yolov5目标检测模型的知识蒸馏（基于响应的蒸馏）

Last update: Dec 04, 2022

Overview

代码地址：

https://github.com/Sharpiless/yolov5-knowledge-distillation

教师模型：

python train.py --weights weights/yolov5m.pt \
        --cfg models/yolov5m.yaml --data data/voc.yaml --epochs 50 \
        --batch-size 8 --device 0 --hyp data/hyp.scratch.yaml

蒸馏训练：

python train.py --weights weights/yolov5s.pt \
        --cfg models/yolov5s.yaml --data data/voc.yaml --epochs 50 \
        --batch-size 8 --device 0 --hyp data/hyp.scratch.yaml \
        --t_weights yolov5m.pt --distill

训练参数:

--weights：预训练模型

--t_weights：教师模型权重

--distill：使用知识蒸馏进行训练

--dist_loss：l2或者kl

--temperature：使用知识蒸馏时的温度

使用《Object detection at 200 Frames Per Second》中的损失

这篇文章分别对这几个损失函数做出改进，具体思路为只有当teacher network的objectness value高时，才学习bounding box坐标和class probabilities。

实验结果：

这里假设VOC2012中新增加的数据为无标签数据（2k张）。

教师模型	训练方法	蒸馏损失	P	R	mAP50
无	正常训练	不使用	0.7756	0.7115	0.7609
Yolov5l	output based	l2	0.7585	0.7198	0.7644
Yolov5l	output based	KL	0.7417	0.7207	0.7536
Yolov5m	output based	l2	0.7682	0.7436	0.7976
Yolov5m	output based	KL	0.7731	0.7313	0.7931

参数和细节正在完善，支持KL散度、L2 logits损失和Sigmoid蒸馏损失等

1. 正常训练：

2. L2蒸馏损失：

我的公众号：

关于作者

B站：https://space.bilibili.com/470550823

CSDN：https://blog.csdn.net/weixin_44936889

AI Studio：https://aistudio.baidu.com/aistudio/personalcenter/thirdview/67156

Github：https://github.com/Sharpiless

yolov5目标检测模型的知识蒸馏（基于响应的蒸馏）

Related tags

Overview

代码地址：

教师模型：

蒸馏训练：

训练参数:

实验结果：

1. 正常训练：

2. L2蒸馏损失：

我的公众号：

关于作者

Owner

Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

Code of Periodic Activation Functions Induce Stationarity

This is just a funny project that we want to see AutoEncoder (AE) can actually work to enhance the features we want

[ECCV 2020] Reimplementation of 3DDFAv2, including face mesh, head pose, landmarks, and more.

Point-NeRF: Point-based Neural Radiance Fields

Image to Image translation, image generataton, few shot learning

a baseline to practice

RoboDesk A Multi-Task Reinforcement Learning Benchmark

Official Repository for our ECCV2020 paper: Imbalanced Continual Learning with Partitioning Reservoir Sampling

The fastai deep learning library

World Models with TensorFlow 2

darija <-> english dictionary

Diverse Image Generation via Self-Conditioned GANs

Source code for the plant extraction workflow introduced in the paper “Agricultural Plant Cataloging and Establishment of a Data Framework from UAV-based Crop Images by Computer Vision”

Vector.ai assignment

《K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters》(2020)

Code/data of the paper "Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction" (BMVC2021)

Exploring the Dual-task Correlation for Pose Guided Person Image Generation

A PyTorch implementation of EfficientNet and EfficientNetV2 (coming soon!)

Prefix-Tuning: Optimizing Continuous Prompts for Generation