Hi! I am making a kaggle notebook based on this but I am wondering, since I am producing a derivative work, could I get a license?

TY!

I am getting this error, not sure why
'''
data@Sidneys-iMac pokeGAN-master % python3 RGBA2RGB.py
Traceback (most recent call last):
File "RGBA2RGB.py", line 16, in
png.save(os.path.join(dst,each.split('.')[0] + '.jpg'), 'JPEG')
File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/PIL/Image.py", line 2099, in save
fp = builtins.open(filename, "w+b")
FileNotFoundError: [Errno 2] No such file or directory: './resized_black/66646859_399920300938859_3244893778049227704_n_18025660906206221.jpg'
data@Sidneys-iMac pokeGAN-master % python3 RGBA2RGB.py
Traceback (most recent call last):
File "RGBA2RGB.py", line 16, in
png.save(os.path.join(dst,each.split('.')[0] + '.jpg'), 'JPEG')
File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/PIL/Image.py", line 2099, in save
fp = builtins.open(filename, "w+b")
FileNotFoundError: [Errno 2] No such file or directory: './resized_black/66646859_399920300938859_3244893778049227704_n_18025660906206221.jpg'
'''

To see if an image looks like a pokemon, I think the shape is more important than the color.
By using RGB, I think it will affect the network's ability to identify the shape.
Maybe we can try to use grayscale instead of RGB to test if it will help?

Hi!
I run this pokeGAN by following the readme.md file.But I am confused that why the d_loss is a negative number? Could you explain it? I will really appreciate that. Thank you very much!

I made the following modifications by forking your repo

• Reorganised the folder structure
  • Folders - demo, src, data
• Re-wrote the pre-processing steps
  • Automatically creates sub-folders within data folder
• Made a demo folder with a jupyter notebook (also contains the model data and GAN images)
  • reason behind this was to see how the loss functions evolve over time.
  • there is still work to be done in this. I would like to show the test functions with some output

If my changes are acceptable to you, could you write back to my on my email?

Also, what GPU are you training on and how long did 5000 epochs take you?

I called python RGBA2RGB.py after calling python resize.py but it is showing this error. Any idea why?

Traceback (most recent call last):
  File "RGBA2RGB.py", line 16, in <module>
    png.save(os.path.join(dst,each.split('.')[0] + '.jpg'), 'JPEG')
  File "C:\Users\Gautam\Anaconda3\lib\site-packages\PIL\Image.py", line 1932, in save
    fp = builtins.open(filename, "w+b")
FileNotFoundError: [Errno 2] No such file or directory: './resized_black/0.jpg'

Is the trained model available somewhere ?
Thanks :-)

resize.py has

if not os.exists(dst):

which should be

if not os.path.exists(dst):

I tried to change the pixel size of the output image. Also changing from an 8x8 grid into one single image that maybe has a higher resolution. But always get an error when changing the variables. Any idea how to change that?

Hello,

I'm having a minor issue when trying to continue an interrupted training.

As expected, these are created under model/NewPokemon in my working directory:

On this code I just couldn't make it continue from where it is left off. It starts from 0 back again when I run PokeGAN.py even though I'm running inside the directory and the folder structure seems correct. I have tried to comment out "sess.run(tf.global_variables_initializer())" and "sess.run(tf.local_variables_initializer())" but still it doesn't continue when I run pokemonGAN.py again.

I haven't modified the code except the fact that, mine saves the model every epoch instead of every 500 - just changed the modulo i%500 to i%1.

Any help would be much appreciated.

Thanks very much!

Hey what does this error mean? Trying to use a new data set.

OpenCV Error: Assertion failed (ssize.width > 0 && ssize.height > 0) in resize, file /tmp/opencv-20180113-80339-d8g5mw/opencv-3.4.0/modules/imgproc/src/resize.cpp, line 4044
Traceback (most recent call last):
  File "resize.py", line 12, in <module>
    img = cv2.resize(img,(256,256))
cv2.error: /tmp/opencv-20180113-80339-d8g5mw/opencv-3.4.0/modules/imgproc/src/resize.cpp:4044: error: (-215) ssize.width > 0 && ssize.height > 0 in function resize