search

kwotsin / TensorFlow-ENet

TensorFlow implementation of ENet
MIT License
257 stars 123 forks source link

Have anyone checked the inference time exactly? #25

Open msson opened 6 years ago

msson commented 6 years ago

When I run the test_enet.py, I see only about 0.5~1fps inference time with 1024x768 resolution. There must be other way to check exact inference time I think. Please give me advice. Thank you.

kwotsin commented 6 years ago

This greatly depends on the hardware you used and seems to be a duplicated problem of #19. Have you checked if the bottleneck comes from the data feeding part rather than model inference?