thuyngch / Human Segmentation Pytorch
Human segmentation models, training/inference code, and trained weights, implemented in PyTorch
Stars: ✭ 289
Projects that are alternatives of or similar to Human Segmentation Pytorch
Pytorch 3dunet
3D U-Net model for volumetric semantic segmentation written in pytorch
Stars: ✭ 765 (+164.71%)
Mutual labels: jupyter-notebook, semantic-segmentation, unet
Pytorch Unet
Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation
Stars: ✭ 470 (+62.63%)
Mutual labels: jupyter-notebook, semantic-segmentation, unet
Deep Learning In Production
Develop production ready deep learning code, deploy it and scale it
Stars: ✭ 216 (-25.26%)
Mutual labels: jupyter-notebook, semantic-segmentation, unet
Multiclass Semantic Segmentation Camvid
Tensorflow 2 implementation of complete pipeline for multiclass image semantic segmentation using UNet, SegNet and FCN32 architectures on Cambridge-driving Labeled Video Database (CamVid) dataset.
Stars: ✭ 67 (-76.82%)
Mutual labels: jupyter-notebook, semantic-segmentation, unet
Kili Playground
Simplest and fastest image and text annotation tool.
Stars: ✭ 166 (-42.56%)
Mutual labels: jupyter-notebook, semantic-segmentation
Keras Segmentation Deeplab V3.1
An awesome semantic segmentation model that runs in real time
Stars: ✭ 156 (-46.02%)
Mutual labels: jupyter-notebook, semantic-segmentation
multiclass-semantic-segmentation
Experiments with UNET/FPN models and cityscapes/kitti datasets [Pytorch]
Stars: ✭ 96 (-66.78%)
Mutual labels: unet, semantic-segmentation
Unet
Generic U-Net Tensorflow 2 implementation for semantic segmentation
Stars: ✭ 100 (-65.4%)
Mutual labels: jupyter-notebook, semantic-segmentation
image-segmentation
Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available
Stars: ✭ 62 (-78.55%)
Mutual labels: unet, semantic-segmentation
3D-UNet-PyTorch-Implementation
The implementation of 3D-UNet using PyTorch
Stars: ✭ 78 (-73.01%)
Mutual labels: unet, semantic-segmentation
Fcn For Semantic Segmentation
Implemention of FCN-8 and FCN-16 with Keras and uses CRF as post processing
Stars: ✭ 155 (-46.37%)
Mutual labels: jupyter-notebook, semantic-segmentation
Multi Task Refinenet
Multi-Task (Joint Segmentation / Depth / Surface Normas) Real-Time Light-Weight RefineNet
Stars: ✭ 139 (-51.9%)
Mutual labels: jupyter-notebook, semantic-segmentation
Ds bowl 2018
Kaggle Data Science Bowl 2018
Stars: ✭ 116 (-59.86%)
Mutual labels: jupyter-notebook, unet
satellite-Image-Semantic-Segmentation-Unet-Tensorflow-keras
Collection of different Unet Variant suchas VggUnet, ResUnet, DenseUnet, Unet. AttUnet, MobileNetUnet, NestedUNet, R2AttUNet, R2UNet, SEUnet, scSEUnet, Unet_Xception_ResNetBlock
Stars: ✭ 43 (-85.12%)
Mutual labels: unet, semantic-segmentation
ResUNetPlusPlus-with-CRF-and-TTA
ResUNet++, CRF, and TTA for segmentation of medical images (IEEE JBIHI)
Stars: ✭ 98 (-66.09%)
Mutual labels: unet, semantic-segmentation
celldetection
Cell Detection with PyTorch.
Stars: ✭ 44 (-84.78%)
Mutual labels: unet, semantic-segmentation
unet pytorch
Pytorch implementation of UNet for converting aerial satellite images into google maps kinda images.
Stars: ✭ 27 (-90.66%)
Mutual labels: unet, semantic-segmentation
TensorFlow-Advanced-Segmentation-Models
A Python Library for High-Level Semantic Segmentation Models based on TensorFlow and Keras with pretrained backbones.
Stars: ✭ 64 (-77.85%)
Mutual labels: unet, semantic-segmentation
Human-Segmentation-PyTorch
Human segmentation models, training/inference code, and trained weights, implemented in PyTorch.
Supported networks
- UNet: backbones MobileNetV2 (all aphas and expansions), ResNetV1 (all num_layers)
- DeepLab3+: backbones ResNetV1 (num_layers=18,34,50,101), VGG16_bn
- BiSeNet: backbones ResNetV1 (num_layers=18)
- PSPNet: backbones ResNetV1 (num_layers=18,34,50,101)
- ICNet: backbones ResNetV1 (num_layers=18,34,50,101)
To assess architecture, memory, forward time (in either cpu or gpu), numper of parameters, and number of FLOPs of a network, use this command:
python measure_model.py
Dataset
Portrait Segmentation (Human/Background)
- Automatic Portrait Segmentation for Image Stylization: 1800 images
- Supervisely Person: 5711 images
Set
- Python3.6.x is used in this repository.
- Clone the repository:
git clone --recursive https://github.com/AntiAegis/Human-Segmentation-PyTorch.git
cd Human-Segmentation-PyTorch
git submodule sync
git submodule update --init --recursive
- To install required packages, use pip:
workon humanseg
pip install -r requirements.txt
pip install -e models/pytorch-image-models
Training
- For training a network from scratch, for example DeepLab3+, use this command:
python train.py --config config/config_DeepLab.json --device 0
where config/config_DeepLab.json is the configuration file which contains network, dataloader, optimizer, losses, metrics, and visualization configurations.
- For resuming training the network from a checkpoint, use this command:
python train.py --config config/config_DeepLab.json --device 0 --resume path_to_checkpoint/model_best.pth
- One can open tensorboard to monitor the training progress by enabling the visualization mode in the configuration file.
Inference
There are two modes of inference: video and webcam.
python inference_video.py --watch --use_cuda --checkpoint path_to_checkpoint/model_best.pth
python inference_webcam.py --use_cuda --checkpoint path_to_checkpoint/model_best.pth
Benchmark
- Networks are trained on a combined dataset from the two mentioned datasets above. There are 6627 training and 737 testing images.
- Input size of model is set to 320.
- The CPU and GPU time is the averaged inference time of 10 runs (there are also 10 warm-up runs before measuring) with batch size 1.
- The mIoU is measured on the testing subset (737 images) from the combined dataset.
- Hardware configuration for benchmarking:
CPU: Intel(R) Core(TM) i7-7700HQ CPU @ 2.80GHz
GPU: GeForce GTX 1050 Mobile, CUDA 9.0
Model | Parameters | FLOPs | CPU time | GPU time | mIoU |
---|---|---|---|---|---|
UNet_MobileNetV2 (alpha=1.0, expansion=6) | 4.7M | 1.3G | 167ms | 17ms | 91.37% |
UNet_ResNet18 | 16.6M | 9.1G | 165ms | 21ms | 90.09% |
DeepLab3+_ResNet18 | 16.6M | 9.1G | 133ms | 28ms | 91.21% |
BiSeNet_ResNet18 | 11.9M | 4.7G | 88ms | 10ms | 87.02% |
PSPNet_ResNet18 | 12.6M | 20.7G | 235ms | 666ms | --- |
ICNet_ResNet18 | 11.6M | 2.0G | 48ms | 55ms | 86.27% |
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].