Training results on ImageNet and Cityscapes

[Asthestarsfalll]

I trained the lpsnet-m on ImageNet 1k for 100 epoch with batch size 1024.The detials are as follows:
Optimizer:

Data augments:

Eval dataset:

result:

Then I use the pre-trained model to train a lpsnet-m on cityscapes for 180k iterations with batch size 16. The detials are as follows:
Loss function:

lr_scheduler:

Optimizer:

Data augments:

Eval dataset:

Result:

[Asthestarsfalll]

Could you please tell me more details about training settings?
And did you finetune model after fusing CONV and BN?