Segmentation models with pretrained backbones. PyTorch.

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Efficient model for semantic segmentation on edge devices, specifically targeting the analysis of disaster scenes from images captured by unmanned aerial vehicles (UAVs).

SSSegmentation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch.

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.

Implementation of the PSPNet machine learning model, used for various sport pitches lines semantic segmentation

PyTorch Implementation of Semantic Segmentation CNNs: This repository features key architectures like UNet, DeepLabv3+, SegNet, FCN, and PSPNet. It's crafted to provide a solid foundation for Semantic Segmentation tasks using PyTorch.

I am aiming to write different Semantic Segmentation models from scratch with different pretrained backbones.

A semantic segmentation of Aerial Imagery from Hurricane Harvey using Deep Learning algorithms

A Python Library for High-Level Semantic Segmentation Models based on TensorFlow and Keras with pretrained backbones.

Satellite Image Classification using semantic segmentation methods in deep learning

deep learning : segmentation d'images

1D and 2D Segmentation Models with options such as Deep Supervision, Guided Attention, BiConvLSTM, Autoencoder, etc.

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

Segmentation models with pretrained backbones. PyTorch. for Google Colab cell motility segmentation example.

COCO-Stuff Benchmark

Here i implemented some segmentation models. There are a few istances of FCN that uses transposed conv vs upsampling+conv as decoder layers, an implementation of UNet and an implementation of PSPNet. There is also an implementation of ResNet50

Spatial and Semantic Segementation

Providing a pipeline for training a segmentation model with different architectures