EfficientNet-PyTorch icon indicating copy to clipboard operation
EfficientNet-PyTorch copied to clipboard

Published 20 hours ago • verified publisher icon lukemelas

The inference time of padding operator is too slow

Open dollarser opened this issue 4 years ago • 0 comments

What is the difference between padding operator in efficientnet and conventional padding? Why is the inference time of padding for onnx model slow? If I need to run faster, how can I optimize the padding operator? thank you!

dollarser avatar Dec 13 '20 08:12 dollarser