about the size of the conv kernel

Ning-Ding / Implementation-CVPR2015-CNN-for-ReID

Implementation for CVPR 2015 Paper: "An Improved Deep Learning Architecture for Person Re-Identification".

MIT License

147 stars 71 forks source link

Closed dingchenwei closed 7 years ago

dingchenwei commented 7 years ago

Hi, I found in the paper that the kernel size is 3 dims, but in your implementation it is 2 dims, is there any difference or influence about that?

dingchenwei commented 7 years ago

I have understand that..conv2D means doing 3D convolution. Sorry for disturbing