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 *.json *.json *.zip 10 changes: 5 additions ...
(+ unlabeled). This repository aims to reproduce the official score of DeepLab v2 on COCO-Stuff datasets. The model can be trained both onCOCO-Stuff 164kand the outdatedCOCO-Stuff 10k, without building the official DeepLab v2 implemented by Caffe. Trained models are providedhere. ResNet-based...
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