JoyHuYY1412

TypeError: int() argument must be a string, a bytes-like object or a number, not 'Tensor'

2

Hi, I got some error messages: ``` /crest/third_party/rand_augment.py:80 _posterize_level_to_arg return (int((level / MAX_LEVEL) * 4), ) ``` Is it something with the version of TensorFlow? My version is 2.4.0.

The dataset link is not valid now, could you give a new link? Thanks

Hi, thank you for your work. I have a question about the CuTMIx. When setting the batch size to 16 for Cityscapes as in your original paper, since using 8GPUs...

Question About thr Sampler Indices

7

Hi thank you for your code. I am reading your semi_sampler.py and find it a little bit confusing. https://github.com/microsoft/SoftTeacher/blob/bef9a256e5c920723280146fc66b82629b3ee9d4/ssod/datasets/samplers/semi_sampler.py#L170 Why do you need to concatenate all the indices? I think...

About label['roidb']['segmes']

7

HI, for coco dataset, when I print label['roidb']['segmes'] in resnet_upsnet.py, I found sometimes the last segmentation is not polygon format, which is of list format, but they look like RLE...

about the loss

2

Thank you for your work. I am not very familiar with MATLAB coding, but according to your paper, I think the loss you used for instance segmentation is: the margin...

could you share the demo of SETR?

1

The demo in your repo is written for pspnet, so could you share the demo for SETR?

Do they share the same head, but only changes the input proposals?

Could you please give the instructions on the processing of mini-imagenet dataset?

I tried to use your roi_pooling code as a layer in my model. But every time it iterates increasing the memory, do you have any idea how to fix this?