Asap I can't make my boss more pretty. )))

[chapayGhub]

I'm a newbie in deep learning and found your code very pretty to start dive ))) I found some problem to run next command: python3.5 dm_main.py --run train

You can check my changes in this place: https://github.com/chapayGhub/deep-makeover/tree/feature/test

briefly: in several places

• I changed labels= to targets= as sample _dmmodel.py

  tf.nn.sigmoid_cross_entropy_with_logits(logits=disc_fake_output, labels=tf.ones_like(disc_fake_output))  
  to      
  tf.nn.sigmoid_cross_entropy_with_logits(logits=disc_fake_output, targets=tf.ones_like(disc_fake_output))

  • I changed order of input parameters for tf.concat function as sample _dmtrain.py

    image    = tf.concat([feature, clipped], 2)
    image    = tf.concat(2, [feature, clipped])

Yooo hooo as result I can started training now!!!

python3.5 dm_main.py --run train:

Connected to pydev debugger (build 163.10154.50)
   69714 source images selected
   78610 target images selected

Generator input (feature) size is 100 x 80 x 3 = 24000
Generator has 0.59M parameters

Discriminator input (feature) size is 100 x 80 x 3 = 24000
Discriminator has 0.84M parameters

Building testing model...
Done.

Model training...
  Progress[  0%], ETA[ 119m], Batch [    0], gene[0.105], disc[1.384] real[0.716] fake[0.669]
    Saved train/batch000000_out.png
  Progress[  1%], ETA[ 117m], Batch [   10], gene[0.083], disc[1.315] real[0.670] fake[0.645]
  Progress[  2%], ETA[ 116m], Batch [   20], gene[0.100], disc[1.304] real[0.705] fake[0.599]
  ..................................................................
  Progress[ 49%], ETA[  60m], Batch [  600], gene[0.096], disc[1.101] real[0.575] fake[0.525]
    Saved train/batch000600_out.png
  Progress[ 50%], ETA[  59m], Batch [  610], gene[0.128], disc[1.274] real[0.603] fake[0.672]
  Progress[ 50%], ETA[  59m], Batch [  620], gene[0.104], disc[1.569] real[0.945] fake[0.624]
  ..................................................................
  Progress[ 95%], ETA[   5m], Batch [  660], gene[0.099], disc[1.356] real[0.754] fake[0.602]
  Progress[225%], ETA[-151m], Batch [  670], gene[0.079], disc[1.350] real[0.572] fake[0.778]
    Checkpoint saved
Finished training!

And we can run: python3 dm_main.py --run inference --infile ../test/arnold.schwarzenegger.jpg --outfile ../test/arnold.schwarzenegger.out.jpg

Don't worry Arnie isn't my boss ))). Only for testing!

And got result: arnold.schwarzenegger.jpg:

arnold.schwarzenegger.out.jpg:

So I have questions:

• Are my code changes is right?
• Is it good result? I wanted to make Arnie more pretty, but made him like Terminator from broken old TV ))
• At first I want to achieve result that you have in example_male_to_female.jpg . What should i do?

PS Thank you Your code very readable and moduled, it very help me!

[david-gpu]

Hi. I'm happy you were able to get the code up and running.

The reason you had to make some changes to the source code in order to run is because you are using an older version of Tensorflow. But that shouldn't be a problem.

There are two reasons why Arnold didn't get transformed into Cinderella. First, your training only lasted 670 batches while for the example images I trained the network for 40,000 to 50,000 batches.

After that you also need to crop and align the face such that the eyes are aligned exactly in the same way as the training samples. To see how the eyes should be aligned you can open some of the training outputs that you get in the train folder.

[chapayGhub]

Woooow Thank you

My configuration: MacOs Siera 10.11.6 scipy 0.18.1 numpy 1.12.0 Pillow 4.0.0 TensorFlow v0.12.1

Do you use TensorFlow 1.0.0-rc0?

[david-gpu]

Yes, I used Tensorflow at commit 28f5099 to be exact.