hi
working in conda i can use midas_v21_small and midas_v21 and everything is ok
using hybrid (file dpt_hybrid-mida-501f0c75.pt in weights) i have this error (on the same input image on midas_v21)
Any suggestions??
Thanks
Luca
update this error is relative to Ubuntu LTS 18.04. In Apple M1 everything works fine
processing input/luca.jpg (1/3)
/home/luca/.local/lib/python3.6/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode)
Traceback (most recent call last):
File "run.py", line 188, in
run(args.input_path, args.output_path, args.model_weights, args.model_type, args.optimize)
File "run.py", line 122, in run
prediction = model.forward(sample)
File "/home/luca/Downloads/MiDaS-master/midas/dpt_depth.py", line 108, in forward
return super().forward(x).squeeze(dim=1)
File "/home/luca/Downloads/MiDaS-master/midas/dpt_depth.py", line 71, in forward
layer_1, layer_2, layer_3, layer_4 = forward_vit(self.pretrained, x)
File "/home/luca/Downloads/MiDaS-master/midas/vit.py", line 59, in forward_vit
glob = pretrained.model.forward_flex(x)
File "/home/luca/Downloads/MiDaS-master/midas/vit.py", line 127, in forward_flex
x = self.patch_embed.backbone(x)
File "/home/luca/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/luca/.local/lib/python3.6/site-packages/timm/models/resnetv2.py", line 409, in forward
x = self.forward_features(x)
File "/home/luca/.local/lib/python3.6/site-packages/timm/models/resnetv2.py", line 403, in forward_features
x = self.stem(x)
File "/home/luca/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/luca/.local/lib/python3.6/site-packages/torch/nn/modules/container.py", line 141, in forward
input = module(input)
File "/home/luca/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/luca/.local/lib/python3.6/site-packages/timm/models/layers/std_conv.py", line 70, in forward
self.weight.view(1, self.out_channels, -1), None, None,
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
isl-org
