guoxuan112 Goto Github PK

viscpm

Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列

yolo-multi-backbones-attention

Model Compression—YOLOv3 with multi lightweight backbones(ShuffleNetV2 HuaWei GhostNet), attention, prune and quantization

yoloair

🔥🔥🔥YOLOv5, YOLOv6, YOLOv7, PPYOLOE, YOLOX, YOLOR, YOLOv4, YOLOv3, PPYOLO, PPYOLOv2, Transformer, Attention, TOOD and Improved-YOLOv5-YOLOv7... Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀

yolof

yolov3-channel-and-layer-pruning

yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

yolov5-lite

🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~

yolov5-multibackbone-compression

YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming) and Quantization (MQBench) Compression Tool Box.

yolov5prune

yolov5_prune

yolov5 prune，Support V2, V3, V4 and V6 versions of yolov5

yolov6

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

yolov7

🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

zh-google-styleguide

Google 开源项目风格指南 (中文版)