Trinh Quoc Nguyen

Hi AterLuna, You have to write code for yourself to generate the flist file. Here is my code: ``` #!/usr/bin/python import argparse import os from random import shuffle parser =...

@AterLuna , Supposed you want to use my code, you need to make a new directory named `training_data`. In that directory, you make 2 more new directories: `training` and `validation`...

I have modified a little bit for anyone needs it. Moreover, you may apply "data augmentation" and put them into other folders ( folder1, folder2,...) without being messy 😄 The...

> @TrinhQuocNguyen Sorry, as a beginner, I am very sorry to disturb you, I will look at your source file again, I hope you can send me your inpaint.yml file...

Oh thank you, I have found the answer: Just set the parameter reuse = tf.AUTO_REUSE `output = model.build_server_graph(input_image, reuse=tf.AUTO_REUSE)` The tensorflow will automatically understand and reuse the graph.

Hello JiahuiYu, Thank you for your quick response. Did you mean `sess.run` ? I'm reading your source code to understand what you have done.

Hello JiahuiYu, Thank you for your response. I'm building the graph. In inpaint.yml file, at `#loss legacy` line. I have found that VGG_MOEL_FILE you have configured, I have read your...

Thank you for your fast response. I have used your pretrained model to apply transfer learning, it saved me a lot of time on a new training set. I am...

Hello Jiahuiyu, Thank you for your awesome code, I have tried to modify and build the graph, but unfortunately I could not build it. I have found that you have...

Here is my code at the moment: use a for loop ``` # prepare folder path input_folder = args.test_dir + "/input" mask_folder = args.test_dir + "/mask" output_folder = args.test_dir +...