search

liyunsheng13 / BDL

MIT License
222 stars 30 forks source link

how did you set discriminator's weight? #14

Closed MyeongJin-Kim closed 5 years ago

MyeongJin-Kim commented 5 years ago

In inner loop for SSL, if N=2, segmentation network is trained 3 times in a row. When training segmentation network, how did you set the discriminator's weight? Initialize discriminator every time or use previous discriminator's weight??

Also same question for outer loop's weight.

liyunsheng13 commented 5 years ago

The weight for the discriminator is randomly initialized.

MyeongJin-Kim commented 5 years ago

Thanks for the comment!

MyeongJin-Kim commented 5 years ago

One more question!

If discriminator is randomly initialized, when train again with previous segmentation weight, mIoU drop at early stage. Did you get the same pattern?

liyunsheng13 commented 5 years ago

I don't quite understand your question. what do you mean by "train again"? If you mean training a new model with pseudo labels, I don't have overfitting problem.