{ "

Denoising Diffusion Probabilistic Models (DDPM) evaluation/sampling

\n

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

\n": "

\u53bb\u566a\u6269\u6563\u6982\u7387\u6a21\u578b (DDPM) \u8bc4\u4f30/\u91c7\u6837

\n

\u8fd9\u662f\u751f\u6210\u56fe\u50cf\u5e76\u5728\u7ed9\u5b9a\u56fe\u50cf\u4e4b\u95f4\u521b\u5efa\u63d2\u503c\u7684\u4ee3\u7801\u3002

\n", "

Sampler class

\n": "

\u91c7\u6837\u5668\u7c7b

\n", "

Estimate _^_0_^_

\n

_^_1_^_

\n": "

\u4f30\u8ba1_^_0_^_

\n

_^_1_^_

\n", "

Generate images

\n": "

\u751f\u6210\u56fe\u50cf

\n", "

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

\n\n": "

\u63d2\u503c\u4e24\u5f20\u56fe\u50cf_^_0_^__^_1_^_\u7136\u540e\u5236\u4f5c\u89c6\u9891

\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": "

\u63d2\u503c\u4e24\u5f20\u56fe\u50cf_^_0_^_\u548c_^_1_^_

\n

\u6211\u4eec\u5f97\u5230_^_2_^_\u548c_^_3_^_\u3002

\n

\u7136\u540e\u63d2\u5165_^_4_^_

\n

\u7136\u540e\u5f97\u5230_^_5_^_

\n
  • _^_12_^_\u662f_^_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": "

    \u4f7f\u7528\u9010\u6b65\u5bf9\u56fe\u50cf\u8fdb\u884c\u91c7\u6837_^_0_^_

    \n

    \u6211\u4eec\u4f7f\u7528\u9010\u6b65\u5bf9\u56fe\u50cf\u8fdb\u884c\u91c7\u6837\uff0c_^_1_^_\u5e76\u5728\u6bcf\u4e00\u6b65\u663e\u793a\u4f30\u7b97\u503c_^_2_^_

    \n", "

    Sample an image using _^_0_^_

    \n\n": "

    \u4f7f\u7528\u5bf9\u56fe\u50cf\u8fdb\u884c\u91c7\u6837_^_0_^_

    \n
  • _^_3_^_\u662f_^_4_^_
    • \n", "

    Sample from _^_0_^_

    \n_^_1_^_": "

    \u6837\u672c\u6765\u81ea_^_0_^_

    \n_^_1_^_", "

    \n": "

    \n", "

    20 second video

    \n": "

    20 \u79d2\u89c6\u9891

    \n", "

    gather _^_0_^_

    \n": "

    \u6536\u96c6_^_0_^_

    \n", "

    _^_0_^_

    \n": "

    _^_0_^_

    \n", "

    _^_0_^_ in a tensor

    \n": "

    _^_0_^_\u5728\u5f20\u91cf\u4e2d

    \n", "

    _^_0_^_ tensor

    \n": "

    _^_0_^_\u5f20\u91cf

    \n", "

    Add batch dimension

    \n": "

    \u6dfb\u52a0\u6279\u91cf\u7ef4\u5ea6

    \n", "

    Add each image

    \n": "

    \u6dfb\u52a0\u6bcf\u5f20\u56fe\u7247

    \n", "

    Add to frames

    \n": "

    \u6dfb\u52a0\u5230\u76f8\u6846

    \n", "

    Create an interpolation animation

    \n": "

    \u521b\u5efa\u63d2\u503c\u52a8\u753b

    \n", "

    Create configs

    \n": "

    \u521b\u5efa\u914d\u7f6e

    \n", "

    Create sampler

    \n": "

    \u521b\u5efa\u91c7\u6837\u5668

    \n", "

    Frames for video

    \n": "

    \u7528\u4e8e\u89c6\u9891\u7684\u5e27

    \n", "

    Generate samples

    \n": "

    \u751f\u6210\u6837\u672c

    \n", "

    Get _^_0_^_ and add to frames

    \n": "

    \u83b7\u53d6_^_0_^_\u5e76\u6dfb\u52a0\u5230\u5e27

    \n", "

    Get frames with different _^_0_^_

    \n": "

    \u83b7\u53d6\u4e0d\u540c\u7684\u5e27_^_0_^_

    \n", "

    Get some images fro data

    \n": "

    \u4ece\u6570\u636e\u4e2d\u83b7\u53d6\u4e00\u4e9b\u56fe\u50cf

    \n", "

    Helper function to create a video

    \n": "

    \u521b\u5efa\u89c6\u9891\u7684\u52a9\u624b\u51fd\u6570

    \n", "

    Helper function to display an image

    \n": "

    \u663e\u793a\u56fe\u50cf\u7684\u8f85\u52a9\u51fd\u6570

    \n", "

    Initialize

    \n": "

    \u521d\u59cb\u5316

    \n", "

    Interval to log _^_0_^_

    \n": "

    \u8bb0\u5f55\u95f4\u9694_^_0_^_

    \n", "

    Iterate until _^_0_^_ steps

    \n": "

    \u8fed\u4ee3\u76f4\u81f3_^_0_^_\u6b65\u9aa4

    \n", "

    Load custom configuration of the training run

    \n": "

    \u52a0\u8f7d\u8bad\u7ec3\u8fd0\u884c\u7684\u81ea\u5b9a\u4e49\u914d\u7f6e

    \n", "

    Load training experiment

    \n": "

    \u8d1f\u8377\u8bad\u7ec3\u5b9e\u9a8c

    \n", "

    Make video

    \n": "

    \u5236\u4f5c\u89c6\u9891

    \n", "

    No gradients

    \n": "

    \u6ca1\u6709\u6e10\u53d8

    \n", "

    Number of sampels

    \n": "

    \u6837\u672c\u6570\u91cf

    \n", "

    Number of samples

    \n": "

    \u6837\u672c\u6570\u91cf

    \n", "

    Return _^_0_^_

    \n": "

    \u8fd4\u56de_^_0_^_

    \n", "

    Sample

    \n": "

    \u6837\u672c

    \n", "

    Sample _^_0_^_ steps

    \n": "

    _^_0_^_\u6b65\u9aa4\u793a\u4f8b

    \n", "

    Sample an image with an denoising animation

    \n": "

    \u4f7f\u7528\u964d\u566a\u52a8\u753b\u5bf9\u56fe\u50cf\u8fdb\u884c\u91c7\u6837

    \n", "

    Sample from _^_0_^_

    \n": "

    \u6837\u672c\u6765\u81ea_^_0_^_

    \n", "

    Set PyTorch modules for saving and loading

    \n": "

    \u8bbe\u7f6e\u7528\u4e8e\u4fdd\u5b58\u548c\u52a0\u8f7d\u7684 PyTorch \u6a21\u5757

    \n", "

    Set configurations

    \n": "

    \u8bbe\u7f6e\u914d\u7f6e

    \n", "

    Show frame

    \n": "

    \u663e\u793a\u6846\u67b6

    \n", "

    Show images

    \n": "

    \u663e\u793a\u56fe\u7247

    \n", "

    Show original images

    \n": "

    \u663e\u793a\u539f\u59cb\u56fe\u50cf

    \n", "

    Start an evaluation

    \n": "

    \u5f00\u59cb\u8bc4\u4f30

    \n", "

    Start evaluation

    \n": "

    \u5f00\u59cb\u8bc4\u4f30

    \n", "

    To calculate

    \n_^_0_^_

    \n": "

    \u8981\u8ba1\u7b97

    \n_^_0_^_

    \n", "

    Training experiment run UUID

    \n": "

    \u8bad\u7ec3\u5b9e\u9a8c\u8fd0\u884c UUID

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