377\u79ef\u5c42</p>\n",
+ "<p>If the number of input channels is not equal to the number of output channels we have to project the shortcut connection </p>\n": "<p>\u5982\u679c\u8f93\u5165\u901a\u9053\u7684\u6570\u91cf\u4e0d\u7b49\u4e8e\u8f93\u51fa\u901a\u9053\u7684\u6570\u91cf\uff0c\u6211\u4eec\u5fc5\u987b\u6295\u5f71\u5feb\u6377\u65b9\u5f0f\u8fde\u63a5</p>\n",
+ "<p>Linear layer for final transformation </p>\n": "<p>\u7528\u4e8e\u6700\u7ec8\u53d8\u6362\u7684\u7ebf\u6027\u5c42</p>\n",
+ "<p>Linear layer for time embeddings </p>\n": "<p>\u7528\u4e8e\u65f6\u95f4\u5d4c\u5165\u7684\u7ebf\u6027\u5c42</p>\n",
+ "<p>Middle (bottom) </p>\n": "<p>\u4e2d\u95f4\uff08\u5e95\u90e8\uff09</p>\n",
+ "<p>Middle block </p>\n": "<p>\u4e2d\u95f4\u65b9\u5757</p>\n",
+ "<p>Multiply by values </p>\n": "<p>\u4e58\u4ee5\u503c</p>\n",
+ "<p>Normalization layer </p>\n": "<p>\u5f52\u4e00\u5316\u5c42</p>\n",
+ "<p>Number of channels </p>\n": "<p>\u9891\u9053\u6570\u91cf</p>\n",
+ "<p>Number of output channels at this resolution </p>\n": "<p>\u6b64\u5206\u8fa8\u7387\u4e0b\u7684\u8f93\u51fa\u58f0\u9053\u6570</p>\n",
+ "<p>Number of resolutions </p>\n": "<p>\u5206\u8fa8\u7387\u6570\u91cf</p>\n",
+ "<p>Project image into feature map </p>\n": "<p>\u5c06\u56fe\u50cf\u6295\u5f71\u5230\u8981\u7d20\u5730\u56fe\u4e2d</p>\n",
+ "<p>Projections for query, key and values </p>\n": "<p>\u67e5\u8be2\u3001\u952e\u548c\u503c\u7684\u6295\u5f71</p>\n",
+ "<p>Reshape to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u91cd\u5851\u4e3a<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Scale for dot-product attention </p>\n": "<p>\u7f29\u653e\u70b9\u4ea7\u54c1\u6ce8\u610f\u529b</p>\n",
+ "<p>Second convolution layer </p>\n": "<p>\u7b2c\u4e8c\u4e2a\u5377\u79ef\u5c42</p>\n",
+ "<p>Second half of U-Net </p>\n": "<p>U-Net \u7684\u4e0b\u534a\u573a</p>\n",
+ "<p>Second linear layer </p>\n": "<p>\u7b2c\u4e8c\u4e2a\u7ebf\u6027\u5c42</p>\n",
+ "<p>Softmax along the sequence dimension <span translate=no>_^_0_^_</span> </p>\n": "<p>\u987a\u5e8f\u7ef4\u5ea6\u4e0a\u7684 Softmax<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Split query, key, and values. Each of them will have shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u62c6\u5206\u67e5\u8be2\u3001\u952e\u548c\u503c\u3002\u4ed6\u4eec\u6bcf\u4e2a\u4eba\u90fd\u4f1a\u6709\u5f62\u72b6<span translate=no>_^_0_^_</span></p>\n",
+ "<p>The input has <span translate=no>_^_0_^_</span> because we concatenate the output of the same resolution from the first half of the U-Net </p>\n": "<p>\u8f93\u5165\u4e4b<span translate=no>_^_0_^_</span>\u6240\u4ee5\u6709\uff0c\u662f\u56e0\u4e3a\u6211\u4eec\u5c06 U-Net \u524d\u534a\u90e8\u5206\u76f8\u540c\u5206\u8fa8\u7387\u7684\u8f93\u51fa\u8fde\u63a5\u8d77\u6765</p>\n",
+ "<p>Time embedding layer. Time embedding has <span translate=no>_^_0_^_</span> channels </p>\n": "<p>\u65f6\u95f4\u5d4c\u5165\u5c42\u3002\u65f6\u95f4\u5d4c\u5165\u6709<span translate=no>_^_0_^_</span>\u9891\u9053</p>\n",
+ "<p>Transform to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u53d8\u6362\u4e3a<span translate=no>_^_0_^_</span></p>\n",
+ "<p>Transform with the MLP </p>\n": "<p>\u4f7f\u7528 MLP \u8fdb\u884c\u8f6c\u578b</p>\n",
+ "<p>Up sample at all resolutions except last </p>\n": "<p>\u9664\u6700\u540e\u4e00\u4e2a\u4ee5\u5916\u7684\u6240\u6709\u5206\u8fa8\u7387\u5411\u4e0a\u91c7\u6837</p>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> has shape <span translate=no>_^_1_^_</span> </li>\n<li><span translate=no>_^_2_^_</span> has shape <span translate=no>_^_3_^_</span></li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u6709\u5f62\u72b6<span translate=no>_^_1_^_</span></li>\n<li><span translate=no>_^_2_^_</span>\u6709\u5f62\u72b6<span translate=no>_^_3_^_</span></li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of channels in the image. <span translate=no>_^_1_^_</span> for RGB. </li>\n<li><span translate=no>_^_2_^_</span> is number of channels in the initial feature map that we transform the image into </li>\n<li><span translate=no>_^_3_^_</span> is the list of channel numbers at each resolution. The number of channels is <span translate=no>_^_4_^_</span> </li>\n<li><span translate=no>_^_5_^_</span> is a list of booleans that indicate whether to use attention at each resolution </li>\n<li><span translate=no>_^_6_^_</span> is the number of <span translate=no>_^_7_^_</span> at each resolution</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u662f\u56fe\u50cf\u4e2d\u7684\u901a\u9053\u6570\u3002<span translate=no>_^_1_^_</span>\u5bf9\u4e8e RGB\u3002</li>\n<li><span translate=no>_^_2_^_</span>\u662f\u521d\u59cb\u7279\u5f81\u56fe\u4e2d\u6211\u4eec\u5c06\u56fe\u50cf\u8f6c\u6362\u4e3a\u7684\u901a\u9053\u6570</li>\n<li><span translate=no>_^_3_^_</span>\u662f\u6bcf\u79cd\u5206\u8fa8\u7387\u4e0b\u7684\u901a\u9053\u7f16\u53f7\u5217\u8868\u3002\u9891\u9053\u7684\u6570\u91cf\u662f<span translate=no>_^_4_^_</span></li>\n<li><span translate=no>_^_5_^_</span>\u662f\u4e00\u4e2a\u5e03\u5c14\u503c\u5217\u8868\uff0c\u7528\u4e8e\u6307\u793a\u662f\u5426\u5728\u6bcf\u4e2a\u5206\u8fa8\u7387\u4e0b\u4f7f\u7528\u6ce8\u610f\u529b</li>\n<li><span translate=no>_^_6_^_</span>\u662f\u6bcf\u79cd\u5206\u8fa8<span translate=no>_^_7_^_</span>\u7387\u7684\u6570\u5b57</li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of channels in the input </li>\n<li><span translate=no>_^_1_^_</span> is the number of heads in multi-head attention </li>\n<li><span translate=no>_^_2_^_</span> is the number of dimensions in each head </li>\n<li><span translate=no>_^_3_^_</span> is the number of groups for <a href=\"../../normalization/group_norm/index.html\">group normalization</a></li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u662f\u8f93\u5165\u4e2d\u7684\u58f0\u9053\u6570</li>\n<li><span translate=no>_^_1_^_</span>\u662f\u591a\u5934\u5173\u6ce8\u4e2d\u7684\u5934\u90e8\u6570\u91cf</li>\n<li><span translate=no>_^_2_^_</span>\u662f\u6bcf\u4e2a\u5934\u90e8\u7684\u5c3a\u5bf8\u6570</li>\n<li><span translate=no>_^_3_^_</span>\u662f\u7ec4\u5f52\u4e00<a href=\"../../normalization/group_norm/index.html\">\u5316\u7684\u7ec4</a>\u6570</li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of dimensions in the embedding</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u662f\u5d4c\u5165\u4e2d\u7684\u7ef4\u6570</li></ul>\n",
+ "<ul><li><span translate=no>_^_0_^_</span> is the number of input channels </li>\n<li><span translate=no>_^_1_^_</span> is the number of input channels </li>\n<li><span translate=no>_^_2_^_</span> is the number channels in the time step (<span translate=no>_^_3_^_</span>) embeddings </li>\n<li><span translate=no>_^_4_^_</span> is the number of groups for <a href=\"../../normalization/group_norm/index.html\">group normalization</a> </li>\n<li><span translate=no>_^_5_^_</span> is the dropout rate</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u662f\u8f93\u5165\u901a\u9053\u7684\u6570\u91cf</li>\n<li><span translate=no>_^_1_^_</span>\u662f\u8f93\u5165\u901a\u9053\u7684\u6570\u91cf</li>\n<li><span translate=no>_^_2_^_</span>\u662f\u65f6\u95f4\u6b65 (<span translate=no>_^_3_^_</span>) \u5d4c\u5165\u4e2d\u7684\u901a\u9053\u6570</li>\n<li><span translate=no>_^_4_^_</span>\u662f\u7528\u4e8e\u7ec4<a href=\"../../normalization/group_norm/index.html\">\u6807\u51c6\u5316\u7684\u7ec4</a>\u6570</li>\n<li><span translate=no>_^_5_^_</span>\u662f\u8f8d\u5b66\u7387</li></ul>\n",
+ "U-Net model for Denoising Diffusion Probabilistic Models (DDPM)": "\u7528\u4e8e\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM) \u7684 U-Net \u6a21\u578b",
+ "UNet model for Denoising Diffusion Probabilistic Models (DDPM)": "\u7528\u4e8e\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM) \u7684 unET \u6a21\u578b"
+}
@@ -0,0 +1,5 @@
+{
+ "<h1>Utility functions for <a href=\"index.html\">DDPM</a> experiemnt</h1>\n": "<h1><a href=\"index.html\">DPM</a> \u5b9f\u9a13\u7528\u30e6\u30fc\u30c6\u30a3\u30ea\u30c6\u30a3\u95a2\u6570</h1>\n",
+ "<p>Gather consts for <span translate=no>_^_0_^_</span> and reshape to feature map shape </p>\n": "<p><span translate=no>_^_0_^_</span>\u5b9a\u6570\u3092\u96c6\u3081\u3066\u30d5\u30a3\u30fc\u30c1\u30e3\u30de\u30c3\u30d7\u306e\u5f62\u72b6\u306b\u5f62\u72b6\u3092\u5909\u3048\u308b</p>\n",
+ "Utility functions for DDPM experiment": "DDPM \u5b9f\u9a13\u7528\u30e6\u30fc\u30c6\u30a3\u30ea\u30c6\u30a3\u95a2\u6570"
+}
@@ -0,0 +1,5 @@
+{
+ "<h1>Utility functions for <a href=\"index.html\">DDPM</a> experiemnt</h1>\n": "<h1><a href=\"index.html\">DDPM</a> \u0d85\u0dad\u0dca\u0daf\u0dd0\u0d9a\u0dd3\u0db8\u0dca \u0dc3\u0db3\u0dc4\u0dcf \u0d8b\u0db4\u0dba\u0ddd\u0d9c\u0dd2\u0dad\u0dcf \u0d9a\u0dcf\u0dbb\u0dca\u0dba\u0dba\u0db1\u0dca</h1>\n",
+ "<p>Gather consts for <span translate=no>_^_0_^_</span> and reshape to feature map shape </p>\n": "<p>\u0dc3\u0dd2\u0dad\u0dd2\u0dba\u0db8\u0dca\u0dc4\u0dd0\u0da9\u0dba\u0da7 \u0dc0\u0dd2\u0dc1\u0dda\u0dc2\u0dcf\u0d82\u0d9c \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0da7 <span translate=no>_^_0_^_</span> \u0dc3\u0dc4 \u0db1\u0dd0\u0dc0\u0dad \u0dc3\u0d9a\u0dc3\u0dca \u0d9a\u0dd2\u0dbb\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0d9c\u0dd0\u0da7\u0dd4\u0db8\u0dca \u0d91\u0d9a\u0dca\u0dbb\u0dd0\u0dc3\u0dca \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
+ "Utility functions for DDPM experiment": "\u0da9\u0dd3\u0da9\u0dd3\u0db4\u0dd3\u0d91\u0db8\u0dca \u0d85\u0dad\u0dca\u0dc4\u0daf\u0dcf \u0db6\u0dd0\u0dbd\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0d8b\u0db4\u0dba\u0ddd\u0d9c\u0dd2\u0dad\u0dcf \u0d9a\u0dcf\u0dbb\u0dca\u0dba\u0dba\u0db1\u0dca"
+}
@@ -0,0 +1,5 @@
+{
+ "<h1>Utility functions for <a href=\"index.html\">DDPM</a> experiemnt</h1>\n": "<h1><a href=\"index.html\">DDPM</a> \u5b9e\u9a8c\u7684\u5b9e\u7528\u7a0b\u5e8f\u51fd\u6570</h1>\n",
+ "<p>Gather consts for <span translate=no>_^_0_^_</span> and reshape to feature map shape </p>\n": "<p>\u6536\u96c6\u8981\u7d20\u5730\u56fe\u5f62\u72b6\u7684<span translate=no>_^_0_^_</span>\u5e38\u91cf\u5e76\u5c06\u5176\u6574\u5f62\u4e3a\u8981\u7d20\u5730\u56fe\u5f62\u72b6</p>\n",
+ "Utility functions for DDPM experiment": "DDPM \u5b9e\u9a8c\u7684\u5b9e\u7528\u7a0b\u5e8f\u51fd\u6570"
+}