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

用opencv的dnn模块做yolov5目标检测，包含C++和Python两个版本的程序

Markov Attention Models

Semantic Segmentation with Pytorch-Lightning

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals.

A curated list of awesome papers for Semantic Retrieval (TOIS Accepted: Semantic Models for the First-stage Retrieval: A Comprehensive Review).

Deep Reinforced Attention Regression for Partial Sketch Based Image Retrieval.

SeqAttack: a framework for adversarial attacks on token classification models

This repository contains several jupyter notebooks to help users learn to use neon, our deep learning framework

Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

TRIQ implementation

Pneumonia Detection using machine learning - with PyTorch

Robust & Reliable Route Recommendation on Road Networks

PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)

PaRT: Parallel Learning for Robust and Transparent AI

Cognition-aware Cognate Detection

The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)

Pytorch implementation of our paper under review -- 1xN Pattern for Pruning Convolutional Neural Networks

HashNeRF-pytorch - Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives

Refactoring dalle-pytorch and taming-transformers for TPU VM

Simple object detection app with streamlit