search

GrayXu / Virtual-Try-On-Flask

Virtual Try-on Network on Flask
Mozilla Public License 2.0
84 stars 20 forks source link

Run time error.output with shape [1, 256, 192] doesn't match the broadcast shape [3, 256, 192] #2

Open saisusrith opened 4 years ago

saisusrith commented 4 years ago

Hi while running the your template.ipynb we get the following error. Even after debugging I could not find the error. RuntimeError: output with shape [1, 256, 192] doesn't match the broadcast shape [3, 256, 192]

GrayXu commented 4 years ago

Hi, thanks for this issue.

Can you copy complete error logs, like which line incurred this error?

saisusrith commented 4 years ago

Hi GrayXu,we debugged your code . The error is at line 179 "one_map = Model.transformer(one_map)".After it calls the Model.transformer error pops up

saisusrith commented 4 years ago

Hi @GrayXu any solution?

GrayXu commented 4 years ago

Sry,
because of Coronavirus vacation in China, I can't access GPU machines to test codes these days.
I don't find errors in Model.transformer. The transformer' just tensorlize and normalize data.
Can you show your local enviroments? I only test it on torch==1.2.0 torchvision==0.2.0 with GPU.

carfei commented 4 years ago

I also encountered the same error message, don't know if you solved it? How to solve it?

carfei commented 4 years ago

@GrayXu ，An error occurred in getPoseMap(self, pose_data)，The number of output channels changed from 3 to 1.So how to solve it?

mad-fogs commented 4 years ago

Sry, because of Coronavirus vacation in China, I can't access GPU machines to test codes these days. I don't find errors in Model.transformer. The transformer' just tensorlize and normalize data. Can you show your local enviroments? I only test it on torch==1.2.0 torchvision==0.2.0 with GPU.

i use torch==1.2.0 torchvision==0.2.0 with GPU, but the error still exists.

mad-fogs commented 4 years ago

Sry, because of Coronavirus vacation in China, I can't access GPU machines to test codes these days. I don't find errors in Model.transformer. The transformer' just tensorlize and normalize data. Can you show your local enviroments? I only test it on torch==1.2.0 torchvision==0.2.0 with GPU.

i use torch==1.2.0 torchvision==0.2.0 with GPU, but the error still exists.

solved. input image size should be 192*256.

anantaarora commented 3 years ago

Hi @mad-fogs , When I am clicking the button for selecting the cloth, it throws an error on submitting. We are saving them in static/img folder right?