Size of Input Images for Using Pre-Trained Model

[ahkarami]

Dear @layumi,
Thank you for your nice work. I have a question. What is the correct size of input image, If one want to use your released pre-trained model (i.e., for forward pass & feature extraction of input image)? I mean (256,128) or (288,144)?

[layumi]

Hi @ahkarami
When training, we crop (256,128) from (288,144).
When testing, since we have global pooling, directly using (288,144) can yield the better performance.

[ahkarami]

Thank you.