search

CSAILVision / semantic-segmentation-pytorch

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
http://sceneparsing.csail.mit.edu/
BSD 3-Clause "New" or "Revised" License
4.95k stars 1.1k forks source link

Pretrained models are not accesible #286

Open dv-ai opened 1 year ago

dv-ai commented 1 year ago

When I try to access to the page of pretrain model (http://sceneparsing.csail.mit.edu/model/pytorch/), the following error is raised: You don't have permission to access this resource.

Could you provide access to the pretrained models?

fido20160817 commented 1 year ago

same question!

KatieSaa commented 1 year ago

http://sceneparsing.csail.mit.edu/model/pytorch/ade20k-mobilenetv2dilated-c1_deepsup/decoder_epoch_20.pth http://sceneparsing.csail.mit.edu/model/pytorch/ade20k-mobilenetv2dilated-c1_deepsup/encoder_epoch_20.pth

ucasligang commented 1 year ago

same question!

zafirshi commented 1 year ago

You can run demo_test.sh in the same way as Quick Start in the readme.

The shell script contains an automatic download method of ade20k-resnet50dilated-ppm_deepsup pretrained model.

You can also follow the above method and manually change the config name to download it to the cpkt/$config path.

http://sceneparsing.csail.mit.edu/model/pytorch/ade20k-mobilenetv2dilated-c1_deepsup/decoder_epoch_20.pth http://sceneparsing.csail.mit.edu/model/pytorch/ade20k-mobilenetv2dilated-c1_deepsup/encoder_epoch_20.pth