It includes all 164K images from COCO 2017 (train 118K, val 5K, test-dev 20K, test-challenge 20K). It covers 172 classes: 80 thing classes, 91 stuff classes and 1 class 'unlabeled'. This dataset will form the basis of all upcoming challenges. COCO 2017 Stuff Segmentation Challenge: A...
cocostuff.py scripts setup_caffemodels.sh setup_cocostuff10k.sh setup_cocostuff164k.sh train.py 3 changes: 2 additions & 1 deletion 3 .gitignore Original file line numberDiff line numberDiff line change @@ -112,4 +112,5 @@ _* .style.yapf ./*.json *_v3plus.py *.js...
PyTorch implementation of DeepLab v2 (ResNet) + COCO-Stuff 10k/164k - zllrunning/deeplab-pytorch-crf
OpenMMLab Semantic Segmentation Toolbox and Benchmark. - mmsegmentation/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_coco-stuff164k-512x512.py at dev-1.x · open-mmlab/mmsegmentation