Eromera/erfnet_pytorch

How to calculate FPS/FWT?

Closed this issue · 2 comments

Dr. Edurado: Hello!
I have been puzzled recently to ask you, so can you tell me?
I am very interested in your real-time semantic work, ERFNet Efficient Residual Factorized ConvNet, but I have not found a description of FPS from your paper, it is related to FWT: FORWARD PASS TIME IN SECONDS, I also run your program , but I don't know if fwt is the Avg time/img:0.042 output during the training of your program, or the forward time per img tested by the script eval_forwardTime.py under the code eval folder, and this time and batchsize have Is it a big relationship? Also, does fwt need to test twice for training and test sets (ie, are they the same)?
I don't understand very well, can you tell me?
Thank you very much for taking time out of your busy schedule!

Forward time in the paper is the time output by eval_forwardTime.py with the model by absorving the batchnorm layers and running with batch_size=1 with the network in eval mode. Training and test sets should be the same, you can select the resolution in the script but normally we use 1024x512.

Hi! Thanks for your reply.