zllrunning / face-makeup.pytorch Goto Github PK

I am getting assertion error "Torch version is not compiled for CUDA support" when try to run on macosx Mojave.

I'm trying to port this trained model to ios but always fail ( output model size is very large and dont know how to use it ) . Can you help to convert it to ios model ?

I am getting above error on running !python makeup.py --img-path imgs/116.jpg command. I have followed all the instructions and am unable to detect the cause of the error. Can someone please help me out here.

What is color code to get this hair color to black? i have tried different color codes but not able to change the hair color to black

Where can we find the documentation or an overview of the processes involved in hair masking?

Hi,

Getting the following error. Is this due to size mismatch?

Downloading: "https://download.pytorch.org/models/resnet18-5c106cde.pth" to /root/.cache/torch/hub/checkpoints/resnet18-5c106cde.pth
100% 44.7M/44.7M [00:00<00:00, 307MB/s]
Traceback (most recent call last):
File "makeup.py", line 86, in
image = hair(image, parsing, part, color)
File "makeup.py", line 54, in hair
changed[parsing != part] = image[parsing != part]
IndexError: boolean index did not match indexed array along dimension 0; dimension is 780 but corresponding boolean dimension is 799

I have issue about make up other image.

Traceback (most recent call last):
  File "makeup.py", line 173, in <module>
    image = hair(image, parsing, part, color)
  File "makeup.py", line 63, in hair
    changed[parsing != part] = image[parsing != part]
IndexError: boolean index did not match indexed array along dimension 0; dimension is 1160 but corresponding boolean dimension is 2000

How to resolve it?

I'm getting this error

changed[parsing != part] = image[parsing != part] IndexError: boolean index did not match indexed array along dimension 0; dimension is 1600 but corresponding boolean dimension is 1062

Right now the Pytorch with CUDA 10.2 is not available for the Windows OS.
When I am running this project with the CUDA 11.3 for the Windows OS, then I am getting the following ERRORs.

  File "F:\Restart_08122021\my_project\module_x\test.py", line 51, in evaluate
    net = BiSeNet(n_classes=n_classes)
  File "F:\Restart_08122021\my_project\module_x\model.py", line 235, in __init__
    self.cp = ContextPath()
  File "F:\Restart_08122021\my_project\module_x\model.py", line 97, in __init__
    self.resnet = Resnet18()
  File "F:\Restart_08122021\my_project\module_x\resnet.py", line 69, in __init__
    self.init_weight()
  File "F:\Restart_08122021\my_project\module_x\resnet.py", line 83, in init_weight
    state_dict = modelzoo.load_url(resnet18_url)
  File "C:\ProgramData\Anaconda3\envs\my_project\lib\site-packages\torch\hub.py", line 595, in load_state_dict_from_url
    return torch.load(cached_file, map_location=map_location)
  File "C:\ProgramData\Anaconda3\envs\my_project\lib\site-packages\torch\serialization.py", line 713, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "C:\ProgramData\Anaconda3\envs\my_project\lib\site-packages\torch\serialization.py", line 905, in _legacy_load
    return legacy_load(f)
  File "C:\ProgramData\Anaconda3\envs\my_project\lib\site-packages\torch\serialization.py", line 841, in legacy_load
    tensor = torch.tensor([], dtype=storage.dtype).set_(
  RuntimeError: Attempted to set the storage of a tensor on device "cuda:0" to a storage on different device "cpu".  This is no longer allowed; the devices must match.

Please help me in solving this error.

HI I have changed the line in makeup.py but color is not chaning when runnin the program the default color mode is blue and when I change the parameters it is not making any change colors = [[255, 0, 0], [20, 70, 180], [20, 70, 180]]
please any help on the issue or guidance on how to change it

Please use pictures with the same length and width to participate in the test.