Awesome
HEAD
mscnn crowd counting model
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 arXiv paper
<p align="center"> <img src="doc/msb.png" alt="multi-scale block" width="350px"> </p> <p align="center"> <img src="doc/mscnn_model.png" alt="mscnn_model" width="800px"> </p> <p align="center"> <img src="doc/mscnn_architecture.png" alt="mscnn_architecture" width="360px"> </p> <p align="center"> <img src="doc/result_display.png" alt="result_display" width="650px"> </p> <p align="center"> <img src="doc/result_table.png" alt="result_table" width="320px"> </p>Contents
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
- Get the code
git clone https://github.com/Ling-Bao/mscnn
cd mscnn
Preparation
-
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.
-
Get dataset and its corresponding map label Baidu Yun Password: sags
-
Unzip dataset to mscnn root directory
tar -xzvf Data_original.tar.gz
Train/Eval
Train is easy, just using following step.
- Train. Using mscnn_train.py to evalute mscnn model
python mscnn_train.py
- Eval. Using mscnn_eval.py to evalute mscnn model
python mscnn_eval.py
Details
- Improving model structure. Add Batch Normal after each convolution layer.
TAIL