facebookresearch/maskrcnn-benchmark

Half/mixed-precision is not faster

Aperta

#1062 aperta il 27 ago 2019

 (3 commenti) (0 reazioni) (0 assegnatari)Python (2574 fork)batch import
help wanted

Metriche repository

Star
 (9161 stelle)
Metriche merge PR
 (Metriche PR in attesa)

Descrizione

❓ Questions and Help

As written in https://github.com/facebookresearch/maskrcnn-benchmark/issues/807#issuecomment-500112612 , DTYPE "float16" does not make training faster( and takes the same amount of memory) when tested with e2e_mask_rcnn_R_50_FPN_1x.yaml. Is this normal or am I doing something wrong? I also want to know if I can make inference faster by FP16(I tried model.half() in test_net, but doesn't work).
My environment is RTX Titan, cudnn 7.6, cuda10.0, driver version Driver Version: 418.67, pytorch-1.2.0, ubuntu 18.04.

Guida contributor