DMDNet doesn't work with DirectML giving CUDA error

[YW5555]

Describe the bug When trying to process video with DMDNet post-processing, a CUDA error pops up due to using DirectML. I'm assuming DMDNet doesn't support DirectML yet?

To Reproduce Steps to reproduce the behavior:

1. Run faceswap with DMDNet as the post-processor.

Details What OS are you using?

• [ ] Linux
• [ ] Linux in WSL
• [X] Windows
• [ ] Mac

Are you using a GPU?

• [ ] No. CPU FTW
• [ ] NVIDIA
• [X] AMD
• [ ] Intel
• [ ] Mac

Which version of roop unleashed are you using? roop unleashed 3.3.4

Applied providers: ['DmlExecutionProvider', 'CPUExecutionProvider'], with options: {'DmlExecutionProvider': {}, 'CPUExecutionProvider': {}}
inswapper-shape: [1, 3, 128, 128]
Traceback (most recent call last):
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\gradio\queueing.py", line 388, in call_prediction
    output = await route_utils.call_process_api(
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\gradio\route_utils.py", line 219, in call_process_api
    output = await app.get_blocks().process_api(
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\gradio\blocks.py", line 1437, in process_api
    result = await self.call_function(
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\gradio\blocks.py", line 1109, in call_function    prediction = await anyio.to_thread.run_sync(
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run    result = context.run(func, *args)
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\gradio\utils.py", line 641, in wrapper
    response = f(*args, **kwargs)
  File "Z:\roop-unleashed\installer\roop-unleashed\ui\tabs\faceswap_tab.py", line 389, in on_preview_frame_changed
    current_frame = live_swap(current_frame, roop.globals.face_swap_mode, use_clip, clip_text, SELECTED_INPUT_FACE_INDEX)
  File "Z:\roop-unleashed\installer\roop-unleashed\roop\core.py", line 189, in live_swap
    process_mgr.initialize(roop.globals.INPUT_FACESETS, roop.globals.TARGET_FACES, options)
  File "Z:\roop-unleashed\installer\roop-unleashed\roop\ProcessMgr.py", line 87, in initialize
    p.Initialize(devicename)
  File "Z:\roop-unleashed\installer\roop-unleashed\roop\processors\Enhance_DMDNet.py", line 32, in Initialize
    self.model_dmdnet = self.create(devicename)
  File "Z:\roop-unleashed\installer\roop-unleashed\roop\processors\Enhance_DMDNet.py", line 197, in create
    weights = torch.load('./models/DMDNet.pth')
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\torch\serialization.py", line 809, in load
    return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\torch\serialization.py", line 1172, in _load
    result = unpickler.load()
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\torch\serialization.py", line 1142, in persistent_load
    typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\torch\serialization.py", line 1116, in load_tensor
    wrap_storage=restore_location(storage, location),
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\torch\serialization.py", line 217, in default_restore_location
    result = fn(storage, location)
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\torch\serialization.py", line 182, in _cuda_deserialize
    device = validate_cuda_device(location)
  File "Z:\roop-unleashed\installer\installer_files\env\lib\site-packages\torch\serialization.py", line 166, in validate_cuda_device
    raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

[github-actions[bot]]

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

[github-actions[bot]]

This issue was closed because it has been stalled for 5 days with no activity.

[aldemoth]

Replacing line 197 of "roop-unleashed\roop\processors\Enhance_DMDNet.py" file solves the problem.

Original line:

    weights = torch.load('./models/DMDNet.pth') 

Fixed:

    weights = torch.load('./models/DMDNet.pth', map_location=self.torchdevice) 

This is CPU only. I didn't try implementing DirectML because I have no space in my ssd currently.

[Mejituu]

Replacing line 197 of "roop-unleashed\roop\processors\Enhance_DMDNet.py" file solves the problem.

Original line:

    weights = torch.load('./models/DMDNet.pth') 

Fixed:

    weights = torch.load('./models/DMDNet.pth', map_location=self.torchdevice) 

This is CPU only. I didn't try implementing DirectML because I have no space in my ssd currently.

DML Good