GroupViT

GroupViT copied to clipboard

why not softmax?

1

Hi, Thanks for the great work. Why do you have to use onehot or gumbel softmax. why don't you use softmax?

Davidleeeeee

command

1

sed -i '1s/^/caption\turl\n/' gcc3m.tsv How to write this command under the Windows system

scm-later

single GPU

1

Hello, can the model be trained on a single GPU

scm-later

Unstable results

9

Hi, thanks for your contribution! I've re-run the model twice with GCC+RedCaps. For the first time, I got 51.9 on ImageNet and 11.6 on COCO, while for the second time,...

CuthbertCai

zero shot on coco

1

Hello! it's a great work. I have a question about zero-shot segmentation. Are we just change [cfg: segmentation/configs/_base_/datasets/pascal_voc12.py](https://github.com/NVlabs/GroupViT/blob/main/configs/default.yml#L90) to "cfg: segmentation/configs/_base_/datasets/coco.py" for coco segmentation?

liuxingbin

About initialization and visualization of group tokens

2

Hi, @xvjiarui @shalinidemello Thank you for presenting this good work. I have some questions about the group tokens. It seems that group_token is set as None for initialization in line...

o0t1ng0o

As the training progresses, the memory required increases

6

Hi, thanks for your great work. In the process of training, I found that the memory usage gradually increased until it was out of memory. There are 252G memory in...

QianyiLiu22

IoU for each category in PASCAL VOC

6

Thanks a lot for your contribution! Do you have IoU for each category for PASCAL VOC dataset? This would help understand how your model performs for each category and sometimes...

zadaianchuk

Non parametric grouping

1

Hi, Can you please provide more details as how you do the non-parametric grouping on CLIP's features (obtained from ViT encoder)?

roysubhankar

Hard assignment

1

Dear authors, Thanks for sharing this nice work. Are the training and testing in classification task in hard assignment style, while the inference in segmentation in soft assignment?

dingjiansw101