BiSeNet
BiSeNet based on pytorch 0.4.1 and python 3.6
Dataset
Download CamVid dataset from Semantic-Segmentation-Suite
Thanks GeorgeSeif for his great job!
Pretrained model
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.
Demo
python demo.py
Result
| Original | GT | Predict |
|---|---|---|
 |
 |
 |
Train
python train.py
Use tensorboard to see the real-time loss and accuracy
loss on train
pixel precision on val
Test
python test.py
Result
| Method | Cropped | Resized |
|---|---|---|
| Pixel Accuracy | 94.1 | 93.2 |
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.
Future work
- Finish real-time segmentation with camera or pre-load video
- Update pixel accuracy calculation algorithm