The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

DeepLab v3+ model in PyTorch. Support different backbones.

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

Train the HRNet model on ImageNet

Tutorials, assignments, and competitions for MIT Deep Learning related courses.

OpenCV fisheye undistortion example

gets equirectangular images from Google StreetView

download panoramas and metadata from Street View, Look Around, and more

Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes