lafite-yu/mttrans-opensource

mttrans-opensource's Issues

Some questions about the code

ReadMe part

Can you improve your ReadMe part?

code release

Could you open soure the whole code project? Appreciate it !!!

the level in Foggy Cityscapes

In the Foggy Cityscapes dataset, the evaluation methods are: (1) use the data of three foggy levels（0.005,0.01,0.02） together as the training set and verification set; (2) use the data set of Foggy level=0.02 as the training set and verification set,

Which dataset do you use?

Some questions about the code implementation

1.In the Pretraining Stage
It is said that you only use the labeled source data in the pretraining stage in your published paper. However, I use the same strategy and found that the model can not produce reliable pseudo labels. Given that you conduct adversarial training on your network, why don't you use the unlabel target data for adversarial training during the pretraining stage?
2.In the Joint-training Stage
I wonder how do you set the arg 'pseudo_label_policy'. When I set the arg to 'by_consistency', it seems the model didn't train well. Do you set the arg to 'traditional'? If so, how do you choose the valuable pseudo labels? By the module PostProcess and a threshold?
Wish all the best, looking forward to your reply.

Questions on momentum updator

If you use the default values of momentum=0.999, interval=1, warm_up=100,
momentum = min(self.momentum, 1 - (1 + self.warm_up) / (self.curr_step + 1 + self.warm_up)) gets the value of self.momentum when curr_step become 100900, and this much step seems to be too much considering the size of the dataset and the batch size.
Can i get some tips on getting the mAP value of 35.843, where only mean teacher and shared QE is used?