TypeError: unhashable type: 'list'

[Max-Well-Wang]

Hello, I have the following problems when I run the main.py file. Can you help me solve it?
Traceback (most recent call last):
File "C:/Users/Administrator/Desktop/ymq/Domain-Aware-Style-Transfer-main/Domain-Aware-Style-Transfer-main/main.py", line 68, in
model = Baseline(args)
File "C:\Users\Administrator\Desktop\ymq\Domain-Aware-Style-Transfer-main\Domain-Aware-Style-Transfer-main\baseline.py", line 79, in init
pretrained_vgg = torchfile.load('./baseline_checkpoints/vgg_normalised_conv4_1.t7')
File "D:\ANACONDA\envs\pytorch\lib\site-packages\torchfile.py", line 424, in load
return reader.read_obj()
File "D:\ANACONDA\envs\pytorch\lib\site-packages\torchfile.py", line 370, in read_obj
obj._obj = self.read_obj()
File "D:\ANACONDA\envs\pytorch\lib\site-packages\torchfile.py", line 385, in read_obj
k = self.read_obj()
File "D:\ANACONDA\envs\pytorch\lib\site-packages\torchfile.py", line 386, in read_obj
v = self.read_obj()
File "D:\ANACONDA\envs\pytorch\lib\site-packages\torchfile.py", line 370, in read_obj
obj._obj = self.read_obj()
File "D:\ANACONDA\envs\pytorch\lib\site-packages\torchfile.py", line 387, in read_obj
obj[k] = v
TypeError: unhashable type: 'list'

[Kibeom-Hong]

Thanks for your interest!

I think you should check the path of 'pretrained_vgg'.

How about set the path as the absolute path?

Please check the code at 71 lines

Thanks.

[mamemo]

Hey guys, I just had the same issue. It's a Windows specific error. When running the code on Linux it outputs the desired results.

Great work by the way!

[TerrenceHenry]

I have same error running on Win10.
File path is correct.
Any ideas on how to resolve this?

[Pragathi-PL]

Yahh same error while running in mac
any idea how to resolve ?

[surfingnirvana]

fix for windows:

baseline.py

line 71 pretrained_vgg = torchfile.load('./baseline_checkpoints/vgg_normalised_conv4_1.t7', force_8bytes_long=True)
line 445 pretrained_vgg = torchfile.load('./baseline_checkpoints/vgg_normalised_conv4_1.t7', force_8bytes_long=True)

site-packages\torchfile.py", line 288 for i in xrange(n): -------------> for i in range(n):