Update README.md

Author: mingukkang

README.md

@@ -306,8 +306,38 @@ CUDA_VISIBLE_DEVICES=0,...,N python3 src/main.py -sefa -sefa_axis SEFA_AXIS -sef
 #  Training GANs
 
 StudioGAN supports the training of 30 representative GANs from DCGAN to StyleGAN3-r.
+
 We used different scripts depending on the dataset and model, and it is as follows:
 
+### CIFAR10
+```bash
+CUDA_VISIBLE_DEVICES=0 python3 src/main.py -t -hdf5 -l -std_stat -std_max STD_MAX -std_step STD_STEP -metrics is fid prdc -ref "train" -cfg CONFIG_PATH -data DATA_PATH -save SAVE_PATH -mpc --post_resizer "friendly" --eval_backbone "InceptionV3_tf"
+```
+
+### CIFAR10 using StyleGAN2/3
+```bash
+CUDA_VISIBLE_DEVICES=0 python3 src/main.py -t -hdf5 -l -metrics is fid prdc -ref "train" -cfg CONFIG_PATH -data DATA_PATH -save SAVE_PATH -mpc --post_resizer "friendly" --eval_backbone "InceptionV3_tf"
+```
+
+### Baby/Papa/Grandpa ImageNet and ImageNet
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 python3 src/main.py -t -hdf5 -l -sync_bn -std_stat -std_max STD_MAX -std_step STD_STEP -metrics is fid prdc -ref "train" -cfg CONFIG_PATH -data DATA_PATH -save SAVE_PATH -mpc --pre_resizer "lanczos" --post_resizer "friendly" --eval_backbone "InceptionV3_tf"
+```
+
+### AFHQv2
+```bash
+export MASTER_ADDR="localhost"
+export MASTER_PORT=8888
+CUDA_VISIBLE_DEVICES=0,1,2,3 python3 src/main.py -t -metrics is fid prdc -ref "train" -cfg CONFIG_PATH -data DATA_PATH -save SAVE_PATH -mpc --pre_resizer "lanczos" --post_resizer "friendly" --eval_backbone "InceptionV3_tf"
+```
+
+### FFHQ
+```bash
+export MASTER_ADDR="localhost"
+export MASTER_PORT=8888
+CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 src/main.py -t -metrics is fid prdc -ref "train" -cfg CONFIG_PATH -data DATA_PATH -save SAVE_PATH -mpc --pre_resizer "lanczos" --post_resizer "friendly" --eval_backbone "InceptionV3_tf"
+```
+
 #  Metrics
 
 StudioGAN supports Inception Score, Frechet Inception Distance, Improved Precision and Recall, Density and Coverage, Intra-Class FID, Classifier Accuracy Score. Users can get ``Intra-Class FID, Classifier Accuracy Score`` scores using ``-iFID, -GAN_train, and -GAN_test`` options, respectively. 
@@ -382,38 +412,36 @@ CUDA_VISIBLE_DEVICES=0,...,N python3 src/evaluate.py -metrics is fid prdc --post
 
 ## StudioGAN thanks the following Repos for the code sharing
 
-Exponential Moving Average: https://github.com/ajbrock/BigGAN-PyTorch
+[[MIT license]](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/sync_batchnorm/LICENSE) Synchronized BatchNorm: https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
 
-Synchronized BatchNorm: https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
+[[MIT license]](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/utils/ops.py) Self-Attention module: https://github.com/voletiv/self-attention-GAN-pytorch
 
-Self-Attention module: https://github.com/voletiv/self-attention-GAN-pytorch
+[[MIT license]](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/utils/diffaug.py) DiffAugment: https://github.com/mit-han-lab/data-efficient-gans
 
-Implementation Details: https://github.com/ajbrock/BigGAN-PyTorch
+[[MIT_license]](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/metrics/prdc.py) PyTorch Improved Precision and Recall: https://github.com/clovaai/generative-evaluation-prdc
 
-Architecture Details: https://github.com/google/compare_gan
-
-StyleGAN2: https://github.com/NVlabs/stylegan2
+[[MIT_license]](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/metrics/prdc.py) PyTorch Density and Coverage: https://github.com/clovaai/generative-evaluation-prdc
 
-DiffAugment: https://github.com/mit-han-lab/data-efficient-gans
+[[MIT license]](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/utils/resize.py) PyTorch clean-FID: https://github.com/GaParmar/clean-fid
 
-Adaptive Discriminator Augmentation: https://github.com/NVlabs/stylegan2
+[[NVIDIA source code license]](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/LICENSE-NVIDIA) StyleGAN2: https://github.com/NVlabs/stylegan2
 
-Tensorflow IS: https://github.com/openai/improved-gan
+[[NVIDIA source code license]](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/LICENSE-NVIDIA) Adaptive Discriminator Augmentation: https://github.com/NVlabs/stylegan2
 
-Tensorflow FID: https://github.com/bioinf-jku/TTUR
+[[Apache License]](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/metrics/fid.py) Pytorch FID: https://github.com/mseitzer/pytorch-fid
 
-Pytorch FID: https://github.com/mseitzer/pytorch-fid
+Implementation Details: https://github.com/ajbrock/BigGAN-PyTorch
 
-Tensorflow Precision and Recall: https://github.com/msmsajjadi/precision-recall-distributions
+Architecture Details: https://github.com/google/compare_gan
 
-PyTorch Improved Precision and Recall: https://github.com/clovaai/generative-evaluation-prdc
+Tensorflow IS: https://github.com/openai/improved-gan
 
-PyTorch Density and Coverage: https://github.com/clovaai/generative-evaluation-prdc
+Tensorflow FID: https://github.com/bioinf-jku/TTUR
 
-PyTorch clean-FID: https://github.com/GaParmar/clean-fid
+Tensorflow Precision and Recall: https://github.com/msmsajjadi/precision-recall-distributions
 
 ## License
-PyTorch-StudioGAN is an open-source library under the MIT license (MIT). However, portions of the library are avaiiable under distinct license terms: StyleGAN2, StyleGAN2-ADA, and StyleGAN3 are licensed under [NVIDIA source code license](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/LICENSE-NVIDIA), Synchronized batch normalization is licensed under [MIT license](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/sync_batchnorm/LICENSE), HDF5 generator is licensed under [MIT license](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/utils/hdf5.py), differentiable SimCLR-style augmentations is licensed under [MIT license](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/utils/simclr_aug.py), and clean-FID is licensed under [MIT license](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/utils/resize.py).
+PyTorch-StudioGAN is an open-source library under the MIT license (MIT). However, portions of the library are avaiiable under distinct license terms: StyleGAN2, StyleGAN2-ADA, and StyleGAN3 are licensed under [NVIDIA source code license](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/LICENSE-NVIDIA), and PyTorch-FID is licensed under [Apache License](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/master/src/metrics/fid.py).
 
 ## Citation
 StudioGAN is established for the following research projects. Please cite our work if you use StudioGAN.