Is there any difference in background after changing the faces with original CycleGAN? How did you fix it? Ty.

Hi, @tjwei when I execute the wgan2-AC-lasagne.ipynb in your repository, the following error appears:

KeyError Traceback (most recent call last)
in
----> 1 netG = DCGAN_G_nobn(imageSize, nz, nc, ngf, 1, n_extra_layers)
2 netG.apply(weights_init)

in init(self, isize, nz, nc, ngf, ngpu, n_extra_layers)
59 main = nn.Sequential()
60 main.add_module('initial.{0}-{1}.convt'.format(nz, cngf),
---> 61 nn.ConvTranspose2d(nz, cngf, 4, 1, 0, bias=False))
62 main.add_module('initial.{0}.relu'.format(cngf),
63 nn.ReLU(True))

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in add_module(self, name, module)
184 raise KeyError("attribute '{}' already exists".format(name))
185 elif '.' in name:
--> 186 raise KeyError("module name can't contain "."")
187 elif name == '':
188 raise KeyError("module name can't be empty string """)

KeyError: 'module name can't contain "."'

How can I solve this problom? Thanks a lot.

Hi I have tried compiling the CycleGAN-lasagne-fber.ipynb file and in the end it complains about No such file or directory. here is the full information on the error.

/home/ubuntu/GANotebooks/CycleGAN-lasagne-fber.ipynb in ()
----> 1 with np.load('model_cycle_fber.npz') as f:
2 param_values = [f['arr_%d' % i] for i in range(len(f.files))]
3 lasagne.layers.set_all_param_values([netDA, netDB, netGA, netGB], param_values)

/home/ubuntu/anaconda3/lib/python3.5/site-packages/numpy/lib/npyio.py in load(file, mmap_mode, allow_pickle, fix_imports, encoding)
368 own_fid = False
369 if isinstance(file, basestring):
--> 370 fid = open(file, "rb")
371 own_fid = True
372 elif is_pathlib_path(file):

FileNotFoundError: [Errno 2] No such file or directory: 'model_cycle_fber.npz'

Hi tjwei,
Thank for your wonderful code. could you please tell me how to save weight of that pix2pix-keras jupyter notebook after finish training? Thank you in advance.

hello . i have got problem in pix2pix-keras

i dont know what shall i download your structers dataset
could you get me direct link to this dataset.
i know this link http://cmp.felk.cvut.cz/~tylecr1/facade/ or http://vision.cs.utexas.edu/projects/finegrained/utzap50k/
but i dont know how prepare this dataset

data = "edges2shoes"
data = "facades"
direction = 0
trainAB = load_data('pix2pix/{}/train/.jpg'.format(data))
valAB = load_data('pix2pix/{}/val/.jpg'.format(data))
assert len(trainAB) and len(valAB)

Hey tjwei!

Ive implemented your cycle GAN today for an application at ours. After a couple bugs its working and it seems to be doing a great job!

I wanted to thank you for your work and also tell you that we would love to invite you to join our startup Recogni! We are looking for people with exactly your skills!

Please find and add me on linkedin gilles backhus if youre interest.

Have a good day dude!

Regards,
Gilles

I would like to know which dataset you used for the face-off application.
How would I train videos for a face off purpose.
I am working on ubuntu 16.04

wgan-gp keras中每次加载模型后，优化器好像又被初始化了，我要怎样才能保存优化器的weights？

Hi

I think the loss function in wgan2-keras should be

loss = loss_fake - loss_real + nz * λ * grad_penalty

in your In[9]

Because you called the loss_mixed = K.mean(netD(netD_mixed_input)) before, which divide nz, so you should make up here.

Am I right?

why in Discriminator, you didn't use batchnormalization？

Hi, I am new to this. Could anyone please tell me how should I get started if I want to train a new model using a source and destination video?

How do I save the model of cyclegan_keras?
Also how do i test the trained model?

Thanks!

When I run pix2pix-keras.ipynb, in the fifth block

if K._BACKEND == 'theano':

raises

AttributeError: module 'keras.backend' has no attribute '_BACKEND'

In the current Keras version (2.2.5), the proper API has changed to K.backend().
Would you please fix that, or should I draft a PR?

Besides, consider that the repo is created 2-3 years ago, there may be a lot of such API change and will be troublesome to fix them all. Would it be helpful to add a requirements.txt stating all the proper version of used packages, to avoiding such problems?

Thanks!