Which model is the one that get the best performance?

[zhengying1013]

Hi,

As you have uploaded too much models, I cannot tell which one is the model with the best performance. Can you tell me which one is the best? I think it should corresponds to the one named "BCP-R5" (63.17%) in Table 6 of your paper.

Thank you very much.

[Abhijat]

Please find the information here:
https://github.com/val-iisc/sketch-parse/tree/master/exp-src

To train, we have:

For BCP-R5, run
python train_r5.py --segnetLoss --lambda1 1.0 --GTpath <train gt images path here> --IMpath <train images path here>

If you just want to evaluate with our trained models, download them from here. The one corresponding to BCP-R5 is model_r5_p50x_D1_17000.pth( deeplab_resnet_sketchParse_r5.py is the corresponding model file. You can evaluate the .pth file using eval_r5.py). Further instructions here.

[zhengying1013]

Thank you very much.