Dear sir,When I run the script:bash ./scripts/train_edges2shoes.sh,the following RuntimeError occurs. (epoch: 1, iters: 49400, time: 0.311) , z_encoded_mag: 0.577, G_total: 4.293, G_L1_encoded: 2.367, z_L1: 0.259, KL: 0.076, G_GAN: 1.002, D_GAN: 0.498, G_GAN2: 0.589, D_GAN2: 0.988 (epoch: 1, iters: 49600, time: 0.322) , z_encoded_mag: 0.409, G_total: 2.001, G_L1_encoded: 0.385, z_L1: 0.302, KL: 0.069, G_GAN: 0.794, D_GAN: 0.960, G_GAN2: 0.450, D_GAN2: 1.137 (epoch: 1, iters: 49800, time: 0.311) , z_encoded_mag: 0.939, G_total: 3.441, G_L1_encoded: 1.597, z_L1: 0.373, KL: 0.079, G_GAN: 0.833, D_GAN: 0.774, G_GAN2: 0.560, D_GAN2: 1.015 skip this point data_size = 1 Traceback (most recent call last): File "./train.py", line 28, in model.update_G() File "/home/rharad/junyanz/BicycleGAN/models/bicycle_gan_model.py", line 148, in update_G self.backward_EG() File "/home/rharad/junyanz/BicycleGAN/models/bicycle_gan_model.py", line 114, in backward_EG self.loss_G.backward(retain_graph=True) File "/home/rharad/anaconda3/lib/python3.6/site-packages/torch/autograd/variable.py", line 167, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph, retain_variables) File "/home/rharad/anaconda3/lib/python3.6/site-packages/torch/autograd/init.py", line 99, in backward variables, grad_variables, retain_graph) RuntimeError: Trying to backward through the graph a second time, but the buffers have already been freed. Specify retain_graph=True when calling backward the first time.

How can I solve this problem.....

Hello! During my using time，i found a confused bug，that is
RuntimeError: output with shape [1, 256, 256] doesn't match the broadcast shape [3, 256, 256] I don`t known why this error appearance, and can you help me to fix it？ whatever，i should thank you for you great project！

Your work gets surprising results and I expect to reproduce the data of LPIPS distance that you list in Figure6. Given one input image, you sample 19 outputs. For every input(maps), do you calculate the LPIPS distance between the given image(maps) and corresponding 19 samples(satellite) ? After that, you sum those 19 groups of data and have a average? Is it the same to other 99 input images in your experiment ? I'm confused about this and looking forward to your reply, thank you!

Hi Junyan,

Thanks for your impressive work. Recently, I apply BicycleGAN-like framework into my GAN model, hoping it learn to generate diverse results. However, my model seems not sensitve to the latent code at all. The outputs look almost same with differnt latent code, both over training and validation stages, even I enlarge the weights of KL-loss and l1-loss on latent code. My KL_loss is becoming very small during training, but the l1-loss can only be converaged to around 0.7. Do you remember what are converaged values of these losses during your training? And kindly do you have any idea or advice of it? Thanks you so much！

Looking forward to your reply.

Best, Lai

Hi, I am getting the following error when running the code. I am using python3.6 and have installed the latest pytorch version(1.0).

Could you suggest the issue involved ?

When ran the code on a single GPU, I got an error:

...
RuntimeError: start (0) + length (0) exceeds dimension size (0). (narrow at /opt/conda/conda-bld/pytorch_1533672544752/work/aten/src/ATen/native/TensorShape.cpp:157)
frame #0: at::Type::narrow(at::Tensor const&, long, long, long) const + 0x80 (0x7f5e4df3de80 in /data/yahui/anaconda2/envs/pytorch-CycleGAN-and-pix2pix/lib/python3.5/site-packages/torch/lib/libcaffe2.so)
...

I have checked the installation and configuration, both of them are correct. So, do you have any ideas for the problem?

Hi, thanks for your amazing work. I have a problem with the multi-gpu support. The original batchsize is 2 for a real image and another random. In fact it's one pair. If we want to use multi-gpu for faster training, the batch size should be larger. But simply changing the batchsize causes error. May I know is it easy to modify the code for this purpose?

Hey Jun-Yan, thanks for putting this repo together. I'm trying to train it on piano roll data and have been seeing unexpected behavior: the generator outputs the same image even though the conditions, i.e. noise vector and real A, change.

Any thoughts on what it could be? I've added the loss log, options, output images during training and output images during inference.

loss_log.txt opt.txt

Model outputs during training(fake_b_encoded, fake_b_random, real_a_encoded,real_b_encoded)

model.set_input(data)
encode = False
z_samples = model.get_z_random(1, opt.nz)
real_A, fake_B, real_B = model.test(z_samples, encode=encode)

Model outputs during inference(real_a, real_b, fake_b)

Hi, thanks for your amazing work. I train the network with my own database, it works well. However, I don't have so many data for training(just about 700 images). My question is

1. How many data should I put in the val folder? Or, the val folder is just for testing the network?
2. Besides the paired data, I also have some unpaired data, for example, (Many B but lack of A, training direction: A2B), let me know if you are consider an algorithm for such semi-supervised situation.

Thanks.

Hi, Thanks for sharing this amazing work! I have tried to apply BicycleGAN into MRI image translation tasks, and it works well! Now, I am trying to change the network as a multiple inputs network. My idea is by given multiple corresponding inputs, the output will be more realistic and accurate. Do you think this is possible to achieve based on bicycleGAN?

when I run command that bash ./scripts/train_edges2shoes.sh I got following error RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1518243271935/work/torch/lib/THC/generic/THCStorage.cu:58 how to solve this problem?

Hi @junyanz, While testing the model I would like to have some control over the diversity of the generated images. Is there anyway to interpolate the latent vector to regulate the outputs? Something similar to StyleGAN?

When I define the option "--netD" or "-netD2" as 'basic_128' or 'basic_256', the function "define_D" should use the parameter "nl_layer", but it report an error.

The condition judge part of function "define_D" is like this:

if netD == 'basic_128':
        net = D_NLayers(input_nc, ndf, n_layers=2, norm_layer=norm_layer, nl_layer=nl_layer)
    elif netD == 'basic_256':
        net = D_NLayers(input_nc, ndf, n_layers=3, norm_layer=norm_layer, nl_layer=nl_layer)
    elif netD == 'basic_128_multi':
        net = D_NLayersMulti(input_nc=input_nc, ndf=ndf, n_layers=2, norm_layer=norm_layer, num_D=num_Ds)
    elif netD == 'basic_256_multi':
        net = D_NLayersMulti(input_nc=input_nc, ndf=ndf, n_layers=3, norm_layer=norm_layer, num_D=num_Ds)
    else:
        raise NotImplementedError('Discriminator model name [%s] is not recognized' % net)
    return init_net(net, init_type, init_gain, gpu_ids)

Hello, the training uses shoe sketches of different thicknesses (half each), and it is found that the diversity of the generated images is reduced. Do you have any suggestions to improve the diversity?

I change the load_size and crop_size to 512 in train_facades.sh, and get error. I want to train on large image size, how to do that?

Traceback (most recent call last):
  File "./train.py", line 48, in <module>
    model.optimize_parameters()   # calculate loss functions, get gradients, update network weights
  File "gxl/BicycleGAN/models/bicycle_gan_model.py", line 209, in optimize_parameters
    self.forward()
  File "gxl/BicycleGAN/models/bicycle_gan_model.py", line 106, in forward
    self.z_encoded, self.mu, self.logvar = self.encode(self.real_B_encoded)
  File "gxl/BicycleGAN/models/bicycle_gan_model.py", line 82, in encode
    mu, logvar = self.netE.forward(input_image)
  File "miniconda3/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 159, in forward
    return self.module(*inputs[0], **kwargs[0])
  File "miniconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "gxl/BicycleGAN/models/networks.py", line 647, in forward
    output = self.fc(conv_flat)
  File "miniconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "miniconda3/lib/python3.7/site-packages/torch/nn/modules/container.py", line 117, in forward
    input = module(input)
  File "miniconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "miniconda3/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 93, in forward
    return F.linear(input, self.weight, self.bias)
  File "miniconda3/lib/python3.7/site-packages/torch/nn/functional.py", line 1690, in linear
    ret = torch.addmm(bias, input, weight.t())
RuntimeError: mat1 dim 1 must match mat2 dim 0

Hi Juyanz,

How are you !hope all is fine .

I want to train this algo on different images ,I was thinking how to train them on self images , 1)What pre-processing steps do i need to take here .Can you please guide me .? 2)The model is not saving to any directory ,Can you please let know where the trained model saves(for our own images) ?

I get similar-ish results when using the same discriminator for both cVAE-GAN and cLR-GAN. Is this a happy coincidence and a strike of luck? Is there some theoretical backing for having 2 discriminators?