Freezing feature detection layers

WongKinYiu / yolor

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

GNU General Public License v3.0

1.98k stars 524 forks source link

Freezing feature detection layers #228

Open Swearinbag opened 2 years ago

Swearinbag commented 2 years ago

I've implemented a way to freeze layers of the network but I wonder what interval of layers decide the feature extraction of the input, so that I can freeze these and see if the model performance increases depending on my custom dataset.