AnyNet icon indicating copy to clipboard operation
AnyNet copied to clipboard

Inference time evaluation input size and TX2 backend

Open MJITG opened this issue 5 years ago • 1 comments

Hi@v@mileyan, I want to know if the input image size is 1242x375 or 1232x368 since 1242x375 cannot run forward through the model. Another question is the same as #18. Could plz tell if you evaluate your model inference time on the TensorRT engine or not? Thank you for your reply and excellent code!

MJITG avatar Jun 05 '20 04:06 MJITG

The input size is 1232x368. The image is cropped before passing through the model. You can see this is Dataloader/KITTILoader.py

fenil25 avatar Aug 04 '20 16:08 fenil25