🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~
翻译 - shufflev2-yolov5：更轻、更快、更容易部署。由yolov5进化而来，模型大小只有1.7M（int8）和3.3M（fp16）。当输入大小为320×320时，它可以在树莓派4B上达到10+ FPS~
C++2.29 k
5 个月前
YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming), Quantizat...
Python998
3 年前
尝试将PP-LCNet转为PyTorch版本，并测试相关指标
Python7
2 年前
Pytorch Version of PP-LCNet
Python10
3 年前
implementation of PPLCNet with SiLU, easier to deploy
Python0
7 个月前