在运行dtu_test.sh时出现test error

[wln19]

Traceback (most recent call last):
File "test.py", line 435, in
save_depth(testlist)
File "test.py", line 133, in save_depth
save_scene_depth([scene])
File "test.py", line 162, in save_scene_depth
outputs = model(sample_cuda["imgs"], sample_cuda["proj_matrices"], sample_cuda["depth_values"])
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/parallel/data_parallel.py", line 153, in forward
return self.module(*inputs[0], **kwargs[0])
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/hy-tmp/Transmvsnet/models/TransMVSNet.py", line 161, in forward
features.append(self.feature(img))
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/hy-tmp/Transmvsnet/models/module.py", line 486, in forward
out = self.out1(intra_feat)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/container.py", line 117, in forward
input = module(input)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/hy-tmp/Transmvsnet/models/dcn.py", line 71, in forward
return deform_conv2d(
TypeError: deform_conv2d() got an unexpected keyword argument 'mask'

[wtyuan96]

deform_conv2d 函数是从 torchvision import 的，参见 link，请检查一下 deform_conv2d 是否被正确 import，以及 torchvision 的版本是否正确。

[jinzhenmu]

您解决了吗？