mscnn人群密度估计模型实现

最新推荐文章于 2022-07-13 10:14:55 发布

Bao_Ling

最新推荐文章于 2022-07-13 10:14:55 发布

阅读量3.8k

点赞数 2

分类专栏：计算机视觉Blogs 深度学习理论Blogs Tensorflow深度神经网络开源框架Blogs

本文链接：https://blog.csdn.net/qingqingdeaini/article/details/79922549

版权

计算机视觉Blogs 同时被 3 个专栏收录

5 篇文章

订阅专栏

深度学习理论Blogs

2 篇文章

订阅专栏

Tensorflow深度神经网络开源框架Blogs

2 篇文章

订阅专栏

本项目为人群计数的开源项目，实现了一种基于多尺度卷积神经网络的人群计数方法。该模型已在ShanghaiTech数据集上进行了验证，并提供了训练和评估的详细步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

mscnn crowd counting model

=======

github

Introduction

This is open source project for crowd counting. Implement with paper “Multi-scale Convolution Neural Networks for Crowd Counting” write by Zeng L, Xu X, Cai B, et al. For more details, please refer to our arXiv paper.

The implementation code of mscnn crowd counting model, please click on github.

multi-scale block

mscnn_model

mscnn_architecture

result_display

result_table

Installation
Preparation
Train/Eval
Details

Installation

Configuration requirements

python3.x

Please using GPU, suggestion more than GTX960

python-opencv
#tensorflow-gpu==1.0.0
#tensorflow==1.0.0
matplotlib==2.2.2
numpy==1.14.2

conda install -c https://conda.binstar.org/menpo opencv3
pip install -r requirements.txt

2. Get the code

git clone https://github.com/Ling-Bao/mscnn
cd mscnn

### Preparation 1. ShanghaiTech Dataset. ShanghaiTech Dataset makes by Zhang Y, Zhou D, Chen S, et al. For more detail, please refer to paper “Single-Image Crowd Counting via Multi-Column Convolutional Neural Network” and click on [here](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhang_Single-Image_Crowd_Counting_CVPR_2016_paper.pdf). 2. Get dataset and its corresponding map label [Baidu Yun](https://pan.baidu.com/s/12EqB1XDyFBB0kyinMA7Pqw) Password: sags 3. Unzip dataset to mscnn root directory

 tar -xzvf  Data_original.tar.gz

### Train/Eval Train is easy, just using following step. 1. Train. Using [mscnn_train.py](mscnn_train.py) to evalute mscnn model

python mscnn_train.py

2. Eval. Using [mscnn_eval.py](mscnn_eval.py) to evalute mscnn model

python mscnn_eval.py

### Details 1. Improving model structure. Add Batch Normal after each convolution layer. 2. Improving activation funtion for last layer to adapt crowd counting map estimation.

formulation