Results of training with cityscapes about icnet-tensorflow HOT 4 CLOSED

Hey @manuel-88 , I have not tried to train on the cityscapes dataset from scratch yet. But I think it might be reachable. Did you try to train with --random-scale and --random-mirror? Data augmentation would be very helpful. Also, you need to set --filter-scale=2 to train on non-pruned model.

from icnet-tensorflow.

Yes, I used data augmentation and I also trained with filter scale 2 but the losses are after 60000 iterations 1/3 higher than on the unpruned model trained over the same iterations. That's strange for me because I thought more weights should give better results?
Is it possible that they used for the Cityscape ICNet Model a pretrained PSPNet?

from icnet-tensorflow.

@manuel-88, the non-pruned model would converge much slowly since there are more parameters need to train.
Yes, there is a way to use a pretrained PSPNet weights on ICNet model. I used their pretrained weights of PSPNet50 trained on ADE20k dataset, and keep training for the sub network of ICNet, thus get a good results!

from icnet-tensorflow.

ok thank you. I will try it

from icnet-tensorflow.