Virtual-Try-On-Flask icon indicating copy to clipboard operation
Virtual-Try-On-Flask copied to clipboard

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

Open saisusrith opened this issue 5 years ago • 9 comments

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]

saisusrith avatar Jan 25 '20 19:01 saisusrith

Hi, thanks for this issue.

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

GrayXu avatar Jan 26 '20 14:01 GrayXu

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 avatar Jan 27 '20 00:01 saisusrith

Hi @GrayXu any solution?

saisusrith avatar Jan 29 '20 18:01 saisusrith

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.

GrayXu avatar Feb 21 '20 14:02 GrayXu

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

carfei avatar Apr 16 '20 05:04 carfei

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

carfei avatar Apr 16 '20 06:04 carfei

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 avatar Jul 02 '20 11:07 mad-fogs

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.

mad-fogs avatar Jul 02 '20 14:07 mad-fogs

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?

anantaarora avatar Nov 07 '20 19:11 anantaarora