Wasabi Url

Change model zoo to wasabi to save model

PyTorch Encoding v1.2.0

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.

	crop size	PyTorch	Gluon
ResNeSt-50	224	81.03	81.04
ResNeSt-101	256	82.83	82.81
ResNeSt-200	320	83.84	83.88
ResNeSt-269	416	84.54	84.53

Semantic Segmentation

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

Results on ADE20K

Method	Backbone	pixAcc%	mIoU%
Deeplab-V3	ResNet-50	80.39	42.1
	ResNet-101	81.11	44.14
	ResNeSt-50 (ours)	81.17	45.12
	ResNeSt-101 (ours)	82.07	46.91
	ResNeSt-200 (ours)	82.45	48.36
	ResNeSt-269 (ours)	82.62	47.60

PyTorch Encoding v1.0.1

1. Compatible with stable PyTorch 14..0.

PyTorch Encoding v1.0.0

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

PyTorch Encoding 0.4.3

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

Encoding Layer & Sync BN

Make the compilation easier to the users.

Encoding Layer

Memory efficient implementation of Encoding Layer.