tanluren / YOLOv3-model-pruning
对 YOLOv3 做模型剪枝(network slimming),对于 oxford hand 数据集(因项目需要),模型剪枝后的参数量减少 80%,Infer 的速度达到原来 2 倍,mAP 基本不变
☆12Updated 5 years ago
Alternatives and similar repositories for YOLOv3-model-pruning:
Users that are interested in YOLOv3-model-pruning are comparing it to the libraries listed below
- Convert YOLOv3 and YOLOv3-tiny (PyTorch version) into TensorRT models.☆61Updated 5 years ago
- this repo is forked from https://github.com/amdegroot/ssd.pytorch. Implemented by pytorch☆46Updated 5 years ago
- yolov5 onnx caffe☆114Updated 3 years ago
- ☆62Updated 4 years ago
- YOLOv3-training-prune☆59Updated 3 years ago
- MobileNetV3 based SSD-lite implementation in Pytorch☆99Updated 5 years ago
- centernet_simple☆24Updated 4 years ago
- centernet, mobilenetv2, centerface☆52Updated 5 years ago
- EfficientNetv2 TensorRT int8☆45Updated 3 years ago
- This repository provides a sample to run yolov3 on int8 mode in tensorRT☆26Updated 5 years ago
- provide pytorch model and ncnn model☆76Updated 4 years ago
- ☆25Updated 2 years ago
- yolov5 onnx caffe☆85Updated 3 years ago
- RepVGG TensorRT int8 量化,实测推理不到1ms一帧!☆61Updated 3 years ago
- centerNet Caffe inference CPP☆69Updated 5 years ago
- yolov5.yaml转换成yolov5.py☆17Updated 4 years ago
- A module to convert pytorch model to caffe model.☆66Updated 4 years ago
- U版yolov5 2.0的tensorrt加速☆37Updated 4 years ago
- onnx模型转caffe模型的工具☆24Updated 4 years ago
- centernet_mobilenetv2 inference by ncnn☆64Updated 5 years ago
- In this repository using the sparse training, group channel pruning and knowledge distilling for YOLOV4,☆31Updated last year
- ☆78Updated 4 years ago
- Stronger SSD & YOLO v3☆39Updated 5 years ago
- This is the unofficial implementation of the "CenterNet:Objects as Points".Just a simple try with self-modified shufflenetv2 and yolov3.…☆111Updated 3 years ago
- Personal Pytorch toy script.☆67Updated 2 years ago
- tensorrt wheels (API)☆77Updated 4 years ago
- ppyolo in pytorch. 44.8% box mAP.☆107Updated 3 years ago
- nanodet int8 量化,实测推理2ms一帧!☆37Updated 3 years ago
- 重新设计的RFBNet300,模型参数量只有0.99MB,AP达到0.78,200FPS☆99Updated 5 years ago
- Implement yolov5 with Tensorrt C++ api, and integrate batchedNMSPlugin. A Python wrapper is also provided.☆50Updated 3 years ago