Skip to content
Projekte

w86763777/pytorch-ddpm has 645 GitHub stars and 76 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-20 05:57 UTC. Last push 2024-06-11.

So werden diese Zahlen gemessen

Gemessener Sternzuwachs

in 24h
0
in 7 days
Verlauf wird gesammelt
in 15 days
Verlauf wird gesammelt
in 1 month
Verlauf wird gesammelt

Nettoänderungen in überlappenden Zeiträumen, keine Tagessummen. Fehlende Messwerte bleiben leer. Sterne zeigen Interesse, nicht Qualität.

Über uns

Unofficial PyTorch implementation of Denoising Diffusion Probabilistic Models

Maschinelles Lernen

README.md

Original

Denoising Diffusion Probabilistic Models

Unofficial PyTorch implementation of Denoising Diffusion Probabilistic Models [1].

This implementation follows the most of details in official TensorFlow implementation [2]. I use PyTorch coding style to port [2] to PyTorch and hope that anyone who is familiar with PyTorch can easily understand every implementation details.

TODO

  • Datasets
    • Support CIFAR10
    • Support LSUN
    • Support CelebA-HQ
  • Featurex
    • Gradient accumulation
    • Multi-GPU training
  • Reproducing Experiment
    • CIFAR10

Requirements

  • Python 3.6

  • Packages Upgrade pip for installing latest tensorboard

    pip install -U pip setuptools
    pip install -r requirements.txt
    
  • Download precalculated statistic for dataset:

    cifar10.train.npz

    Create folder stats for cifar10.train.npz.

    stats
    └── cifar10.train.npz
    

Train From Scratch

  • Take CIFAR10 for example:
    python main.py --train \
        --flagfile ./config/CIFAR10.txt
    
  • [Optional] Overwrite arguments
    python main.py --train \
        --flagfile ./config/CIFAR10.txt \
        --batch_size 64 \
        --logdir ./path/to/logdir
    
  • [Optional] Select GPU IDs
    CUDA_VISIBLE_DEVICES=1 python main.py --train \
        --flagfile ./config/CIFAR10.txt
    
  • [Optional] Multi-GPU training
    CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py --train \
        --flagfile ./config/CIFAR10.txt \
        --parallel
    

Evaluate

  • A flagfile.txt is autosaved to your log directory. The default logdir for config/CIFAR10.txt is ./logs/DDPM_CIFAR10_EPS
  • Start evaluation
    python main.py \
        --flagfile ./logs/DDPM_CIFAR10_EPS/flagfile.txt \
        --notrain \
        --eval
    
  • [Optional] Multi-GPU evaluation
    CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py \
        --flagfile ./logs/DDPM_CIFAR10_EPS/flagfile.txt \
        --notrain \
        --eval \
        --parallel
    

Reproducing Experiment

CIFAR10

  • FID: 3.249, Inception Score: 9.475(0.174)

The checkpoint can be downloaded from my drive.

Reference

[1] Denoising Diffusion Probabilistic Models

[2] Official TensorFlow implementation