search

rosinality / ocr-pytorch

Object-Contextual Representations for Semantic Segmentation in PyTorch
MIT License
63 stars 14 forks source link

trained model on cityscapes #4

Closed krishnakanthnakka closed 4 years ago

krishnakanthnakka commented 4 years ago

Do you mind sharing the trained model on cityscapes?

rosinality commented 4 years ago

Hmm I haven't tried this model on cityscapes.

krishnakanthnakka commented 4 years ago

do you have any trained model on other datasets? I want to try some experiments to understand effects of contextual dependencies in OCRNet.

rosinality commented 4 years ago

I have checkpoints trained on ADE20K: https://drive.google.com/open?id=1xRrAB8dMTL-S7aYK5UrEoyWYWn2B_uhg

krishnakanthnakka commented 4 years ago

Thank you:)