EfficientNet-PyTorch
EfficientNet-PyTorch copied to clipboard
Extract features and endpoints in one pass
Hi,
I would like to extract features and the endpoints in one pass like in the original implementation.
import efficientnet_builder
features, endpoints = efficientnet_builder.build_model_base(images, 'efficientnet-b0')
Can I call extract_features(self, inputs)
and extract_endpoints(self, inputs)
separately without affecting the computational graph? If yes, does the order of call make a difference? If not, How to do it? My idea is to use both features and these endpoints for my task. Any help is appreciated!
Thanks!