BiSeNet based on pytorch

Download CamVid dataset from Semantic-Segmentation-Suite
Thanks GeorgeSeif for his great job!

Download epoch_295.pth in GoogleDrive and put it in ./checkpoints
The net structure has been modified, so the pretrained model does not match the current model.

python demo.py

Original	GT	Predict

python train.py

Use tensorboard to see the real-time loss and accuracy

python test.py

Cropped and Resized means two image processing method to make the input image size fixed, it seems like Cropped input images get better result. I guess it's because cropped masks keep the original ground truth information while resized loss it.

• Finish real-time segmentation with camera or pre-load video
• Update pixel accuracy calculation algorithm

• Semantic-Segmentation-Suite
• BiSeNet-paper