About performance of PSPNet-ResNet50

[dontLoveBugs]

Hi, I use your code to train PSPNet-ResNet50 in ade dataset and my result is:

Method	backbone	Mean IoU	Accuracy
PSPNet	resnet50v1c	38.98%	78.52%

The result is worse than yours. My environment is pytorch 1.0, cuda 10.

[yu-changqian]

Could you give me more details? What's the performance results with this checkpoint?

[dontLoveBugs]

I have tested the checkpoint and it has the same checkpoint as you shows. However, when I train the model from scratch，all my trained results are worse than yours. At fact, I has changed your code in order to read datasets without the train/val.txt files and added tensorboard to visulize training process. But I think these changes should not make a great difference. This is my changed code.

[yu-changqian]

Maybe you can use the lr=2e-2. I will also test the setting with the distributed-parallel api if I have the free machines.

[dontLoveBugs]

At fact, I test various parameters combinations, such as lr 0.1 to 0.2, weght_decay 0.0001 to 0.0005, with or without using apex api.