add comments

README.md

@@ -98,7 +98,7 @@ cd CUT
 
 ### CUT and FastCUT Training and Test
 
-- Download the grumpifycat dataset (Fig 8 of the paper. Russian Blue -> Grumpy Cats)
+- Download the `grumpifycat` dataset (Fig 8 of the paper. Russian Blue -> Grumpy Cats)
 ```bash
 bash ./datasets/download_cut_dataset.sh grumpifycat
 ```
@@ -119,7 +119,7 @@ The checkpoints will be stored at `./checkpoints/grumpycat_*/web`.
 
 - Test the CUT model:
 ```bash
-python test.py --dataroot ./datasets/grumpifycat --name grumpycat_CUT --CUT_mode CUT
+python test.py --dataroot ./datasets/grumpifycat --name grumpycat_CUT --CUT_mode CUT --phase train
 
 ```
 
@@ -177,4 +177,4 @@ If you use this code for your research, please cite our [paper](https://arxiv.or
 
 
 ### Acknowledgments
-We thank Allan Jabri and Phillip Isola for helpful discussion and feedback. Our code is developed based on [pytorch-CycleGAN-and-pix2pix](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix). We also thank [pytorch-fid](https://github.com/mseitzer/pytorch-fid) for FID computation and [drn](https://github.com/fyu/drn) for mIoU computation, and [stylegan2-pytorch](https://github.com/rosinality/stylegan2-pytorch/) for the PyTorch implementation of StyleGAN2 used in single-image translation.
+We thank Allan Jabri and Phillip Isola for helpful discussion and feedback. Our code is developed based on [pytorch-CycleGAN-and-pix2pix](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix). We also thank [pytorch-fid](https://github.com/mseitzer/pytorch-fid) for FID computation,  [drn](https://github.com/fyu/drn) for mIoU computation, and [stylegan2-pytorch](https://github.com/rosinality/stylegan2-pytorch/) for the PyTorch implementation of StyleGAN2 used in our single-image translation setting.

models/cut_model.py

@@ -2,12 +2,16 @@
 import torch
 from .base_model import BaseModel
 from . import networks
-from .nce import PatchNCELoss
+from .patchnce import PatchNCELoss
 import util.util as util
 
 
 class CUTModel(BaseModel):
-    """ This class implements CUT and FastCUT model
+    """ This class implements CUT and FastCUT model, described in the paper
+    Contrastive Learning for Unpaired Image-to-Image Translation
+    Taesung Park, Alexei A. Efros, Richard Zhang, Jun-Yan Zhu
+    ECCV, 2020
+
     The code borrows heavily from the PyTorch implementation of CycleGAN
     https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
     """

models/networks.py

@@ -7,8 +7,6 @@
 import numpy as np
 from .stylegan_networks import StyleGAN2Discriminator, StyleGAN2Generator, TileStyleGAN2Discriminator
 
-# from IPython import embed
-
 ###############################################################################
 # Helper Functions
 ###############################################################################

models/stylegan_networks.py

@@ -1,3 +1,10 @@
+"""
+The network architectures is based on PyTorch implemenation of StyleGAN2Encoder.
+Original PyTorch repo: https://github.com/rosinality/style-based-gan-pytorch
+Origianl StyelGAN2 paper: https://github.com/NVlabs/stylegan2
+We　use the network architeture for our single-image traning setting.
+"""
+
 import math
 import numpy as np
 import random