chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"<h1>Train a large model on CIFAR 10</h1>\n<p>This trains a large model on CIFAR 10 for <a href=\"index.html\">distillation</a>.</p>\n": "<h1>CIFAR 10 \u3067\u5927\u898f\u6a21\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3059\u308b</h1>\n<p>\u3053\u308c\u306fCIFAR <a href=\"index.html\">10\u306e\u5927\u578b\u30e2\u30c7\u30eb\u3092\u84b8\u7559\u7528\u306b\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u307e\u3059</a>\u3002</p>\n",
|
||||
"<h2>Configurations</h2>\n<p>We use <a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a> which defines all the dataset related configurations, optimizer, and a training loop.</p>\n": "<h2>\u30b3\u30f3\u30d5\u30a3\u30ae\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3</h2>\n<p>\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u95a2\u9023\u3059\u308b\u3059\u3079\u3066\u306e\u69cb\u6210\u3001\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30eb\u30fc\u30d7\u3092\u5b9a\u7fa9\u3059\u308b\u3082\u306e\u3092\u4f7f\u7528\u3057\u3066\u3044\u307e\u3059<a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a>\u3002</p>\n",
|
||||
"<h3>Create model</h3>\n": "<h3>\u30e2\u30c7\u30eb\u4f5c\u6210</h3>\n",
|
||||
"<h3>VGG style model for CIFAR-10 classification</h3>\n<p>This derives from the <a href=\"../experiments/cifar10.html\">generic VGG style architecture</a>.</p>\n": "<h3>CIFAR-10 \u5206\u985e\u7528\u306e VGG \u30b9\u30bf\u30a4\u30eb\u30e2\u30c7\u30eb</h3>\n<p><a href=\"../experiments/cifar10.html\">\u3053\u308c\u306f\u4e00\u822c\u7684\u306a VGG \u30b9\u30bf\u30a4\u30eb\u306e\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u306b\u7531\u6765\u3057\u307e\u3059</a>\u3002</p>\n",
|
||||
"<p> </p>\n": "<p></p>\n",
|
||||
"<p> Create a convolution layer and the activations</p>\n": "<p>\u30b3\u30f3\u30dc\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u30ec\u30a4\u30e4\u30fc\u3068\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3\u306e\u4f5c\u6210</p>\n",
|
||||
"<p>Batch normalization </p>\n": "<p>\u30d0\u30c3\u30c1\u6b63\u898f\u5316</p>\n",
|
||||
"<p>Convolution layer </p>\n": "<p>\u30b3\u30f3\u30dc\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u30ec\u30a4\u30e4\u30fc</p>\n",
|
||||
"<p>Create a model with given convolution sizes (channels) </p>\n": "<p>\u4e0e\u3048\u3089\u308c\u305f\u7573\u307f\u8fbc\u307f\u30b5\u30a4\u30ba (\u30c1\u30e3\u30cd\u30eb) \u3067\u30e2\u30c7\u30eb\u3092\u4f5c\u6210</p>\n",
|
||||
"<p>Create configurations </p>\n": "<p>\u69cb\u6210\u306e\u4f5c\u6210</p>\n",
|
||||
"<p>Create experiment </p>\n": "<p>\u5b9f\u9a13\u3092\u4f5c\u6210</p>\n",
|
||||
"<p>Dropout </p>\n": "<p>\u30c9\u30ed\u30c3\u30d7\u30a2\u30a6\u30c8</p>\n",
|
||||
"<p>Load configurations </p>\n": "<p>\u69cb\u6210\u3092\u30ed\u30fc\u30c9</p>\n",
|
||||
"<p>Print number of parameters in the model </p>\n": "<p>\u30e2\u30c7\u30eb\u5185\u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u306e\u6570\u3092\u51fa\u529b\u3057\u307e\u3059</p>\n",
|
||||
"<p>ReLU activation </p>\n": "<p>ReLU \u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3</p>\n",
|
||||
"<p>Set model for saving/loading </p>\n": "<p>\u4fdd\u5b58/\u8aad\u307f\u8fbc\u307f\u7528\u306e\u30e2\u30c7\u30eb\u3092\u8a2d\u5b9a</p>\n",
|
||||
"<p>Start the experiment and run the training loop </p>\n": "<p>\u5b9f\u9a13\u3092\u958b\u59cb\u3057\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30eb\u30fc\u30d7\u3092\u5b9f\u884c\u3057\u307e\u3059</p>\n",
|
||||
"Train a large model on CIFAR 10": "CIFAR 10 \u3067\u5927\u898f\u6a21\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3059\u308b",
|
||||
"Train a large model on CIFAR 10 for distillation.": "CIFAR 10 \u3067\u84b8\u7559\u7528\u306e\u5927\u578b\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u307e\u3059\u3002"
|
||||
}
|
||||
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"<h1>Train a large model on CIFAR 10</h1>\n<p>This trains a large model on CIFAR 10 for <a href=\"index.html\">distillation</a>.</p>\n<p><a href=\"https://app.labml.ai/run/d46cd53edaec11eb93c38d6538aee7d6\"><span translate=no>_^_0_^_</span></a></p>\n": "<h1>CIFAR10 \u0dc4\u0dd2 \u0dc0\u0dd2\u0dc1\u0dcf\u0dbd \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1</h1>\n<p>\u0db8\u0dd9\u0dba <a href=\"index.html\">\u0d86\u0dc3\u0dc0\u0db1\u0dba</a>\u0dc3\u0db3\u0dc4\u0dcf CIFAR 10 \u0dc4\u0dd2 \u0dc0\u0dd2\u0dc1\u0dcf\u0dbd \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb\u0dba\u0dd2. </p>\n<p><a href=\"https://app.labml.ai/run/d46cd53edaec11eb93c38d6538aee7d6\"><span translate=no>_^_0_^_</span></a></p>\n",
|
||||
"<h2>Configurations</h2>\n<p>We use <a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a> which defines all the dataset related configurations, optimizer, and a training loop.</p>\n": "<h2>\u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dca</h2>\n<p>\u0dc3\u0dd2\u0dba\u0dbd\u0dd4\u0db8\u0daf\u0dad\u0dca\u0dad \u0d9a\u0da7\u0dca\u0da7\u0dbd \u0d86\u0dc1\u0dca\u0dbb\u0dd2\u0dad \u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0dba\u0db1\u0dca, \u0db4\u0dca\u0dbb\u0dc1\u0dc3\u0dca\u0dad\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0dc4 \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0dbd\u0dd6\u0db4\u0dba\u0d9a\u0dca \u0db1\u0dd2\u0dbb\u0dca\u0dc0\u0da0\u0db1\u0dba \u0d9a\u0dbb\u0db1 \u0d85\u0db4\u0dd2 \u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf <a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a> \u0d9a\u0dbb\u0db8\u0dd4. </p>\n",
|
||||
"<h3>Create model</h3>\n": "<h3>\u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1</h3>\n",
|
||||
"<h3>VGG style model for CIFAR-10 classification</h3>\n<p>This derives from the <a href=\"../experiments/cifar10.html\">generic VGG style architecture</a>.</p>\n": "<h3>CIFA-10\u0dc0\u0dbb\u0dca\u0d9c\u0dd3\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0db3\u0dc4\u0dcf VGG \u0dc0\u0dd2\u0dbd\u0dcf\u0dc3\u0dd2\u0dad\u0dcf\u0dc0\u0dda \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba</h3>\n<p>\u0db8\u0dd9\u0dba <a href=\"../experiments/cifar10.html\">\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba VGG \u0dc0\u0dd2\u0dbd\u0dcf\u0dc3\u0dd2\u0dad\u0dcf\u0dc0\u0dda \u0d9c\u0dd8\u0dc4 \u0db1\u0dd2\u0dbb\u0dca\u0db8\u0dcf\u0dab \u0dc1\u0dd2\u0dbd\u0dca\u0db4\u0dba\u0dd9\u0db1\u0dca</a>\u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dd3. </p>\n",
|
||||
"<p> </p>\n": "<p> </p>\n",
|
||||
"<p> Create a convolution layer and the activations</p>\n": "<p> \u0dc3\u0d82\u0dc0\u0dc4\u0db1\u0dc3\u0dca\u0dad\u0dbb\u0dba\u0d9a\u0dca \u0dc3\u0dc4 \u0dc3\u0d9a\u0dca\u0dbb\u0dd2\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dca \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1</p>\n",
|
||||
"<p>Batch normalization </p>\n": "<p>\u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba </p>\n",
|
||||
"<p>Convolution layer </p>\n": "<p>\u0dc3\u0d82\u0dc0\u0dc4\u0db1\u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
|
||||
"<p>Create a model with given convolution sizes (channels) </p>\n": "<p>\u0dbd\u0db6\u0dcf\u0daf\u0dd3 \u0d87\u0dad\u0dd2 \u0dc3\u0d82\u0dc0\u0dc4\u0db1 \u0db4\u0dca\u0dbb\u0db8\u0dcf\u0dab (\u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf) \u0dc3\u0dc4\u0dd2\u0dad \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \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 experiment </p>\n": "<p>\u0d85\u0dad\u0dca\u0dc4\u0daf\u0dcf\u0db6\u0dd0\u0dbd\u0dd3\u0db8 \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
|
||||
"<p>Dropout </p>\n": "<p>\u0dc4\u0dd0\u0dbd\u0dd3\u0db8 </p>\n",
|
||||
"<p>Load configurations </p>\n": "<p>\u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0dba\u0db1\u0dca\u0db4\u0dd6\u0dbb\u0dab\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
|
||||
"<p>Print number of parameters in the model </p>\n": "<p>\u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0dda\u0db4\u0dbb\u0dcf\u0db8\u0dd2\u0dad\u0dd2 \u0d9c\u0dab\u0db1 \u0db8\u0dd4\u0daf\u0dca\u0dbb\u0dab\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
|
||||
"<p>ReLU activation </p>\n": "<p>Relu\u0dc3\u0d9a\u0dca\u0dbb\u0dd2\u0dba </p>\n",
|
||||
"<p>Set model for saving/loading </p>\n": "<p>\u0d89\u0dad\u0dd2\u0dbb\u0dd2\u0d9a\u0dd2\u0dbb\u0dd3\u0db8/\u0db4\u0dd0\u0da7\u0dc0\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba \u0dc3\u0d9a\u0dc3\u0db1\u0dca\u0db1 </p>\n",
|
||||
"<p>Start the experiment and run the training loop </p>\n": "<p>\u0d85\u0dad\u0dca\u0dc4\u0daf\u0dcf\u0db6\u0dd0\u0dbd\u0dd3\u0db8 \u0d86\u0dbb\u0db8\u0dca\u0db7 \u0d9a\u0dbb \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0dbd\u0dd6\u0db4\u0dba \u0d9a\u0dca\u0dbb\u0dd2\u0dba\u0dcf\u0dad\u0dca\u0db8\u0d9a \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
|
||||
"Train a large model on CIFAR 10": "CIFAR 10 \u0dc4\u0dd2 \u0dc0\u0dd2\u0dc1\u0dcf\u0dbd \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1",
|
||||
"Train a large model on CIFAR 10 for distillation.": "\u0d86\u0dc3\u0dc0\u0db1\u0dba \u0dc3\u0db3\u0dc4\u0dcf CIFAR 10 \u0dc4\u0dd2 \u0dc0\u0dd2\u0dc1\u0dcf\u0dbd \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1."
|
||||
}
|
||||
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"<h1>Train a large model on CIFAR 10</h1>\n<p>This trains a large model on CIFAR 10 for <a href=\"index.html\">distillation</a>.</p>\n": "<h1>\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3\u4e00\u4e2a\u5927\u578b\u6a21\u578b</h1>\n<p>\u8fd9\u4f1a\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3\u4e00\u4e2a\u7528\u4e8e<a href=\"index.html\">\u84b8\u998f</a>\u7684\u5927\u578b\u6a21\u578b\u3002</p>\n",
|
||||
"<h2>Configurations</h2>\n<p>We use <a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a> which defines all the dataset related configurations, optimizer, and a training loop.</p>\n": "<h2>\u914d\u7f6e</h2>\n<p>\u6211\u4eec\u4f7f\u7528<a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a>\u5b83\u6765\u5b9a\u4e49\u6240\u6709\u4e0e\u6570\u636e\u96c6\u76f8\u5173\u7684\u914d\u7f6e\u3001\u4f18\u5316\u5668\u548c\u8bad\u7ec3\u5faa\u73af\u3002</p>\n",
|
||||
"<h3>Create model</h3>\n": "<h3>\u521b\u5efa\u6a21\u578b</h3>\n",
|
||||
"<h3>VGG style model for CIFAR-10 classification</h3>\n<p>This derives from the <a href=\"../experiments/cifar10.html\">generic VGG style architecture</a>.</p>\n": "<h3>\u9002\u7528\u4e8e CIFAR-10 \u5206\u7c7b\u7684 VGG \u6837\u5f0f\u6a21\u578b</h3>\n<p>\u8fd9\u6e90\u4e8e<a href=\"../experiments/cifar10.html\">\u901a\u7528\u7684 VGG \u98ce\u683c\u67b6\u6784</a>\u3002</p>\n",
|
||||
"<p> </p>\n": "<p></p>\n",
|
||||
"<p> Create a convolution layer and the activations</p>\n": "<p>\u521b\u5efa\u5377\u79ef\u5c42\u548c\u6fc0\u6d3b</p>\n",
|
||||
"<p>Batch normalization </p>\n": "<p>\u6279\u91cf\u6807\u51c6\u5316</p>\n",
|
||||
"<p>Convolution layer </p>\n": "<p>\u5377\u79ef\u5c42</p>\n",
|
||||
"<p>Create a model with given convolution sizes (channels) </p>\n": "<p>\u4f7f\u7528\u7ed9\u5b9a\u7684\u5377\u79ef\u5927\u5c0f\uff08\u901a\u9053\uff09\u521b\u5efa\u6a21\u578b</p>\n",
|
||||
"<p>Create configurations </p>\n": "<p>\u521b\u5efa\u914d\u7f6e</p>\n",
|
||||
"<p>Create experiment </p>\n": "<p>\u521b\u5efa\u5b9e\u9a8c</p>\n",
|
||||
"<p>Dropout </p>\n": "<p>\u8f8d\u5b66</p>\n",
|
||||
"<p>Load configurations </p>\n": "<p>\u88c5\u8f7d\u914d\u7f6e</p>\n",
|
||||
"<p>Print number of parameters in the model </p>\n": "<p>\u6253\u5370\u6a21\u578b\u4e2d\u53c2\u6570\u7684\u6570\u91cf</p>\n",
|
||||
"<p>ReLU activation </p>\n": "<p>\u6fc0\u6d3b ReLU</p>\n",
|
||||
"<p>Set model for saving/loading </p>\n": "<p>\u8bbe\u7f6e\u4fdd\u5b58/\u52a0\u8f7d\u7684\u6a21\u578b</p>\n",
|
||||
"<p>Start the experiment and run the training loop </p>\n": "<p>\u5f00\u59cb\u5b9e\u9a8c\u5e76\u8fd0\u884c\u8bad\u7ec3\u5faa\u73af</p>\n",
|
||||
"Train a large model on CIFAR 10": "\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3\u4e00\u4e2a\u5927\u578b\u6a21\u578b",
|
||||
"Train a large model on CIFAR 10 for distillation.": "\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3\u4e00\u4e2a\u5927\u578b\u6a21\u578b\u8fdb\u884c\u84b8\u998f\u3002"
|
||||
}
|
||||
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<h1><a href=\"https://nn.labml.ai/distillation/index.html\">Distilling the Knowledge in a Neural Network</a></h1>\n<p>This is a <a href=\"https://pytorch.org\">PyTorch</a> implementation/tutorial of the paper <a href=\"https://arxiv.org/abs/1503.02531\">Distilling the Knowledge in a Neural Network</a>.</p>\n<p>It's a way of training a small network using the knowledge in a trained larger network; i.e. distilling the knowledge from the large network.</p>\n<p>A large model with regularization or an ensemble of models (using dropout) generalizes better than a small model when trained directly on the data and labels. However, a small model can be trained to generalize better with help of a large model. Smaller models are better in production: faster, less compute, less memory.</p>\n<p>The output probabilities of a trained model give more information than the labels because it assigns non-zero probabilities to incorrect classes as well. These probabilities tell us that a sample has a chance of belonging to certain classes. For instance, when classifying digits, when given an image of digit <em>7</em>, a generalized model will give a high probability to 7 and a small but non-zero probability to 2, while assigning almost zero probability to other digits. Distillation uses this information to train a small model better. </p>\n": "<h1><a href=\"https://nn.labml.ai/distillation/index.html\">\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3067\u306e\u77e5\u8b58\u306e\u62bd\u51fa</a></h1>\n<p>\u3053\u308c\u306f\u3001<a href=\"https://arxiv.org/abs/1503.02531\">\u8ad6\u6587\u300c\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306b\u304a\u3051\u308b\u77e5\u8b58\u306e\u62bd\u51fa</a>\u300d<a href=\"https://pytorch.org\">\u306ePyTorch\u5b9f\u88c5/\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3067\u3059</a>\u3002</p>\n<p>\u3053\u308c\u306f\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u6e08\u307f\u306e\u5927\u898f\u6a21\u306a\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u77e5\u8b58\u3092\u4f7f\u7528\u3057\u3066\u5c0f\u898f\u6a21\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3059\u308b\u65b9\u6cd5\u3067\u3059\u3002\u3064\u307e\u308a\u3001\u5927\u898f\u6a21\u306a\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u304b\u3089\u77e5\u8b58\u3092\u62bd\u51fa\u3059\u308b\u65b9\u6cd5\u3067\u3059\u3002</p>\n<p>\u30c7\u30fc\u30bf\u3084\u30e9\u30d9\u30eb\u3067\u76f4\u63a5\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u305f\u5834\u5408\u3001\u6b63\u5247\u5316\u3092\u884c\u3063\u305f\u5927\u898f\u6a21\u306a\u30e2\u30c7\u30eb\u3084 (\u30c9\u30ed\u30c3\u30d7\u30a2\u30a6\u30c8\u3092\u4f7f\u7528\u3057\u305f) \u30e2\u30c7\u30eb\u306e\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u306f\u3001\u5c0f\u3055\u306a\u30e2\u30c7\u30eb\u3088\u308a\u3082\u4e00\u822c\u5316\u304c\u5bb9\u6613\u3067\u3059\u3002\u305f\u3060\u3057\u3001\u5c0f\u3055\u3044\u30e2\u30c7\u30eb\u3067\u3082\u3001\u5927\u304d\u306a\u30e2\u30c7\u30eb\u306e\u52a9\u3051\u3092\u501f\u308a\u3066\u3088\u308a\u4e00\u822c\u5316\u3057\u3084\u3059\u3044\u3088\u3046\u306b\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3067\u304d\u307e\u3059\u3002\u672c\u756a\u74b0\u5883\u3067\u306f\u3001\u30e2\u30c7\u30eb\u304c\u5c0f\u3055\u3044\u307b\u3069\u901f\u304f\u3001\u51e6\u7406\u80fd\u529b\u304c\u5c11\u306a\u304f\u3001\u30e1\u30e2\u30ea\u3082\u5c11\u306a\u304f\u3066\u6e08\u307f\u307e\u3059\u3002</p>\n<p>\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u6e08\u307f\u30e2\u30c7\u30eb\u306e\u51fa\u529b\u78ba\u7387\u306f\u3001\u8aa4\u3063\u305f\u30af\u30e9\u30b9\u306b\u3082\u30bc\u30ed\u4ee5\u5916\u306e\u78ba\u7387\u3092\u5272\u308a\u5f53\u3066\u308b\u305f\u3081\u3001\u30e9\u30d9\u30eb\u3088\u308a\u3082\u591a\u304f\u306e\u60c5\u5831\u3092\u63d0\u4f9b\u3057\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u78ba\u7387\u304b\u3089\u3001\u30b5\u30f3\u30d7\u30eb\u304c\u7279\u5b9a\u306e\u30af\u30e9\u30b9\u306b\u5c5e\u3057\u3066\u3044\u308b\u53ef\u80fd\u6027\u304c\u3042\u308b\u3053\u3068\u304c\u308f\u304b\u308a\u307e\u3059\u3002\u305f\u3068\u3048\u3070\u3001\u6570\u5b57\u3092\u5206\u985e\u3059\u308b\u969b\u3001<em>7 \u6841\u306e\u753b\u50cf\u304c\u4e0e\u3048\u3089\u308c\u305f\u5834\u5408\u3001\u4e00\u822c\u5316\u30e2\u30c7\u30eb\u3067\u306f 7</em> \u306b\u306f\u9ad8\u3044\u78ba\u7387\u30012 \u306b\u306f\u5c0f\u3055\u3044\u306a\u304c\u3089\u3082\u30bc\u30ed\u3067\u306f\u306a\u3044\u78ba\u7387\u304c\u4e0e\u3048\u3089\u308c\u3001\u4ed6\u306e\u6570\u5b57\u306b\u306f\u307b\u307c\u30bc\u30ed\u306e\u78ba\u7387\u3092\u5272\u308a\u5f53\u3066\u307e\u3059\u3002\u84b8\u7559\u3067\u306f\u3001\u3053\u306e\u60c5\u5831\u3092\u5229\u7528\u3057\u3066\u5c0f\u578b\u30e2\u30c7\u30eb\u306e\u5b66\u7fd2\u52b9\u679c\u3092\u9ad8\u3081\u307e\u3059</p>\u3002\n",
|
||||
"Distilling the Knowledge in a Neural Network": "\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3067\u306e\u77e5\u8b58\u306e\u62bd\u51fa"
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<h1><a href=\"https://nn.labml.ai/distillation/index.html\">Distilling the Knowledge in a Neural Network</a></h1>\n<p>This is a <a href=\"https://pytorch.org\">PyTorch</a> implementation/tutorial of the paper <a href=\"https://arxiv.org/abs/1503.02531\">Distilling the Knowledge in a Neural Network</a>.</p>\n<p>It's a way of training a small network using the knowledge in a trained larger network; i.e. distilling the knowledge from the large network.</p>\n<p>A large model with regularization or an ensemble of models (using dropout) generalizes better than a small model when trained directly on the data and labels. However, a small model can be trained to generalize better with help of a large model. Smaller models are better in production: faster, less compute, less memory.</p>\n<p>The output probabilities of a trained model give more information than the labels because it assigns non-zero probabilities to incorrect classes as well. These probabilities tell us that a sample has a chance of belonging to certain classes. For instance, when classifying digits, when given an image of digit <em>7</em>, a generalized model will give a high probability to 7 and a small but non-zero probability to 2, while assigning almost zero probability to other digits. Distillation uses this information to train a small model better. </p>\n": "<h1><a href=\"https://nn.labml.ai/distillation/index.html\">\u5728\u795e\u7ecf\u7f51\u7edc\u4e2d\u63d0\u70bc\u77e5\u8bc6</a></h1>\n<p>\u8fd9\u662f\u8bba\u6587\u300a<a href=\"https://arxiv.org/abs/1503.02531\">\u5728\u795e\u7ecf\u7f51\u7edc\u4e2d\u63d0\u70bc\u77e5\u8bc6\u300b\u7684 PyT</a> <a href=\"https://pytorch.org\">orch</a> \u5b9e\u73b0/\u6559\u7a0b\u3002</p>\n<p>\u8fd9\u662f\u4e00\u79cd\u4f7f\u7528\u7ecf\u8fc7\u8bad\u7ec3\u7684\u5927\u578b\u7f51\u7edc\u4e2d\u7684\u77e5\u8bc6\u6765\u8bad\u7ec3\u5c0f\u578b\u7f51\u7edc\u7684\u65b9\u6cd5\uff1b\u5373\u4ece\u5927\u578b\u7f51\u7edc\u4e2d\u63d0\u70bc\u77e5\u8bc6\u3002</p>\n<p>\u76f4\u63a5\u5728\u6570\u636e\u548c\u6807\u7b7e\u4e0a\u8bad\u7ec3\u65f6\uff0c\u5177\u6709\u6b63\u5219\u5316\u6216\u6a21\u578b\u96c6\u5408\uff08\u4f7f\u7528 dropout\uff09\u7684\u5927\u578b\u6a21\u578b\u6bd4\u5c0f\u578b\u6a21\u578b\u7684\u6982\u5316\u6548\u679c\u66f4\u597d\u3002\u4f46\u662f\uff0c\u5728\u5927\u578b\u6a21\u578b\u7684\u5e2e\u52a9\u4e0b\uff0c\u53ef\u4ee5\u8bad\u7ec3\u5c0f\u6a21\u578b\u4ee5\u66f4\u597d\u5730\u8fdb\u884c\u6982\u62ec\u3002\u8f83\u5c0f\u7684\u6a21\u578b\u5728\u751f\u4ea7\u4e2d\u66f4\u597d\uff1a\u901f\u5ea6\u66f4\u5feb\u3001\u8ba1\u7b97\u66f4\u5c11\u3001\u5185\u5b58\u66f4\u5c11\u3002</p>\n<p>\u7ecf\u8fc7\u8bad\u7ec3\u7684\u6a21\u578b\u7684\u8f93\u51fa\u6982\u7387\u6bd4\u6807\u7b7e\u63d0\u4f9b\u7684\u4fe1\u606f\u66f4\u591a\uff0c\u56e0\u4e3a\u5b83\u4e5f\u4f1a\u4e3a\u9519\u8bef\u7684\u7c7b\u5206\u914d\u975e\u96f6\u6982\u7387\u3002\u8fd9\u4e9b\u6982\u7387\u544a\u8bc9\u6211\u4eec\uff0c\u6837\u672c\u6709\u53ef\u80fd\u5c5e\u4e8e\u67d0\u4e9b\u7c7b\u522b\u3002\u4f8b\u5982\uff0c\u5728\u5bf9\u6570\u5b57\u8fdb\u884c\u5206\u7c7b\u65f6\uff0c\u5f53\u7ed9\u5b9a\u6570\u5b57 <em>7</em> \u7684\u56fe\u50cf\u65f6\uff0c\u5e7f\u4e49\u6a21\u578b\u4f1a\u7ed9\u51fa7\u7684\u9ad8\u6982\u7387\uff0c\u7ed92\u7684\u6982\u7387\u5f88\u5c0f\u4f46\u4e0d\u662f\u96f6\uff0c\u800c\u7ed9\u5176\u4ed6\u6570\u5b57\u5206\u914d\u51e0\u4e4e\u4e3a\u96f6\u7684\u6982\u7387\u3002\u84b8\u998f\u5229\u7528\u8fd9\u4e9b\u4fe1\u606f\u6765\u66f4\u597d\u5730\u8bad\u7ec3\u5c0f\u578b\u6a21\u578b\u3002</p>\n",
|
||||
"Distilling the Knowledge in a Neural Network": "\u5728\u795e\u7ecf\u7f51\u7edc\u4e2d\u63d0\u70bc\u77e5\u8bc6"
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"<h1>Train a small model on CIFAR 10</h1>\n<p>This trains a small model on CIFAR 10 to test how much <a href=\"index.html\">distillation</a> benefits.</p>\n": "<h1>CIFAR 10 \u3067\u5c0f\u578b\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u3088\u3046</h1>\n<p>\u3053\u308c\u306b\u3088\u308a\u3001CIFAR 10\u306e\u5c0f\u578b\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u3066\u3001<a href=\"index.html\">\u84b8\u7559\u306b\u3069\u308c\u3060\u3051\u306e\u30e1\u30ea\u30c3\u30c8\u304c\u3042\u308b\u304b\u3092\u30c6\u30b9\u30c8\u3057\u307e\u3059</a>\u3002</p>\n",
|
||||
"<h2>Configurations</h2>\n<p>We use <a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a> which defines all the dataset related configurations, optimizer, and a training loop.</p>\n": "<h2>\u30b3\u30f3\u30d5\u30a3\u30ae\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3</h2>\n<p>\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u95a2\u9023\u3059\u308b\u3059\u3079\u3066\u306e\u69cb\u6210\u3001\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30eb\u30fc\u30d7\u3092\u5b9a\u7fa9\u3059\u308b\u3082\u306e\u3092\u4f7f\u7528\u3057\u3066\u3044\u307e\u3059<a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a>\u3002</p>\n",
|
||||
"<h3>Create model</h3>\n": "<h3>\u30e2\u30c7\u30eb\u4f5c\u6210</h3>\n",
|
||||
"<h3>VGG style model for CIFAR-10 classification</h3>\n<p>This derives from the <a href=\"../experiments/cifar10.html\">generic VGG style architecture</a>.</p>\n": "<h3>CIFAR-10 \u5206\u985e\u7528\u306e VGG \u30b9\u30bf\u30a4\u30eb\u30e2\u30c7\u30eb</h3>\n<p><a href=\"../experiments/cifar10.html\">\u3053\u308c\u306f\u4e00\u822c\u7684\u306a VGG \u30b9\u30bf\u30a4\u30eb\u306e\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u306b\u7531\u6765\u3057\u307e\u3059</a>\u3002</p>\n",
|
||||
"<p> </p>\n": "<p></p>\n",
|
||||
"<p> Create a convolution layer and the activations</p>\n": "<p>\u30b3\u30f3\u30dc\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u30ec\u30a4\u30e4\u30fc\u3068\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3\u306e\u4f5c\u6210</p>\n",
|
||||
"<p>Batch normalization </p>\n": "<p>\u30d0\u30c3\u30c1\u6b63\u898f\u5316</p>\n",
|
||||
"<p>Convolution layer </p>\n": "<p>\u30b3\u30f3\u30dc\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u30ec\u30a4\u30e4\u30fc</p>\n",
|
||||
"<p>Create a model with given convolution sizes (channels) </p>\n": "<p>\u4e0e\u3048\u3089\u308c\u305f\u7573\u307f\u8fbc\u307f\u30b5\u30a4\u30ba (\u30c1\u30e3\u30cd\u30eb) \u3067\u30e2\u30c7\u30eb\u3092\u4f5c\u6210</p>\n",
|
||||
"<p>Create configurations </p>\n": "<p>\u69cb\u6210\u306e\u4f5c\u6210</p>\n",
|
||||
"<p>Create experiment </p>\n": "<p>\u5b9f\u9a13\u3092\u4f5c\u6210</p>\n",
|
||||
"<p>Load configurations </p>\n": "<p>\u69cb\u6210\u3092\u30ed\u30fc\u30c9</p>\n",
|
||||
"<p>Print number of parameters in the model </p>\n": "<p>\u30e2\u30c7\u30eb\u5185\u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u306e\u6570\u3092\u51fa\u529b\u3057\u307e\u3059</p>\n",
|
||||
"<p>ReLU activation </p>\n": "<p>ReLU \u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3</p>\n",
|
||||
"<p>Set model for saving/loading </p>\n": "<p>\u4fdd\u5b58/\u8aad\u307f\u8fbc\u307f\u7528\u306e\u30e2\u30c7\u30eb\u3092\u8a2d\u5b9a</p>\n",
|
||||
"<p>Start the experiment and run the training loop </p>\n": "<p>\u5b9f\u9a13\u3092\u958b\u59cb\u3057\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30eb\u30fc\u30d7\u3092\u5b9f\u884c\u3057\u307e\u3059</p>\n",
|
||||
"Train a small model on CIFAR 10": "CIFAR 10 \u3067\u5c0f\u578b\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u3088\u3046",
|
||||
"Train a small model on CIFAR 10 to test how much distillation benefits.": "CIFAR 10\u3067\u5c0f\u578b\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u3066\u3001\u84b8\u7559\u306b\u3069\u308c\u3060\u3051\u306e\u30e1\u30ea\u30c3\u30c8\u304c\u3042\u308b\u304b\u3092\u30c6\u30b9\u30c8\u3057\u307e\u3059\u3002"
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"<h1>Train a small model on CIFAR 10</h1>\n<p>This trains a small model on CIFAR 10 to test how much <a href=\"index.html\">distillation</a> benefits.</p>\n<p><a href=\"https://app.labml.ai/run/3b8fda8edaef11eb951eebc4a6e2bfac\"><span translate=no>_^_0_^_</span></a></p>\n": "<h1>CIFAR10 \u0dc4\u0dd2 \u0d9a\u0dd4\u0da9\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1</h1>\n<p>\u0db8\u0dd9\u0db8CIFAR \u0db8\u0dad \u0d9a\u0dd4\u0da9\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 10 \u0d9a\u0ddc\u0db4\u0db8\u0dab <a href=\"index.html\">\u0d86\u0dc3\u0dc0\u0db1\u0dba</a> \u0db4\u0dca\u0dbb\u0dad\u0dd2\u0dbd\u0dcf\u0db7 \u0db4\u0dbb\u0dd3\u0d9a\u0dca\u0dc2\u0dcf \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0da7. </p>\n<p><a href=\"https://app.labml.ai/run/3b8fda8edaef11eb951eebc4a6e2bfac\"><span translate=no>_^_0_^_</span></a></p>\n",
|
||||
"<h2>Configurations</h2>\n<p>We use <a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a> which defines all the dataset related configurations, optimizer, and a training loop.</p>\n": "<h2>\u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dca</h2>\n<p>\u0dc3\u0dd2\u0dba\u0dbd\u0dd4\u0db8\u0daf\u0dad\u0dca\u0dad \u0d9a\u0da7\u0dca\u0da7\u0dbd \u0d86\u0dc1\u0dca\u0dbb\u0dd2\u0dad \u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0dba\u0db1\u0dca, \u0db4\u0dca\u0dbb\u0dc1\u0dc3\u0dca\u0dad\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0dc4 \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0dbd\u0dd6\u0db4\u0dba\u0d9a\u0dca \u0db1\u0dd2\u0dbb\u0dca\u0dc0\u0da0\u0db1\u0dba \u0d9a\u0dbb\u0db1 \u0d85\u0db4\u0dd2 \u0db7\u0dcf\u0dc0\u0dd2\u0dad\u0dcf <a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a> \u0d9a\u0dbb\u0db8\u0dd4. </p>\n",
|
||||
"<h3>Create model</h3>\n": "<h3>\u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1</h3>\n",
|
||||
"<h3>VGG style model for CIFAR-10 classification</h3>\n<p>This derives from the <a href=\"../experiments/cifar10.html\">generic VGG style architecture</a>.</p>\n": "<h3>CIFA-10\u0dc0\u0dbb\u0dca\u0d9c\u0dd3\u0d9a\u0dbb\u0dab\u0dba \u0dc3\u0db3\u0dc4\u0dcf VGG \u0dc0\u0dd2\u0dbd\u0dcf\u0dc3\u0dd2\u0dad\u0dcf\u0dc0\u0dda \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba</h3>\n<p>\u0db8\u0dd9\u0dba <a href=\"../experiments/cifar10.html\">\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba VGG \u0dc0\u0dd2\u0dbd\u0dcf\u0dc3\u0dd2\u0dad\u0dcf\u0dc0\u0dda \u0d9c\u0dd8\u0dc4 \u0db1\u0dd2\u0dbb\u0dca\u0db8\u0dcf\u0dab \u0dc1\u0dd2\u0dbd\u0dca\u0db4\u0dba\u0dd9\u0db1\u0dca</a>\u0dbd\u0db6\u0dcf \u0d9c\u0db1\u0dd3. </p>\n",
|
||||
"<p> </p>\n": "<p> </p>\n",
|
||||
"<p> Create a convolution layer and the activations</p>\n": "<p> \u0dc3\u0d82\u0dc0\u0dc4\u0db1\u0dc3\u0dca\u0dad\u0dbb\u0dba\u0d9a\u0dca \u0dc3\u0dc4 \u0dc3\u0d9a\u0dca\u0dbb\u0dd2\u0dba \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0dca \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1</p>\n",
|
||||
"<p>Batch normalization </p>\n": "<p>\u0d9a\u0dab\u0dca\u0da9\u0dcf\u0dba\u0db8\u0dca\u0dc3\u0dcf\u0db8\u0dcf\u0db1\u0dca\u0dba\u0d9a\u0dbb\u0dab\u0dba </p>\n",
|
||||
"<p>Convolution layer </p>\n": "<p>\u0dc3\u0d82\u0dc0\u0dc4\u0db1\u0dc3\u0dca\u0dae\u0dbb\u0dba </p>\n",
|
||||
"<p>Create a model with given convolution sizes (channels) </p>\n": "<p>\u0dbd\u0db6\u0dcf\u0daf\u0dd3 \u0d87\u0dad\u0dd2 \u0dc3\u0d82\u0dc0\u0dc4\u0db1 \u0db4\u0dca\u0dbb\u0db8\u0dcf\u0dab (\u0db1\u0dcf\u0dbd\u0dd2\u0d9a\u0dcf) \u0dc3\u0dc4\u0dd2\u0dad \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \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 experiment </p>\n": "<p>\u0d85\u0dad\u0dca\u0dc4\u0daf\u0dcf\u0db6\u0dd0\u0dbd\u0dd3\u0db8 \u0dc3\u0dcf\u0daf\u0db1\u0dca\u0db1 </p>\n",
|
||||
"<p>Load configurations </p>\n": "<p>\u0dc0\u0dd2\u0db1\u0dca\u0dba\u0dcf\u0dc3\u0dba\u0db1\u0dca\u0db4\u0dd6\u0dbb\u0dab\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
|
||||
"<p>Print number of parameters in the model </p>\n": "<p>\u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0dda\u0db4\u0dbb\u0dcf\u0db8\u0dd2\u0dad\u0dd2 \u0d9c\u0dab\u0db1 \u0db8\u0dd4\u0daf\u0dca\u0dbb\u0dab\u0dba \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
|
||||
"<p>ReLU activation </p>\n": "<p>Relu\u0dc3\u0d9a\u0dca\u0dbb\u0dd2\u0dba </p>\n",
|
||||
"<p>Set model for saving/loading </p>\n": "<p>\u0d89\u0dad\u0dd2\u0dbb\u0dd2\u0d9a\u0dd2\u0dbb\u0dd3\u0db8/\u0db4\u0dd0\u0da7\u0dc0\u0dd3\u0db8 \u0dc3\u0db3\u0dc4\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba \u0dc3\u0d9a\u0dc3\u0db1\u0dca\u0db1 </p>\n",
|
||||
"<p>Start the experiment and run the training loop </p>\n": "<p>\u0d85\u0dad\u0dca\u0dc4\u0daf\u0dcf\u0db6\u0dd0\u0dbd\u0dd3\u0db8 \u0d86\u0dbb\u0db8\u0dca\u0db7 \u0d9a\u0dbb \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0dbd\u0dd6\u0db4\u0dba \u0d9a\u0dca\u0dbb\u0dd2\u0dba\u0dcf\u0dad\u0dca\u0db8\u0d9a \u0d9a\u0dbb\u0db1\u0dca\u0db1 </p>\n",
|
||||
"Train a small model on CIFAR 10": "CIFAR 10 \u0dc4\u0dd2 \u0d9a\u0dd4\u0da9\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1",
|
||||
"Train a small model on CIFAR 10 to test how much distillation benefits.": "CIFAR 10 \u0dc4\u0dd2 \u0d9a\u0dd4\u0da9\u0dcf \u0d86\u0d9a\u0dd8\u0dad\u0dd2\u0dba\u0d9a\u0dca \u0db4\u0dd4\u0dc4\u0dd4\u0dab\u0dd4 \u0d9a\u0dbb\u0db1\u0dca\u0db1 \u0d86\u0dc3\u0dc0\u0db1\u0dba \u0db4\u0dca\u0dbb\u0dad\u0dd2\u0dbd\u0dcf\u0db7 \u0d9a\u0ddc\u0db4\u0db8\u0dab \u0daf\u0dd0\u0dba\u0dd2 \u0db4\u0dbb\u0dd3\u0d9a\u0dca\u0dc2\u0dcf \u0d9a\u0dd2\u0dbb\u0dd3\u0db8\u0da7."
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"<h1>Train a small model on CIFAR 10</h1>\n<p>This trains a small model on CIFAR 10 to test how much <a href=\"index.html\">distillation</a> benefits.</p>\n": "<h1>\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3\u4e00\u4e2a\u5c0f\u578b\u6a21\u578b</h1>\n<p>\u8fd9\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3\u4e86\u4e00\u4e2a\u5c0f\u578b\u6a21\u578b\uff0c\u4ee5\u6d4b\u8bd5<a href=\"index.html\">\u84b8\u998f</a>\u7684\u76ca\u5904\u6709\u591a\u5927\u3002</p>\n",
|
||||
"<h2>Configurations</h2>\n<p>We use <a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a> which defines all the dataset related configurations, optimizer, and a training loop.</p>\n": "<h2>\u914d\u7f6e</h2>\n<p>\u6211\u4eec\u4f7f\u7528<a href=\"../experiments/cifar10.html\"><span translate=no>_^_0_^_</span></a>\u5b83\u6765\u5b9a\u4e49\u6240\u6709\u4e0e\u6570\u636e\u96c6\u76f8\u5173\u7684\u914d\u7f6e\u3001\u4f18\u5316\u5668\u548c\u8bad\u7ec3\u5faa\u73af\u3002</p>\n",
|
||||
"<h3>Create model</h3>\n": "<h3>\u521b\u5efa\u6a21\u578b</h3>\n",
|
||||
"<h3>VGG style model for CIFAR-10 classification</h3>\n<p>This derives from the <a href=\"../experiments/cifar10.html\">generic VGG style architecture</a>.</p>\n": "<h3>\u9002\u7528\u4e8e CIFAR-10 \u5206\u7c7b\u7684 VGG \u6837\u5f0f\u6a21\u578b</h3>\n<p>\u8fd9\u6e90\u4e8e<a href=\"../experiments/cifar10.html\">\u901a\u7528\u7684 VGG \u98ce\u683c\u67b6\u6784</a>\u3002</p>\n",
|
||||
"<p> </p>\n": "<p></p>\n",
|
||||
"<p> Create a convolution layer and the activations</p>\n": "<p>\u521b\u5efa\u5377\u79ef\u5c42\u548c\u6fc0\u6d3b</p>\n",
|
||||
"<p>Batch normalization </p>\n": "<p>\u6279\u91cf\u6807\u51c6\u5316</p>\n",
|
||||
"<p>Convolution layer </p>\n": "<p>\u5377\u79ef\u5c42</p>\n",
|
||||
"<p>Create a model with given convolution sizes (channels) </p>\n": "<p>\u4f7f\u7528\u7ed9\u5b9a\u7684\u5377\u79ef\u5927\u5c0f\uff08\u901a\u9053\uff09\u521b\u5efa\u6a21\u578b</p>\n",
|
||||
"<p>Create configurations </p>\n": "<p>\u521b\u5efa\u914d\u7f6e</p>\n",
|
||||
"<p>Create experiment </p>\n": "<p>\u521b\u5efa\u5b9e\u9a8c</p>\n",
|
||||
"<p>Load configurations </p>\n": "<p>\u88c5\u8f7d\u914d\u7f6e</p>\n",
|
||||
"<p>Print number of parameters in the model </p>\n": "<p>\u6253\u5370\u6a21\u578b\u4e2d\u53c2\u6570\u7684\u6570\u91cf</p>\n",
|
||||
"<p>ReLU activation </p>\n": "<p>\u6fc0\u6d3b ReLU</p>\n",
|
||||
"<p>Set model for saving/loading </p>\n": "<p>\u8bbe\u7f6e\u4fdd\u5b58/\u52a0\u8f7d\u7684\u6a21\u578b</p>\n",
|
||||
"<p>Start the experiment and run the training loop </p>\n": "<p>\u5f00\u59cb\u5b9e\u9a8c\u5e76\u8fd0\u884c\u8bad\u7ec3\u5faa\u73af</p>\n",
|
||||
"Train a small model on CIFAR 10": "\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3\u4e00\u4e2a\u5c0f\u578b\u6a21\u578b",
|
||||
"Train a small model on CIFAR 10 to test how much distillation benefits.": "\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3\u4e00\u4e2a\u5c0f\u6a21\u578b\uff0c\u4ee5\u6d4b\u8bd5\u84b8\u998f\u7684\u76ca\u5904\u3002"
|
||||
}
|
||||
Reference in New Issue
Block a user