Skip to content

Human segmentation models, training/inference code, and trained weights, implemented in PyTorch

Notifications You must be signed in to change notification settings

thuyngch/Human-Segmentation-PyTorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

b15baef · Aug 22, 2020

History

90 Commits
Mar 10, 2019
Aug 15, 2019
Apr 6, 2019
Jun 15, 2019
Apr 6, 2019
Apr 6, 2019
Aug 18, 2019
Mar 19, 2019
Aug 15, 2019
Mar 19, 2019
Aug 18, 2019
Aug 18, 2019
Jun 15, 2019
May 2, 2020
Aug 18, 2019
Aug 18, 2019
Jul 20, 2019

Repository files navigation

Human-Segmentation-PyTorch

Human segmentation models, training/inference code, and trained weights, implemented in PyTorch.

Supported networks

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)

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%

Releases

No releases published

Packages

No packages published