3 results found Sort:

478
2.2k
mit
40
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Ari...
Created 2019-12-04
295 commits to master branch, last one 2 years ago
YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming), Quantizat...
Created 2021-10-26
62 commits to main branch, last one 2 years ago
A package to make do Network Slimming a little easier
Created 2021-01-29
36 commits to master branch, last one 2 years ago