Change model zoo to wasabi to save model

ResNeSt

Split-Attention Network, A New ResNet Variant. It significantly boosts the performance of downstream models such as Mask R-CNN, Cascade R-CNN and DeepLabV3.

Semantic Segmentation

• PyTorch models and training: Please visit PyTorch Encoding Toolkit.
• Training with Gluon: Please visit GluonCV Toolkit.

Results on ADE20K

1. Compatible with stable PyTorch 14..0.

1. Compatible with stable PyTorch 1.0.
2. Inplace ABN with SyncBN.
3. ImageNet training script

1. Segmentation examples and pretrained models.
2. Pypi install through pip install torch-encoding

Make the compilation easier to the users.

Memory efficient implementation of Encoding Layer.