kevinzakka / recurrent-visual-attention

A PyTorch Implementation of "Recurrent Models of Visual Attention"
MIT License
468 stars 123 forks source link

Performance on CPU vs GPU #17

Closed xycforgithub closed 6 years ago

xycforgithub commented 6 years ago

Hi, Just wonder if anyone encounters the same problem - it looks like the code is faster on cpu than on gpu. On my cpu (i7) it only takes around 80s per epoch but on gpu (a P100) it takes around 180s.

Anyone with the same problem?

xycforgithub commented 6 years ago

Ok just saw the other post for faster retina. I changed to that faster retina and it seems the performance are similar.