codes

Training

First set a config file in options/train/, then run as following:

python train.py -opt options/train/train_IRN_x4.yml

Test

First set a config file in options/test/, then run as following:

python test.py -opt options/test/test_IRN_x4.yml

Pretrained models can be downloaded from Google Drive or Baidu Drive (extraction code: lukj).

Code Framework

The code framework follows BasicSR. It mainly consists of four parts - Config, Data, Model and Network.

Let us take the train command python train.py -opt options/train/train_IRN_x4.yml for example. A sequence of actions will be done after this command.

• train.py is called.
• Reads the configuration in options/train/train_IRN_x4.yml, including the configurations for data loader, network, loss, training strategies and etc. The config file is processed by options/options.py.
• Creates the train and validation data loader. The data loader is constructed in data/__init__.py according to different data modes.
• Creates the model (is constructed in models/__init__.py according to different model types).
• Start to train the model. Other actions like logging, saving intermediate models, validation, updating learning rate and etc are also done during the training.

Contents

Config

options/ Configure the options for data loader, network structure, model, training strategies and etc.

Data

data/ A data loader to provide data for training, validation and testing.

Model

models/ Construct models for training and testing.

Network

models/modules/ Construct different network architectures.