Deep Feature Flow for Video Semantic Segmentation

Based on Deeplab V2

1. Setup environment

If you want to try DFF, you should download cityscapes video data and put it into data/cityscapes_video

Pretrained Model

Download pretrained resnet model flow net from Onedrive, and put the model into mode/pretrained_model/


3. Train and Test

Training Deeplab V2

python ./experiments/deeplab/ --cfg ./experiments/deeplab/cfgs/deeplab_resnet_v1_101_cityscapes_segmentation_base.yaml

Training Deeplab V2 Deformable

python ./experiments/deeplab/ --cfg ./experiments/deeplab/cfgs/deeplab_resnet_v1_101_cityscapes_segmentation_dcn.yaml

Training DFF Deeplab V2

python ./experiments/deeplab_dff/ --cfg ./experiments/deeplab_dff/cfgs/deeplab_resnet_v1_101_cityscapes_segmentation_video.yaml

4. Performance


5. TODO List

7. Acknowledgement

Thanks for the official deep featuere flow implementation and deeplab implementation from MSRACVER