DLAS - A configuration-driven trainer for generative models, with mild oneAPI support

Go to file

James Betker aa0305def9 Resnet discriminator overhaul It's been a tough day figuring out WTH is going on with my discriminators. It appears the raw FixUp discriminator can get into an "defective" state where they stop trying to learn and just predict as close to "0" D_fake and D_real as possible. In this state they provide no feedback to the generator and never recover. Adding batch norm back in seems to fix this so it must be some sort of parameterization error.. Should look into fixing this in the future.		2020-05-06 17:27:30 -06:00
.idea	Support inference across batches, support inference on cpu, checkpoint	2020-05-04 08:48:25 -06:00
codes	Resnet discriminator overhaul	2020-05-06 17:27:30 -06:00
.flake8	mmsr	2019-08-23 21:42:47 +08:00
.gitignore	mmsr	2019-08-23 21:42:47 +08:00
.style.yapf	mmsr	2019-08-23 21:42:47 +08:00
LICENSE
README.md	Update README.md	2019-11-24 07:47:57 +00:00

README.md

MMSR

MMSR is an open source image and video super-resolution toolbox based on PyTorch. It is a part of the open-mmlab project developed by Multimedia Laboratory, CUHK. MMSR is based on our previous projects: BasicSR, ESRGAN, and EDVR.

Highlights

A unified framework suitable for image and video super-resolution tasks. It is also easy to adapt to other restoration tasks, e.g., deblurring, denoising, etc.
State of the art: It includes several winning methods in competitions: such as ESRGAN (PIRM18), EDVR (NTIRE19).
Easy to extend: It is easy to try new research ideas based on the code base.

Updates

[2019-07-25] MMSR v0.1 is released.

Dependencies and Installation

Python 3 (Recommend to use Anaconda)
PyTorch >= 1.1
NVIDIA GPU + CUDA
Deformable Convolution. We use mmdetection's dcn implementation. Please first compile it.
```
cd ./codes/models/archs/dcn
python setup.py develop
```
Python packages: pip install -r requirements.txt

Dataset Preparation

We use datasets in LDMB format for faster IO speed. Please refer to DATASETS.md for more details.

Training and Testing

Please see wiki- Training and Testing for the basic usage, i.e., training and testing.

Model Zoo and Baselines

Results and pre-trained models are available in the wiki-Model Zoo.

Contributing

We appreciate all contributions. Please refer to mmdetection for contributing guideline.

Python code style
We adopt PEP8 as the preferred code style. We use flake8 as the linter and yapf as the formatter. Please upgrade to the latest yapf (>=0.27.0) and refer to the yapf configuration and flake8 configuration.

Before you create a PR, make sure that your code lints and is formatted by yapf.

License

This project is released under the Apache 2.0 license.