GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → ZhengPeng7 → W-Net-Keras

ZhengPeng7 / W-Net-Keras

Licence: MIT license
An unofficial implementation of W-Net for crowd counting.

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

kerasu-netcrowd-countingw-net

Projects that are alternatives of or similar to W-Net-Keras

PyTorch-Deep-Image-Steganography
A PyTorch implementation of image steganography utilizing deep convolutional neural networks
Stars: ✭ 71 (+255%)
Mutual labels:  u-net
Deep-Learning-liver-segmentation
Application of Deep Learning to the segmentation of medical images
Stars: ✭ 39 (+95%)
Mutual labels:  u-net
NWPU-Crowd-Sample-Code
The sample code for a large-scale crowd counting dataset, NWPU-Crowd.
Stars: ✭ 140 (+600%)
Mutual labels:  crowd-counting
U-Net-Satellite
Road Detection from satellite images using U-Net.
Stars: ✭ 38 (+90%)
Mutual labels:  u-net
UNet-Tensorflow
A brief tensorflow implementation about UNet.
Stars: ✭ 26 (+30%)
Mutual labels:  u-net
MARUNet
Multi-level Attention Refined UNet for crowd counting
Stars: ✭ 30 (+50%)
Mutual labels:  crowd-counting
DeepWay.v2
Autonomous navigation for blind people
Stars: ✭ 65 (+225%)
Mutual labels:  u-net
CSRNet-keras
Implementation of the CSRNet paper (CVPR 18) in keras-tensorflow
Stars: ✭ 107 (+435%)
Mutual labels:  crowd-counting
yapic
Yet Another Pixel Classifier (based on deep learning)
Stars: ✭ 24 (+20%)
Mutual labels:  u-net
IIM
PyTorch implementations of the paper: "Learning Independent Instance Maps for Crowd Localization"
Stars: ✭ 94 (+370%)
Mutual labels:  crowd-counting
radnet
U-Net for biomedical image segmentation
Stars: ✭ 11 (-45%)
Mutual labels:  u-net
adaptive-segmentation-mask-attack
Pre-trained model, code, and materials from the paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation" (MICCAI 2019).
Stars: ✭ 50 (+150%)
Mutual labels:  u-net
Fashion-Clothing-Parsing
FCN, U-Net models implementation in TensorFlow for fashion clothing parsing
Stars: ✭ 29 (+45%)
Mutual labels:  u-net
squeeze-unet
Squeeze-unet Semantic Segmentation for embedded devices
Stars: ✭ 21 (+5%)
Mutual labels:  u-net
S-DCNet
Unofficial Pytorch implementation of S-DCNet and SS-DCNet
Stars: ✭ 17 (-15%)
Mutual labels:  crowd-counting
Pix2Pix-Keras
基于pix2pix模型的动漫图片自动上色(keras实现) 2019-2-25
Stars: ✭ 95 (+375%)
Mutual labels:  u-net
Smart-City-Sample
The smart city reference pipeline shows how to integrate various media building blocks, with analytics powered by the OpenVINO™ Toolkit, for traffic or stadium sensing, analytics and management tasks.
Stars: ✭ 141 (+605%)
Mutual labels:  crowd-counting
Crowd-Counting-with-MCNNs
Crowd counting on the ShanghaiTech dataset, using multi-column convolutional neural networks.
Stars: ✭ 23 (+15%)
Mutual labels:  crowd-counting
deepedge
deep learning edge detector based on U-net and BSDS 500 dataset
Stars: ✭ 25 (+25%)
Mutual labels:  u-net
CrowdFlow
Optical Flow Dataset and Benchmark for Visual Crowd Analysis
Stars: ✭ 87 (+335%)
Mutual labels:  crowd-counting
View All Similar Projects ➔

W-Net-Keras

Unofficial implementation of W-Net for crowd counting in Keras.

Paper:

Results now:

On dataset ShanghaiTech B

Under development...

MAE MSE Mean of Frobenius Norm MAPE PSNR SSIM
7.85 12.17 6.75e-7 6.46% 29.27 0.93

Dataset:

Training Parameters:

  1. Loss = MSE * 1000 + BCE * 10;

  2. Optimizer = Adam(lr=1e-4, decay=5e-3);

  3. Batch size: 1;

  4. Data augmentation: Flip horizontally online randomly;

  5. Patch: No patch;

  6. Batch normalization: No BN layers at present;

  7. Weights: Got best weights in epoch248(250 epochs in total), and here is the loss records:

    Loss_records

  8. Prediction example:

    example

Run:

  1. Download dataset;
  2. Data generation: run thegenerate_datasets.ipynb .
  3. Run the main.ipynb to train, test, analyze and evaluate the image quality.
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].