Demo for SkipNet architecture presented in ICCV 2021 paper of "Bias Loss for Mobile Neural Networks".
for installing required packages run
pip install -r requirements.txt
Pretrained models are available from Google Drive. For the testing please download and place them in the same directory as the validation script (currently testing available only for skipnet-m, code will be updated).
python validate.py --data path/to/the/dataset
"Bias Loss for Mobile Neural Networks"
By Lusine Abrahamyan, Valentin Ziatchin, Yiming Chen and Nikos Deligiannis.
SkipNet beats other SOTA lightweight CNNs such as MobileNetV3 and FBNet.
|
