search

huanghoujing / beyond-part-models

PCB of paper: Beyond Part Models: Person Retrieval with Refined Part Pooling, using Pytorch
331 stars 81 forks source link

About the code execution process #30

Open ShuoYe2020 opened 5 years ago

ShuoYe2020 commented 5 years ago

Dear huanghoujing, thanks for your work and happy new year, I have great interest in your work, however my pytorch version is 1.0, so, when i run your code, There is an error: 'RuntimeError: zero-dimensional tensor (at position 0) cannot be concatenated ', could you please tell me, where should be change in your code?

huanghoujing commented 5 years ago

Your problem should be this line. You can change cat to stack to solve the problem.

BTW, you may use this code which is based on pytorch 1.0 and contains improved PCB and beyond.

ShuoYe2020 commented 5 years ago

Thanks for your help, now i have completed the network replication! My current confusion is in the testing phase, function get_sample() will get five parameters :im、 id、 cam、 im_name、 mark , what is 'id' and 'cam' represent for, What is the relation to the name such as ' 00000511_0004_00000007.jpg'?

I guess '0004' is the cam 4 ,what is 'mark'?