From 9505a80b9794ad1d1dd153f4b50fe0dbe1f4c8e3 Mon Sep 17 00:00:00 2001
From: jiupinjia <51430557+jiupinjia@users.noreply.github.com>
Date: Sun, 19 Jul 2020 17:09:46 -0400
Subject: [PATCH] Update README.md

---
 README.md | 116 +++++++++++++++++++++++++++---------------------------
 1 file changed, 58 insertions(+), 58 deletions(-)

diff --git a/README.md b/README.md
index 2d62455..311ea18 100644
--- a/README.md
+++ b/README.md
@@ -24,16 +24,16 @@ See [Requirements.txt](requirements.txt).
 
 1. Clone this repo:
 
-   ``````shell
-   git clone https://github.com/jiupinjia/Deep-adversarial-decomposition.git 
-   cd Deep-adversarial-decomposition
-   ``````
+```bash
+git clone https://github.com/jiupinjia/Deep-adversarial-decomposition.git 
+cd Deep-adversarial-decomposition
+```
 
 2. Download our demo datasets from 1) [Google Driver](https://drive.google.com/open?id=1MIBstoZI1hJ2Rio2CP5Gq1KLJ0IVC1Rd); or 2) [BaiduYun](https://pan.baidu.com/s/17Lfh5LpXrTsxkwFdoi_Jhw) (Key: xxxx), and unzip into the repo directory.
 
-   ``````shell
-   unzip datasets.zip
-   ``````
+```bash
+unzip datasets.zip
+```
    
    Please not that in each of our demo datasets, we only uploaded a very small part of the data, which are used to show the directory configurations of the datasets. To reproduce the results reported in our paper, you can download the full versions of these datasets. All datasets used in our experiments are publicly available. Please check out our [paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Zou_Deep_Adversarial_Decomposition_A_Unified_Framework_for_Separating_Superimposed_Images_CVPR_2020_paper.pdf) for more details.
    
@@ -75,49 +75,49 @@ python train.py --dataset mnist --net_G unet_64 --checkpoint_dir checkpoints --v
 
 - To train the model:
 
-  ``````shell
-  python train.py --dataset rain100h --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
-  ``````
+```bash
+python train.py --dataset rain100h --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
+```
 
 - To test the model:
 
-  ``````shell
-  python eval_derain.py --dataset rain100h --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
-  ``````
+```bash
+python eval_derain.py --dataset rain100h --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
+```
 
 #### On [Rain800](https://arxiv.org/abs/1701.05957) 
 
 - To train the model:
 
-  ``````shell
-  python train.py --dataset rain800 --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
-  ``````
+```bash
+python train.py --dataset rain800 --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
+```
 
 - To test the model:
 
-  ``````shell
-  python eval_derain.py --dataset rain800 --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
-  ``````
+```bash
+python eval_derain.py --dataset rain800 --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
+```
 
 #### On [DID-MDN](https://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Density-Aware_Single_Image_CVPR_2018_paper.pdf) 
 
 - To train the model:
 
-  ``````shell
-  python train.py --dataset did-mdn --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
-  ``````
+```bash
+python train.py --dataset did-mdn --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
+```
 
 - To test the model on [DID-MDN](https://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Density-Aware_Single_Image_CVPR_2018_paper.pdf):
 
-  ``````shell
-  python eval_derain.py --dataset did-mdn-test1 --ckptdir checkpoints --net_G unet_512 --save_output
-  ``````
+```bash
+python eval_derain.py --dataset did-mdn-test1 --ckptdir checkpoints --net_G unet_512 --save_output
+```
 
 - To test the model on [DDN-1k](https://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Density-Aware_Single_Image_CVPR_2018_paper.pdf):
 
-  ``````shell
-  python eval_derain.py --dataset did-mdn-test2 --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
-  ``````
+```bash
+python eval_derain.py --dataset did-mdn-test2 --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
+```
 
 
 
@@ -127,15 +127,15 @@ python train.py --dataset mnist --net_G unet_64 --checkpoint_dir checkpoints --v
 
 - To train the model (together on all three subsets [defocused, focused, ghosting]):
 
-  ``````shell
-  python train.py --dataset syn3-all --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
-  ``````
+```bash
+python train.py --dataset syn3-all --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
+```
 
 - To test the model:
 
-  ``````shell
-  python eval_dereflection.py --dataset syn3-all --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
-  ``````
+```bash
+python eval_dereflection.py --dataset syn3-all --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
+```
    
    You can also train and test separately on the three subsets of [Synthesis-Reflection](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wen_Single_Image_Reflection_Removal_Beyond_Linearity_CVPR_2019_paper.pdf) by specifying `--dataset` above to `syn3-defocused`, `syn3-focused`, or `syn3-ghosting`. 
 
@@ -143,30 +143,30 @@ python train.py --dataset mnist --net_G unet_64 --checkpoint_dir checkpoints --v
 
 - To train the model:
 
-  ``````shell
-  python train.py --dataset bdn --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_256 --pixel_loss pixel_loss --metric psnr_gt1
-  ``````
+```bash
+python train.py --dataset bdn --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_256 --pixel_loss pixel_loss --metric psnr_gt1
+```
 
 - To test the model:
 
-  ``````shell
-  python eval_dereflection.py --dataset bdn --ckptdir checkpoints --net_G unet_256 --in_size 256 --save_output
-  ``````
+```bash
+python eval_dereflection.py --dataset bdn --ckptdir checkpoints --net_G unet_256 --in_size 256 --save_output
+```
 
 
 #### On [Zhang's dataset](https://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Single_Image_Reflection_CVPR_2018_paper.pdf) 
 
 - To train the model:
 
-  ``````shell
-  python train.py --dataset xzhang --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
-  ``````
+```bash
+python train.py --dataset xzhang --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric psnr_gt1
+```
 
 - To test the model:
 
-  ``````shell
-  python eval_dereflection.py --dataset xzhang --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
-  ``````
+```bash
+python eval_dereflection.py --dataset xzhang --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
+```
 
 
 
@@ -176,30 +176,30 @@ python train.py --dataset mnist --net_G unet_64 --checkpoint_dir checkpoints --v
 
 - To train the model:
 
-  ``````shell
-  python train.py --dataset istd --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_256 --pixel_loss pixel_loss --metric labrmse_gt1
-  ``````
+```bash
+python train.py --dataset istd --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_256 --pixel_loss pixel_loss --metric labrmse_gt1
+```
 
 - To test the model:
 
-  ``````shell
-  python eval_deshadow.py --dataset istd --ckptdir checkpoints --net_G unet_256 --in_size 256 --save_output
-  ``````
+```bash
+python eval_deshadow.py --dataset istd --ckptdir checkpoints --net_G unet_256 --in_size 256 --save_output
+```
 
 
 #### On [SRD](https://openaccess.thecvf.com/content_cvpr_2017/papers/Qu_DeshadowNet_A_Multi-Context_CVPR_2017_paper.pdf) 
 
 - To train the model:
 
-  ``````shell
-  python train.py --dataset srd --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric labrmse_gt1
-  ``````
+```bash
+python train.py --dataset srd --checkpoint_dir checkpoints --vis_dir val_out --max_num_epochs 200 --batch_size 2 --enable_d1d2 --enable_d3 --enable_synfake --net_G unet_512 --pixel_loss pixel_loss --metric labrmse_gt1
+```
 
 - To test the model:
 
-  ``````shell
-  python eval_deshadow.py --dataset srd --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
-  ``````
+```bash
+python eval_deshadow.py --dataset srd --ckptdir checkpoints --net_G unet_512 --in_size 512 --save_output
+```