KUMA TYANN

HI @suzhenghang Since this code used "sbd_voc2012train_image2category.txt" and "SBD" data. I can not find where to download it and how to transform my image data to “SBD” format. Could you...

Same as you guys. I reduced classes to 2, and make predication visualized in epoch, but no improvement happened.

@hellochick, Thanks. Maybe I forgot adding this parameter.

I trained model by Cityscapes dataset. During training, I reduced lr from 1e-3 to 1e-5, but loss value was always high(2.5, loss of two classification data can reduce to 2.1)...

I classified car, bus and truck to one class and regard others as second class. By training on the gamma & beta variable after some epoches, the loss can reduce....

@psuff I get much better result than before. The train error becomes lower, but eva error is still not very low. Anyhow I can accept it. Last time, I used...