icnet

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

TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".

Keras-Semantic-Segmentation

ICNet and PSPNet-50 in Tensorflow for real-time semantic segmentation

ICNet implemented by pytorch, for real-time semantic segmentation on high-resolution images, mIOU=71.0 on cityscapes, single inference time is 19ms, FPS is 52.6.

Semantic segmentation task for ADE20k & cityscapse dataset, based on several models.

This repository contains UNet and ICNet implementations for semantic segmentation of nuclei images, from Kaggle's 2018 Data Science Bowl

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

Implementation of ICNet by chainer