search

NVIDIA / semantic-segmentation

Nvidia Semantic Segmentation monorepo
BSD 3-Clause "New" or "Revised" License
1.77k stars 387 forks source link

demo.py for sdcnet #136

Open fjremnav opened 3 years ago

fjremnav commented 3 years ago

Is there a demo.py for sdcnet? Where can I download pretrained sdcnet?

Thanks,

fitsumreda commented 3 years ago

Does this work for you? https://github.com/NVIDIA/semantic-segmentation/tree/sdcnet#pre-trained-models Look at the pre-trained models for sdccityscapes and FlowNet2_

fjremnav commented 3 years ago

@fitsumreda

My understanding of sdcnet usage is to generate additional annotations and augment to cityscape datasheet. Is this correct? Does this pretrained model "pretrained_models/cityscapes_best.pth[1071MB, WideResNet38 backbone]" use scdnet augmentation in the training?

Thanks,

fitsumreda commented 3 years ago

Yes, it was trained with sdcnet augmentation.

fjremnav commented 3 years ago

@fitsumreda

Thanks for the answer. I am looking for a way, like using optical flow to improve temporal consistency of segmentation results for a video. Do you know anyone who has worked on this area?

Thanks,