sharat29ag / cdal Goto Github PK

Hi~
Thanks for your great work. The paper was very good, and I read it well.
I want to know how to make a training data file such as '000007.npy'.
can i get the training data making source?

Thank you so much for sharing the code. Paper and work are really interesting. For the image classification scenario and also on the second set of features from your repo, the "reward" goes to "nan" after the first epoch and it throws assertion failure. Can you advise me on the parameters or settings for how to overcome this? Thank you in advance! (For image classification we pass the features array: number_of_features X batch << of unlabelled>>? For the segmentation there are 19/20)

Thanks for your great work.
I research at active learning too, and i did some work about detection on VOC using SSD.
I want to compare the results with data in your paper. But i cannot find the exact mAP data in your paper and supplements.
Could you provide the exact mAP numbers to this email? [email protected]
Thanks for your great work again.

Hi! Thank your for your code ! Do you have the code for CDAL_CS?

Hello, thank you for this nice work.
Can you tell me which DRN architecture is used for semantic segmentation on Cityscapes? I fail to find one matching the reported performance (62.95 mIoU on full data) in the DRN repo.

Hi~ @sharat29ag
Thanks for your great work.
Could you share the selected Pascal VOC subsets by CDAL? I hope to reproduce the detection results of active learning.