This repository contains an op-for-op PyTorch reimplementation of Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks .
- Google Driver
- Baidu Driver access:
llot
Modify the contents of the file as follows.
config.py
line 35mode="train"
change tomodel="valid"
;config.py
line 83model_path=f"results/{exp_name}/g-last.pth"
change tomodel_path=f"<YOUR-WEIGHTS-PATH>.pth"
;- Run
python validate.py
.
Modify the contents of the file as follows.
config.py
line 35mode="valid"
change tomodel="train"
;- Run
python train.py
.
If you want to load weights that you've trained before, modify the contents of the file as follows.
config.py
line 35mode="valid"
change tomodel="train"
;config.py
line 52start_epoch=0
change tostart_epoch=XXX
;config.py
line 53resume=False
change toresume=True
;config.py
line 54resume_d_weight=""
change toresume_d_weight=<YOUR-RESUME-D-WIGHTS-PATH>
;config.py
line 55resume_g_weight=""
change toresume_g_weight=<YOUR-RESUME-G-WIGHTS-PATH>
;- Run
python train.py
.
If you find a bug, create a GitHub issue, or even better, submit a pull request. Similarly, if you have questions, simply post them as GitHub issues.
I look forward to seeing what the community does with these models!
Alec Radford, Luke Metz, Soumith Chintala
Abstract
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision
applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help
bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of
CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints,
and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show
convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts
to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks -
demonstrating their applicability as general image representations.
@article{adversarial,
title={Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks},
author={Alec Radford, Luke Metz, Soumith Chintala},
journal={arXiv},
year={2015}
}