For some reason, when I open the web document, real_a and fake_b are matching, but the real_b is from another image; however in the images folder the images are correct. Does someone know why does this happen?

I want see the values while training, tf.log(predict_real + EPS) and tf.log(1 - predict_fake + EPS).
so, i'm add the code(#add code) in the main.

           if should(a.progress_freq):
                fetches["discrim_loss"] = model.discrim_loss
                fetches["gen_loss_GAN"] = model.gen_loss_GAN
                fetches["gen_loss_L1"] = model.gen_loss_L1

According to scipy, scipy.misc.toimage()

toimage is deprecated! toimage is deprecated in SciPy 1.0.0, and will be removed in 1.2.0. Use Pillow’s Image.fromarray directly instead.

which is used on line 46 of utils/visualizer.py is now a deprecated function under the newest scipy version. As a result this co

Traceback (most recent call last):
File "train.py", line 45, in
train_display_images_b = torch.stack([train_loader_b.dataset[i] for i in range(display_size)]).cuda()
File "train.py", line 45, in
train_display_images_b = torch.stack([train_loader_b.dataset[i] for i in range(display_size)]).cuda()
File "/content/MUNIT/data.py", line 119, in getitem
pat

I am afraid that the image links in TUTORIAL.md are 404.
Is that because of my Internet connection or they're just not found?

with video_demo.py about 20% speed compared to your 1.0 repo. but thanks much for sharing!

since most people coyping the commands:

5. For detail about arguments and config file, see docs or python P2PaLa.py -h. -> should be python P2PaLA.py -h

Preprocessing requires setting up 2 separate repositories. It's crazy. We should improve this.

Ideas

1. Add the two preprocessing repositories as submodules so they're in a central location
2. Create a single, simple script that calls both preprocessing libraries. Note these libraries have different (and possibly conflicting) dependencies, so that's a bit tricky.