energy_based_generative_models

KO | EN

gitlite — search

#javascript #python #go #android #machine-learning #deep-learning #docker #nodejs #windows #awesome #cli #kubernetes #awesome-list #security

energy_based_generative_models

(★ 154)

PyTorch code accompanying our paper on Maximum Entropy Generators for Energy-Based Models

파일 탐색기

최종 버전 다운로드 (.zip)

- __init__.py
- celeba.py
- cifar.py
- kdd.py
- mnist.py
- mnist_anomaly.py
- toy.py
- __init__.py
- celeba.py
- cifar.py
- kdd.py
- mnist.py
- regularizers.py
- toy.py
- - eval_metrics_cifar.py
  - latent_space_mcmc.py
- - anomaly_kdd.py
  - anomaly_mnist.py
  - classifier_mnist.py
  - ebm_celeba.py
  - ebm_cifar.py
  - ebm_mnist.py
  - ebm_toy.py
  - functions.py
  - wgan-gp_cifar.py
  - wgan-gp_mnist.py
- evals.py
- inception_score.py
- sampler.py
- utils.py
.gitignore
README.md

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Maximum Entropy Generators for Energy-Based Models

All experiments have tensorboard visualizations for samples / density / train curves etc.

1. To run the toy data experiments:
```
python scripts/train/ebm_toy.py --dataset swissroll --save_path logs/swissroll
```

2. To run the discrete mode collapse experiment:
```
python scripts/train/ebm_mnist.py --save_path logs/mnist_3 --n_stack 3
```

This requires the pretrained mnist classifier:
```
python scripts/train/mnist_classifier.py
```

3. To run the CIFAR image generation experiment:
```
python scripts/train/ebm_cifar.py --save_path logs/cifar
```

To run the MCMC evalulations on CIFAR data:
```
python scripts/test/eval_metrics_cifar --load_path logs/cifar --n_samples 50000 --mcmc_iters 5 --temp .01
```

NOTE: This requires cloning the TTUR repo in the current working directory (https://github.com/bioinf-jku/TTUR).

4. To run the CelebA image generation experiments:
```
python scripts/train/ebm_celeba.py --save_path logs/celeba
```

NOTE: Results are subject to PyTorch version. I have already noticed variance in quantitative numbers with PyTorch version upgrades.

energy_based_generative_models

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

energy_based_generative_models

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README