LWCC: A LightWeight Crowd Counting library for Python that includes several pretrained state-of-the-art models.

Overview

LWCC: A LightWeight Crowd Counting library for Python

LWCC is a lightweight crowd counting framework for Python. It wraps four state-of-the-art models all based on convolutional neural networks: CSRNet, Bayesian crowd counting, DM-Count, and SFANet. The library is based on PyTorch.

Installation

The easiest way to install library LWCC and its prerequisites is to use the package manager pip.

pip install lwcc

Usage

You can import the library and use its functionalities by:

from lwcc import LWCC

Count estimation

Most straightforward way to use the library:

img = "path/to/image"
count = LWCC.get_count(img)

This uses CSRNet pretrained on SHA (default). You can choose a different model pretrained on different data set using:

count = LWCC.get_count(img, model_name = "DM-Count", model_weights = "SHB")

The result is a float with predicted count.

Large images

Note: By default all images are resized such that the longest side is less than 1000px, preserving the aspect ratio. Otherwise models might perform worse for large images with sparse crowds (counting patterns on shirts, dresses). If you are estimating dense crowds, we recommend you to set the resize_img to False. The call should look like this:

count = LWCC.get_count(img, model_name = "DM-Count", model_weights = "SHB", resize_img = True)

Multiple images

Library allows prediction of count for multiple images with a single call of get_count. You can simply pass a list of image paths:

img1 = "path/to/image1"
img2 = "path/to/image2"
count = LWCC.get_count([img1, img2])

Result is then a dictionary of pairs image_name : image_count: result

Density map

You can also request a density map by setting flag return_density = True. The result is then a tuple (count, density_map), where density_map is a 2d array with predicted densities. The array is smaller than the input image and its size depends on the model.

import matplotlib.pyplot as plt

count, density = LWCC.get_count(img, return_density = True)

plt.imshow(density)
plt.show()

result_density

This also works for multiple images (list of image paths as input). Result is then a tuple of two dictionaries, where the first dictionary is the same as above (pairs of image_name : image_count) and the second dictionary contains pairs of image_name : density_map.

Loading the model

You can also directly access the PyTorch models by loading them first with the load_model method.

model = LWCC.load_model(model_name = "DM-Count", model_weights = "SHA")

The loaded model is a PyTorch model and you can access its weights as with any other PyTorch model.

You can use it for inference as:

 count = LWCC.get_count(img, model = model)

Models

LWCC currently offers 4 models (CSRNet, Bayesian crowd counting, DM-Count, SFANet) pretrained on Shanghai A, Shanghai B, and UCF-QNRF datasets. The following table shows the model name and MAE / MSE result of the available pretrained models on the test sets.

Model name SHA SHB QNRF
CSRNet 75.44 / 113.55 11.27 / 19.32 Not available
Bay 66.92 / 112.07 8.27 / 13.56 90.43 / 161.41
DM-Count 61.39 / 98.56 7.68 / 12.66 88.97 / 154.11
SFANet Not available 7.05 / 12.18 Not available

Valid options for model_name are written in the first column and thus include: CSRNet, Bay, DM-Count, and SFANet. Valid options for model_weights are written in the first row and thus include: SHA, SHB, and QNRF.

Note: Not all model_weights are supported with all model_names. See the above table for possible combinations.

How does it work?

The goal of crowd counting methods is to determine the number of people present in a particular area. There exist many approaches (detection, regression, density-based approaches), however, since 2015 many convolutional neural network (CNN) based approaches have been proposed. The basic idea behind CNN based approaches is that they normally try to predict the density map from the input image and infer the count from it. These models differ in the use of different backbones, loss functions, additional maps, etc. If you are interested in a particular algorithm, you are welcome to read the paper belonging to the specific model.

FAQ - Frequently asked questions

Can I see some more examples of LWCC in action?

Yes, you can find some examples in Examples.ipynb!

How accurate are the models?

You can see the mean absolute error (MAE) and mean squared error (MSE) of the pretrained models on test sets in section models. We recommend models pretrained on SHA or QNRF for dense crowds, and SHB for sparse crowds.

Is GPU support available?

No, GPU support is currently not supported yet, but is planned for the future version.

Can I load custom weights?

Full support of loading custom pretrained weights is not supported, but is planned in the future version.

Can I train the models myself?

The library does not support training, only inference.

Why are my results bad?

This might depend on the model you use, image size, density or type of the crowd, or the weights that you use. For example, models might often make mistakes for images with a group portrait, as they are trained on images containing crowds on streets, concerts, etc. Using SHAweights on relatively sparse crowds might also give very wrong results. On the other hand, SHB might perform better as the weights were trained on Shanghai B data set, which containts images with relatively sparse crowds. Using high quality images with sparse crowds might also yield bad results, as the algorithms might mistake some textures of clothings for a crowd.

As a rule of thumb, you should use SHB if you are planning on estimating the number of people in images with sparse crowds, and SHA or QNRF for images with dense crowds. Keep in mind that current algorithms predict the density, and there still might be some mistakes. You are welcome to try out different combinations of models and weights and see which one works the best for your problem.

Support

If you like the library please show us your support by ⭐️ starring the project!

If you wish to include your own crowd counting model, please contact us ([email protected] or [email protected]).

Stargazers

Stargazers repo roster for @tersekmatija/lwcc

Citation

This library is a result of a research of CNN Crowd Counting models by Matija Teršek and Maša Kljun. Although the paper has not been published yet, please provide the link to this GitHub repository if you use LWCC in your research.

License

This library is licensed under MIT license (see LICENSE). Licenses of the models wrapped in the library will be inherited, depending on the model you use ( CSRNet, Bayesian crowd counting, DM-Count, and SFANet).

Owner
Matija Teršek
Data Science Master's student
Matija Teršek
simple demo codes for Learning to Teach with Dynamic Loss Functions

Learning to Teach with Dynamic Loss Functions This repo contains the simple demo for the NeurIPS-18 paper: Learning to Teach with Dynamic Loss Functio

Lijun Wu 15 Dec 30, 2021
Updated for TTS(CE) = Also Known as TTN V3. The code requires the first server to be 'ttn' protocol.

Updated Updated for TTS(CE) = Also Known as TTN V3. The code requires the first server to be 'ttn' protocol. Introduction This balenaCloud (previously

Remko 1 Oct 17, 2021
Structured Data Gradient Pruning (SDGP)

Structured Data Gradient Pruning (SDGP) Weight pruning is a technique to make Deep Neural Network (DNN) inference more computationally efficient by re

Bradley McDanel 10 Nov 11, 2022
Official implementation of paper Gradient Matching for Domain Generalization

Gradient Matching for Domain Generalisation This is the official PyTorch implementation of Gradient Matching for Domain Generalisation. In our paper,

94 Dec 23, 2022
Vision Transformer for 3D medical image registration (Pytorch).

ViT-V-Net: Vision Transformer for Volumetric Medical Image Registration keywords: vision transformer, convolutional neural networks, image registratio

Junyu Chen 192 Dec 20, 2022
Official Pytorch Implementation of Unsupervised Image Denoising with Frequency Domain Knowledge

Unsupervised Image Denoising with Frequency Domain Knowledge (BMVC 2021 Oral) : Official Project Page This repository provides the official PyTorch im

Donggon Jang 12 Sep 26, 2022
You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks.

AllSet This is the repo for our paper: You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks. We prepared all codes and a subse

Jianhao 51 Dec 24, 2022
Deep learning model, heat map, data prepo

deep learning model, heat map, data prepo

Pamela Dekas 1 Jan 14, 2022
Joint Detection and Identification Feature Learning for Person Search

Person Search Project This repository hosts the code for our paper Joint Detection and Identification Feature Learning for Person Search. The code is

712 Dec 17, 2022
Repository for "Toward Practical Monocular Indoor Depth Estimation" (CVPR 2022)

Toward Practical Monocular Indoor Depth Estimation Cho-Ying Wu, Jialiang Wang, Michael Hall, Ulrich Neumann, Shuochen Su [arXiv] [project site] DistDe

Meta Research 122 Dec 13, 2022
DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing Figure: Joint multi-attribute edits using DyStyle model. Great diversity

74 Dec 03, 2022
Semi-supervised Video Deraining with Dynamical Rain Generator (CVPR, 2021, Pytorch)

S2VD Semi-supervised Video Deraining with Dynamical Rain Generator (CVPR, 2021) Requirements and Dependencies Ubuntu 16.04, cuda 10.0 Python 3.6.10, P

Zongsheng Yue 53 Nov 23, 2022
Deep Compression for Dense Point Cloud Maps.

DEPOCO This repository implements the algorithms described in our paper Deep Compression for Dense Point Cloud Maps. How to get started (using Docker)

Photogrammetry & Robotics Bonn 67 Dec 06, 2022
It's like Shape Editor in Maya but works with skeletons (transforms).

Skeleposer What is Skeleposer? Briefly, it's like Shape Editor in Maya, but works with transforms and joints. It can be used to make complex facial ri

Alexander Zagoruyko 1 Nov 11, 2022
An Efficient Implementation of Analytic Mesh Algorithm for 3D Iso-surface Extraction from Neural Networks

AnalyticMesh Analytic Marching is an exact meshing solution from neural networks. Compared to standard methods, it completely avoids geometric and top

Karbo 45 Dec 21, 2022
Codes and pretrained weights for winning submission of 2021 Brain Tumor Segmentation (BraTS) Challenge

Winning submission to the 2021 Brain Tumor Segmentation Challenge This repo contains the codes and pretrained weights for the winning submission to th

94 Dec 28, 2022
Used to record WKU's utility bills on a regular basis.

WKU水电费小助手 一个用于定期记录WKU水电费的脚本 Looking for English Readme? 背景 由于WKU校园内的水电账单系统时常存在扣费延迟的现象,而补扣的费用缺乏令人信服的证明。不少学生为费用摸不着头脑,但也没有申诉的依据。为了更好地掌握水电费使用情况,留下一手证据,我开源

2 Jul 21, 2022
Autonomous Driving on Curvy Roads without Reliance on Frenet Frame: A Cartesian-based Trajectory Planning Method

C++/ROS Source Codes for "Autonomous Driving on Curvy Roads without Reliance on Frenet Frame: A Cartesian-based Trajectory Planning Method" published in IEEE Trans. Intelligent Transportation Systems

Bai Li 88 Dec 23, 2022
Navigating StyleGAN2 w latent space using CLIP

Navigating StyleGAN2 w latent space using CLIP an attempt to build sth with the official SG2-ADA Pytorch impl kinda inspired by Generating Images from

Mike K. 55 Dec 06, 2022
MM1 and MMC Queue Simulation using python - Results and parameters in excel and csv files

implementation of MM1 and MMC Queue on randomly generated data and evaluate simulation results then compare with analytical results and draw a plot curve for them, simulate some integrals and compare

Mohamadreza Rezaei 1 Jan 19, 2022