{ "

Denoising Diffusion Probabilistic Models (DDPM) evaluation/sampling

\n

This is the code to generate images and create interpolations between given images.

\n": "

\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM) \u306e\u8a55\u4fa1/\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0

\n

\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

\n", "

Sampler class

\n": "

\u30b5\u30f3\u30d7\u30e9\u30fc\u30af\u30e9\u30b9

\n", "

Estimate _^_0_^_

\n

_^_1_^_

\n": "

\u898b\u7a4d\u3082\u308a _^_0_^_

\n

_^_1_^_

\n", "

Generate images

\n": "

\u753b\u50cf\u3092\u751f\u6210

\n", "

Interpolate two images _^_0_^_ and _^_1_^_ and make a video

\n\n": "

_^_0_^__^_1_^_2\u679a\u306e\u753b\u50cf\u3092\u88dc\u9593\u3057\u3066\u52d5\u753b\u3092\u4f5c\u6210

\n\n", "

Interpolate two images _^_0_^_ and _^_1_^_

\n

We get _^_2_^_ and _^_3_^_.

\n

Then interpolate to _^_4_^_

\n

Then get _^_5_^_

\n\n": "

2 \u3064\u306e\u753b\u50cf\u3092\u88dc\u9593\u3057\u3001_^_0_^_ _^_1_^_

\n

_^_2_^__^_3_^_\u3068\u53d6\u5f97\u3057\u307e\u3059.

\n

\u6b21\u306b\u3001\u6b21\u306e\u3088\u3046\u306b\u88dc\u9593\u3057\u307e\u3059 _^_4_^_

\n

\u6b21\u306b\u3001\u53d6\u5f97 _^_5_^_

\n
  • _^_12_^_\u306f _^_13_^_
    • \n", "

    Sample an image step-by-step using _^_0_^_

    \n

    We sample an image step-by-step using _^_1_^_ and at each step show the estimate _^_2_^_

    \n": "

    \u3092\u4f7f\u7528\u3057\u3066\u753b\u50cf\u3092\u6bb5\u968e\u7684\u306b\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3059\u308b _^_0_^_

    \n

    _^_1_^_\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 _^_2_^_

    \n", "

    Sample an image using _^_0_^_

    \n\n": "

    \u3092\u4f7f\u7528\u3057\u3066\u753b\u50cf\u3092\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3059\u308b _^_0_^_

    \n
  • _^_3_^_\u306f _^_4_^_
    • \n", "

    Sample from _^_0_^_

    \n_^_1_^_": "

    \u304b\u3089\u306e\u30b5\u30f3\u30d7\u30eb _^_0_^_

    \n_^_1_^_", "

    \n": "

    \n", "

    20 second video

    \n": "

    20 \u79d2\u306e\u30d3\u30c7\u30aa

    \n", "

    gather _^_0_^_

    \n": "

    \u96c6\u307e\u308b _^_0_^_

    \n", "

    _^_0_^_

    \n": "

    _^_0_^_

    \n", "

    _^_0_^_ in a tensor

    \n": "

    _^_0_^_\u30c6\u30f3\u30bd\u30eb\u3067

    \n", "

    _^_0_^_ tensor

    \n": "

    _^_0_^_\u30c6\u30f3\u30bd\u30eb

    \n", "

    Add batch dimension

    \n": "

    \u30d0\u30c3\u30c1\u30c7\u30a3\u30e1\u30f3\u30b7\u30e7\u30f3\u3092\u8ffd\u52a0

    \n", "

    Add each image

    \n": "

    \u5404\u753b\u50cf\u3092\u8ffd\u52a0

    \n", "

    Add to frames

    \n": "

    \u30d5\u30ec\u30fc\u30e0\u306b\u8ffd\u52a0

    \n", "

    Create an interpolation animation

    \n": "

    \u88dc\u9593\u30a2\u30cb\u30e1\u30fc\u30b7\u30e7\u30f3\u306e\u4f5c\u6210

    \n", "

    Create configs

    \n": "

    \u30b3\u30f3\u30d5\u30a3\u30b0\u306e\u4f5c\u6210

    \n", "

    Create sampler

    \n": "

    \u30b5\u30f3\u30d7\u30e9\u30fc\u306e\u4f5c\u6210

    \n", "

    Frames for video

    \n": "

    \u30d3\u30c7\u30aa\u7528\u30d5\u30ec\u30fc\u30e0

    \n", "

    Generate samples

    \n": "

    \u30b5\u30f3\u30d7\u30eb\u3092\u751f\u6210

    \n", "

    Get _^_0_^_ and add to frames

    \n": "

    _^_0_^_\u30d5\u30ec\u30fc\u30e0\u306e\u53d6\u5f97\u3068\u8ffd\u52a0

    \n", "

    Get frames with different _^_0_^_

    \n": "

    \u7570\u306a\u308b\u30d5\u30ec\u30fc\u30e0\u3092\u53d6\u5f97 _^_0_^_

    \n", "

    Get some images fro data

    \n": "

    \u30c7\u30fc\u30bf\u304b\u3089\u3044\u304f\u3064\u304b\u306e\u753b\u50cf\u3092\u53d6\u5f97

    \n", "

    Helper function to create a video

    \n": "

    \u52d5\u753b\u3092\u4f5c\u6210\u3059\u308b\u305f\u3081\u306e\u30d8\u30eb\u30d1\u30fc\u6a5f\u80fd

    \n", "

    Helper function to display an image

    \n": "

    \u753b\u50cf\u3092\u8868\u793a\u3059\u308b\u30d8\u30eb\u30d1\u30fc\u95a2\u6570

    \n", "

    Initialize

    \n": "

    [\u521d\u671f\u5316]

    \n", "

    Interval to log _^_0_^_

    \n": "

    \u30ed\u30b0\u306b\u8a18\u9332\u3059\u308b\u9593\u9694 _^_0_^_

    \n", "

    Iterate until _^_0_^_ steps

    \n": "

    _^_0_^_\u30b9\u30c6\u30c3\u30d7\u307e\u3067\u7e70\u308a\u8fd4\u3059

    \n", "

    Load custom configuration of the training run

    \n": "

    \u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30e9\u30f3\u306e\u30ab\u30b9\u30bf\u30e0\u69cb\u6210\u3092\u30ed\u30fc\u30c9

    \n", "

    Load training experiment

    \n": "

    \u8ca0\u8377\u8a13\u7df4\u5b9f\u9a13

    \n", "

    Make video

    \n": "

    \u52d5\u753b\u3092\u4f5c\u308b

    \n", "

    No gradients

    \n": "

    \u30b0\u30e9\u30c7\u30fc\u30b7\u30e7\u30f3\u306a\u3057

    \n", "

    Number of sampels

    \n": "

    \u30b5\u30f3\u30d7\u30eb\u6570

    \n", "

    Number of samples

    \n": "

    \u30b5\u30f3\u30d7\u30eb\u6570

    \n", "

    Return _^_0_^_

    \n": "

    \u30ea\u30bf\u30fc\u30f3 _^_0_^_

    \n", "

    Sample

    \n": "

    [\u30b5\u30f3\u30d7\u30eb]

    \n", "

    Sample _^_0_^_ steps

    \n": "

    _^_0_^_\u30b5\u30f3\u30d7\u30eb\u30b9\u30c6\u30c3\u30d7

    \n", "

    Sample an image with an denoising animation

    \n": "

    \u30ce\u30a4\u30ba\u9664\u53bb\u30a2\u30cb\u30e1\u30fc\u30b7\u30e7\u30f3\u306b\u3088\u308b\u753b\u50cf\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0

    \n", "

    Sample from _^_0_^_

    \n": "

    \u304b\u3089\u306e\u30b5\u30f3\u30d7\u30eb _^_0_^_

    \n", "

    Set PyTorch modules for saving and loading

    \n": "

    \u4fdd\u5b58\u3068\u8aad\u307f\u8fbc\u307f\u7528\u306e PyTorch \u30e2\u30b8\u30e5\u30fc\u30eb\u306e\u8a2d\u5b9a

    \n", "

    Set configurations

    \n": "

    \u69cb\u6210\u3092\u8a2d\u5b9a

    \n", "

    Show frame

    \n": "

    \u30d5\u30ec\u30fc\u30e0\u3092\u8868\u793a

    \n", "

    Show images

    \n": "

    \u753b\u50cf\u3092\u8868\u793a

    \n", "

    Show original images

    \n": "

    \u5143\u306e\u753b\u50cf\u3092\u8868\u793a

    \n", "

    Start an evaluation

    \n": "

    \u8a55\u4fa1\u3092\u958b\u59cb\u3059\u308b

    \n", "

    Start evaluation

    \n": "

    \u8a55\u4fa1\u3092\u958b\u59cb\u3059\u308b

    \n", "

    To calculate

    \n_^_0_^_

    \n": "

    \u8a08\u7b97\u3059\u308b\u306b\u306f

    \n_^_0_^_

    \n", "

    Training experiment run UUID

    \n": "

    \u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u5b9f\u9a13\u5b9f\u884c UUID

    \n", "\n": "\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" }