Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

HistoSeg is an Encoder-Decoder DCNN which utilizes the novel Quick Attention Modules and Multi Loss function to generate segmentation masks from histopathological images with greater accuracy. This repo contains the code to Test and Train the HistoSeg

Base on tensorrt version 8.2.4, compare inference speed for different tensorrt api.

A DeepLab V3+ Model with choice of Encoder for Binary Segmentation. Implemented with Tensorflow.

Undergraduate Thesis : an improved Deeplabv3+ algorithm

Point cloud painting with semantic labels

DeepLab v3+ model in PyTorch. Support different backbones.

Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)

Image segmentation implemented using pytorch on a COCO format Dataset of Ingredients with various models including U-NET, U-NET++, SegNet and DeepLabV3+

Semantic segmentation with railsem19 conducted in advance to carry out detecting railway-related objects performed by the KRRI.

A DeepLab V3+ Model with ResNet 50 Encoder to perform Binary Segmentation Tasks. Implemented with PyTorch.

A guide to use MMSegmentation to develop and benchmark different models on custom dataset.

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.

Run inference on binary (2 classes only) Deeplab model cropping large images in a sliding window approach.

An implementation of Deeplabv3plus in TensorFlow2 for semantic land cover segmentation

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

Semantic Segmentation for Urban Scene understanding - Cityscapes dataset

In this project, I developed and trained a model that uses the Deep Lab V3 Plus architecture for image segmentation — trained particularly on human figures (faced, bodies, et cetera). The model as well as the code to run the model has been provided.

Enhanced Image Segmentation with Iterative Image Inpainting

Dockerized Semantic Image Segmentation service using Tensorflow, Keras, and DeepLabv3+