Skip to content

Image segmentation project. Two architectures implemented: VGG-16 + FCN-8 module and U-Net. For FCN-8, pre-trained weights are used from SSD300. Although it is designed for object detection, its feature extractor can be reused in another task involving similar classes. Linked article explains the full project.

License

Notifications You must be signed in to change notification settings

Apiquet/Segmentation

Repository files navigation

Image segmentation project

The project is explained here

In this repository is implemented three architectures: VGG-16 + FCN-8 module, VGG-16 + FCN-4 module and U-Net.

The two models with VGG-16 use pre-trained weights from SSD300 model implemented here. Although the SSD300 is designed for object detection, its feature extractor can be reused in another task involving similar classes. The related article (link at the top of this readme) explains the implementation and compares training with and without transfer learning. It also describes how to parse raw data to train segmentation models.

  • FCN-8 architecture and some visualizations:

FCN8

Person dog

Person then dog

Dog

  • FCN-4 architecture and some visualizations:

FCN4

Person dog

Person then dog

Dog

  • U-NET architecture and a visualization: paper

U-Net

Dog-UNet

Usage

  • Training: the notebooks UNET/FCN4/8_training.ipynb show how to train a UNET / VGG-16 + FCN-4 / VGG-16 + FCN8 models.
  • Testing: the notebook infer_on_videos.ipynb shows how to infer the segmentation model VGG-16 + FCN-4 on a single image or on a video.

The script under utils/ folder allows to create the visualizations

About

Image segmentation project. Two architectures implemented: VGG-16 + FCN-8 module and U-Net. For FCN-8, pre-trained weights are used from SSD300. Although it is designed for object detection, its feature extractor can be reused in another task involving similar classes. Linked article explains the full project.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published