This implementation is based on Tensorflow 1.12 + tf.keras and Eager Execution
Tensorflow 1.12 ,Pillow
- Create a Anaconda3 environment with pip
- Activate the environment
- install tensorflow 1.12
- Install pillow by running the following command
username@PC:~$ conda install -c anaconda pillow
- Go to this link and download "saved_data".
- Dump it to the project directory.
- Training losses and validating errors are saved in "saved_data/runs". Please follow the following instruction to see them in tensorboard.
username@PC:~$ cd saved_dir
username@PC:~$ tensorboard --logdir="runs" --port=6006
Then, open your browser and go to the link below.
username@PC:~$ http://computer_name_or_ip_address:6006
- Qualitative examples are stored in "saved_data/qualitative".
- Checkpoints are stored in "saved_data/checkpoints"
Thanks to all available implementation of this paper.