JoyHuYY1412

> Hi, would you mind trying with the most recent version of tensorflow? We didn't find any issue running the code with the most recent version. Hi thank you for...

> Would you mind providing the dataset configuration? Hi, I have a similar problem when I evaluate two Cityscapes subsets. Since I want to use two eval hooks, I refer...

> Hello, > I found the calculation of the adaptive weight of less-forget constraint different from the description in the paper. Did I misunderstand this part or miss some details?...

> Dear author, > > Thank you for your excellent work! > > I am a little curious about the pretrained model, it is trained on the entire ImageNet-21k dataset,...

> The last indice only contains one group of images in the dataset. However, each dataset usually contain two groups( `wh`). Thank you for your help! I am not so...

> Yes, it works just like your description. Thanks!

> Yes, it works just like your description. Hi sorry to bother you again, but I have a few more questions and your help is appreciated. After using ordinary augmentation...

> See here. > > https://github.com/microsoft/SoftTeacher/blob/bef9a256e5c920723280146fc66b82629b3ee9d4/ssod/datasets/builder.py#L161 > > > It will flatten the nested list to a one dimension list like `[a,[b,c]]->[a,b,c]`. Thank you so much!

> We try to get the performance using resnet101 in your paper. But the final performance is a little worse than the reported result. > > I wonder is there...

I give some example: > > {'counts': [20939, 13, 289, 18, > 12, 1, 271, 35, 7, 12, 248, 56, 245, 59, 242, 62, 218, 1, 19, 65, 217, 2,...