Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

[AlexYez]

Hi! When I try to run a file app.py or run_video.py, I'm getting this error:

Loading weights from local directory
A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
Running on local URL:  http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Traceback (most recent call last):
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\gradio\queueing.py", line 495, in call_prediction
    output = await route_utils.call_process_api(
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api
    output = await app.get_blocks().process_api(
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\gradio\blocks.py", line 1561, in process_api
    result = await self.call_function(
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\gradio\blocks.py", line 1179, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\anyio\_backends\_asyncio.py", line 2134, in run_sync_in_worker_thread
    return await future
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\gradio\utils.py", line 678, in wrapper
    response = f(*args, **kwargs)
  File "app.py", line 75, in on_submit
    depth = predict_depth(model, image)
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "app.py", line 52, in predict_depth
    return model(image)
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "D:\Apps\AiApps\xdrive\DepthGen\Depth-Anything\depth_anything\dpt.py", line 158, in forward
    features = self.pretrained.get_intermediate_layers(x, 4, return_class_token=True)
  File "D:\Apps\AiApps\xdrive\DepthGen\Depth-Anything\torchhub/facebookresearch_dinov2_main\vision_transformer.py", line 308, in get_intermediate_layers
    outputs = self._get_intermediate_layers_not_chunked(x, n)
  File "D:\Apps\AiApps\xdrive\DepthGen\Depth-Anything\torchhub/facebookresearch_dinov2_main\vision_transformer.py", line 272, in _get_intermediate_layers_not_chunked
    x = self.prepare_tokens_with_masks(x)
  File "D:\Apps\AiApps\xdrive\DepthGen\Depth-Anything\torchhub/facebookresearch_dinov2_main\vision_transformer.py", line 214, in prepare_tokens_with_masks
    x = self.patch_embed(x)
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "D:\Apps\AiApps\xdrive\DepthGen\Depth-Anything\torchhub/facebookresearch_dinov2_main\dinov2\layers\patch_embed.py", line 76, in forward
    x = self.proj(x)  # B C H W
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "D:\Apps\AiApps\xdrive\DepthGen\miniconda3\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
    return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

Windows 10, cuda 11

[LiheYoung]

Is your model successfully loaded to GPU in this line? Is the DEVICE outputs cuda?

[AlexYez]

Is your model successfully loaded to GPU in this line? Is the DEVICE outputs cuda?

Yes, I downloaded model and config file, and models loaded locally with this command: model = DepthAnything.from_pretrained('checkpoints/depth_anything_vitb14', local_files_only=True) and with commands:

print(torch.cuda.is_available())
print(torch.cuda.current_device())

I got:

True
0

I have RTX 3070 as 0 cuda device

[AlexYez]

I found the problem, for local model this code work: depth_anything = DepthAnything.from_pretrained('checkpoints/depth_anything_vitb14', local_files_only=True).to(DEVICE).eval() Please update manual, for local models ".to(DEVICE).eval()" parameter at the end of command needed