diff --git a/.idea/workspace.xml b/.idea/workspace.xml index 8cbcf5c..cad7e00 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -1,12 +1,7 @@ - - - - - - + diff --git a/README.md b/README.md index 2cc2d67..8159a7e 100644 --- a/README.md +++ b/README.md @@ -52,20 +52,26 @@ The result on BSD100, Set14, Set5 will be reported later. The code is highly ins ### Denpendency +* python2.7 * tensorflow (tested on r1.0, r1.2) -* TF slim library * Download and extract the pre-trained model from my [google drive](https://drive.google.com/a/gapp.nthu.edu.tw/uc?id=0BxRIhBA0x8lHNDJFVjJEQnZtcmc&export=download) +* Download the VGG19 weights from the [TF-slim models](http://download.tensorflow.org/models/vgg_19_2016_08_28.tar.gz) +* The code is tested on: + * Ubuntu 14.04 LTS with CPU architecture x86_64 + Nvidia Titan X + * Ubuntu 16.04 LTS with CPU architecture x86_64 + Nvidia 1080, 1080Ti or Titan X + ### Recommended * Ubuntu 16.04 with tensorflow GPU edition ### Getting Started +Throughout the project, we denote the directory you cloned the repo as ```SRGAN-tensorflow_ROOT```
* #### Run test using pre-trained model ```bash # clone the repository from github git clone https://github.com/brade31919/SRGAN-tensorflow.git -cd SRGAN-tensorflow/ +cd $SRGAN-tensorflow_ROOT/ # Download the pre-trained model from the google-drive # Go to https://drive.google.com/a/gapp.nthu.edu.tw/uc?id=0BxRIhBA0x8lHNDJFVjJEQnZtcmc&export=download @@ -75,7 +81,7 @@ tar xvf SRGAN_pre-trained.tar # Run the test mode sh test_SRGAN.sh -#The result can be viewed at SRGAN-tensorflow/result/images/ +#The result can be viewed at $SRGAN-tensorflow_ROOT/result/images/ ```
@@ -83,7 +89,7 @@ sh test_SRGAN.sh #### Data and checkpoint preparation To run the training process, things will become a little complicated. Follow the steps below carefully!!
-Go to the project root directory. Download the vgg weight from [TF-silm model](https://github.com/tensorflow/models/tree/master/slim)
+Go to the project root directory. Download the vgg weight from [TF-silm model](http://download.tensorflow.org/models/vgg_19_2016_08_28.tar.gz)
```bash # make the directory to put the vgg19 pre-trained model @@ -136,7 +142,11 @@ CUDA_VISIBLE_DEVICES=0 python main.py \ #Set CUDA devices correctly if you use After ensuring the configuration. execute the script: ```bash # Executing the script +cd $SRGAN-tensorflow_ROOT/ sh train_SRResnet.sh +``` +Launch tensorboard to monitor the training process +```bash # Launch the tensorboard cd ./experiment_SRResnet/log/ tensorboard --logdir . @@ -193,7 +203,11 @@ CUDA_VISIBLE_DEVICES=0 python main.py \ After ensuring the configuration. execute the script: ```bash # Executing the script +cd $SRGAN-tensorflow_ROOT/ sh train_SRGAN.sh +``` +Launch the tensorboard to monitor the training process +```bash # Launch the tensorboard cd ./experiment_SRGAN_MSE/log/ tensorboard --logdir . @@ -258,7 +272,11 @@ CUDA_VISIBLE_DEVICES=0 python main.py \ #Set the place to put the c After ensuring the configuration. execute the script: ```bash # Executing the script +cd $SRGAN-tensorflow_ROOT/ sh train_SRGAN.sh +``` +Launch tensorboard to monitor the training process +```bash # Launch the tensorboard cd ./experiment_SRGAN_VGG54/log/ tensorboard --logdir . @@ -290,7 +308,7 @@ The training process in the tensorboard should be like this ### More result on benchmark -####Coming soon!!! +#### Coming soon!!! ### Reference * [C. Ledig, L. Theis, F. Huszar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, W. Shi, Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network, accepted at CVPR (oral), 2017.](https://arxiv.org/pdf/1609.04802.pdf) diff --git a/data/test_HR/54096081_p0.png b/data/test_HR/54096081_p0.png new file mode 100644 index 0000000..f5a3d34 Binary files /dev/null and b/data/test_HR/54096081_p0.png differ diff --git a/data/test_LR/54096081_p0.png b/data/test_LR/54096081_p0.png new file mode 100644 index 0000000..cf6001c Binary files /dev/null and b/data/test_LR/54096081_p0.png differ