update README and update scripts

Author: junyanz

README.md

@@ -8,9 +8,9 @@ This is our PyTorch implementation for both unpaired and paired image-to-image t
 
 The code was written by [Jun-Yan Zhu](https://github.com/junyanz) and [Taesung Park](https://github.com/taesung89), and supported by [Tongzhou Wang](https://ssnl.github.io/).
 
-This PyTorch implementation produces results comparable or better than our original Torch software. If you would like to reproduce the exact same results as in the papers, check out the original [CycleGAN Torch](https://github.com/junyanz/CycleGAN) and [pix2pix Torch](https://github.com/phillipi/pix2pix) code
+This PyTorch implementation produces results comparable to or better than our original Torch software. If you would like to reproduce the exact same results as in the papers, check out the original [CycleGAN Torch](https://github.com/junyanz/CycleGAN) and [pix2pix Torch](https://github.com/phillipi/pix2pix) code
 
-**Note**: The current software works well with PyTorch 0.1-0.3. PyTorch 0.4 support will be added by the end of May.
+**Note**: The current software works well with PyTorch 0.4. Check out the older [branch](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/tree/pytorch0.3.1) that supports PyTorch 0.1-0.3.
 
 #### CycleGAN: [[Project]](https://junyanz.github.io/CycleGAN/) [[Paper]](https://arxiv.org/pdf/1703.10593.pdf) [[Torch]](https://github.com/junyanz/CycleGAN)
 <img src="https://junyanz.github.io/CycleGAN/images/teaser_high_res.jpg" width="900"/>
@@ -71,7 +71,7 @@ CycleGAN course assignment [code](http://www.cs.toronto.edu/~rgrosse/courses/csc
 
 ## Getting Started
 ### Installation
-- Install PyTorch and dependencies from http://pytorch.org
+- Install PyTorch 0.4 and dependencies from http://pytorch.org
 - Install Torch vision from the source.
 ```bash
 git clone https://github.com/pytorch/vision

scripts/check_all.sh

@@ -0,0 +1,21 @@
+set -ex
+echo 'apply a pretrained cyclegan model'
+# bash pretrained_models/download_cyclegan_model.sh horse2zebra
+# bash ./datasets/download_cyclegan_dataset.sh horse2zebra
+# python test.py --dataroot datasets/horse2zebra/testA --checkpoints_dir ./checkpoints/ --name horse2zebra_pretrained --no_dropout --model test --dataset_mode single --loadSize 256
+
+echo 'apply a pretrained pix2pix model'
+# bash pretrained_models/download_pix2pix_model.sh facades_label2photo
+# bash ./datasets/download_pix2pix_dataset.sh facades
+# python test.py --dataroot ./datasets/facades/ --which_direction BtoA --model pix2pix --name facades_label2photo_pretrained --dataset_mode aligned --which_model_netG unet_256 --norm batch
+
+
+echo 'cyclegan train (1 epoch) and test'
+# bash ./datasets/download_cyclegan_dataset.sh maps
+# python train.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan --no_dropout --niter 1 --niter_decay 0 --max_dataset_size 100 --save_latest_freq 100
+# python test.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan --phase test --no_dropout
+
+
+echo 'pix2pix train (1 epoch) and test'
+python train.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --which_model_netG unet_256 --which_direction BtoA --lambda_A 100 --dataset_mode aligned --no_lsgan --norm batch --pool_size 0 --niter 1 --niter_decay 0 --save_latest_freq 400
+python test.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --which_model_netG unet_256 --which_direction BtoA --dataset_mode aligned --norm batch

scripts/conda_deps.sh

@@ -1,3 +1,4 @@
+set -ex
 conda install numpy pyyaml mkl mkl-include setuptools cmake cffi typing
 conda install -c pytorch magma-cuda80 # or magma-cuda90 if CUDA 9
 conda install pytorch torchvision -c pytorch  # install pytorch; if you want to use cuda90, add cuda90

scripts/install_deps.sh

@@ -1,2 +1,3 @@
+set -ex
 pip install visdom
 pip install dominate

scripts/test_cyclegan.sh

@@ -1 +1,2 @@
+set -ex
 python test.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan --phase test --no_dropout

scripts/test_pix2pix.sh

@@ -1 +1,2 @@
+set -ex
 python test.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --which_model_netG unet_256 --which_direction BtoA --dataset_mode aligned --norm batch

scripts/test_single.sh

@@ -1 +1,2 @@
+set -ex
 python test.py --dataroot ./datasets/facades/testB/ --name facades_pix2pix --model test --which_model_netG unet_256 --which_direction BtoA --dataset_mode single --norm batch

scripts/train_cyclegan.sh

@@ -1 +1,2 @@
+set -ex
 python train.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan --pool_size 50 --no_dropout

scripts/train_pix2pix.sh

@@ -1 +1,2 @@
+set -ex
 python train.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --which_model_netG unet_256 --which_direction BtoA --lambda_A 100 --dataset_mode aligned --no_lsgan --norm batch --pool_size 0