Hello, I tried uploading my segmentation mask to test the code but I get the following error: IndexError: index 26 is out of bounds for axis 2 with size 19 When I change the number of channels I get this error: RuntimeError: Given groups=1, weight of size [64, 19, 3, 3], expected input[1, 200, 256,...

If I want to use your model to do a image-to-sketch task, should I pretrain the StyleGAN with my sketch datasets, then train your encoder with real facial image?

In a ResNet, the coarser blocks come first: pixel2style2pixel/models/encoders/helpers.py Lines 32 to 35 in 3611171 get_block(in_channel=64, depth=64, num_units=3), g...

Hi there, Thanks for your great work! I am very interested in your method and want to do some follow up work. Some competitors in your paper do not provide the corresponding pre-trained models, for example pix2pixHD in sketch2image task, and pix2pixHD, SPADE, CC FPSE for label2image task. I wonder i...

Hi, I trained the pSp encoder on a set of 6k real->cartoon image pairs. I trained for 70k iterations after which the test/loss function converged and stopped improving. The results after 70k iterations are still too far away from a good outcome. Below is a screenshot of Tensorboard as well as exa...

What are the visual studio and CUDA versions required for successful ninja compilation? I have visual studio 2019 and CUDA 11.2! Ninja compilation throws an error saying "C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\bin\Hostx86\x86/link.exe" fused_bias_act...

Hello, my goal is to convert an image of any face into its cartoon version. I have a set of ~6k image pairs (real face and its cartoon version) for training. To be able to convert a never seen face into its cartoon version I need to do the following: Use the ~6k image pairs to train a PSP encoder u...

I want to ask a little bit about style mixing. If I input 5 pictures of a person's face at 5 different angles If I use your style mixing it produces 5 ouputs will it be continuous? I mean those 5 faces refer to the same style, even though it's 5 different angles of the same face. Ex: input 5 differe...

Hello. Thank you for providing a good source code. I am a university student who is doing research in Korea. Currently, I want to create a polyp in the mask part by synthesizing a mask in the image with pixel2style2pixel. Below are the training result and the inference result. training result inf...

I tried large batch-size (i.e., 16 and 64) with linearly increasing learning rate lr=1e-4*(bs/8). However, it can not accelerate the convergence, both happening in pSp and e4e. Have you ever tested performance in large batchsize or can you give me some suggestions?