Jian Ding

Question about using or-resnet for original --> rot experiments

3

I use the network defined in the demo.py, it is ok to reproduce the similar results for original --> rot experiments on mnist. But when I changed to or-resnet, it...

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?

The meaning of pre_assign_attn

5

Thank you for sharing such a nice work. I have some questions. (1) What is the meaning of self.pre_assign_attn? Has it been described in the paper? https://github.com/NVlabs/GroupViT/blob/b4ef51b8ae997f4741811025ac2290df3423a27a/models/group_vit.py#L284 (2) Does self.assign...

I notice that you comment the "relu_cccp6".If I recomment the layer "relu_cccp6", the loss will always be 10 after every iteration,why?

https://github.com/zengarden/light_head_rcnn/blob/790f94e4e1481fbc403b101a763d4a9df56ee32a/experiments/lizeming/light_head_rcnn.ori_res101.coco.ps_roialign/network_desp.py#L211 Thank you for sharing the code. And I have a question. In the description of the paper, you only use 4 channels for bounding box regression. But it seems...

Failed to connect error

7

Dear Authors, Thanks for sharing this great work. When I run `python run.py --path_to_vm Ubuntu/Ubuntu.vmx --headless --observation_type screenshot --model gemini-pro-vision --result_dir ./results ` I have the following errors: ` [2024-04-17...

Dear authors, Thanks for sharing your great work. I want to know how to visualize the regions as shown in Fig.6, and Fig 8. Can you release the code? Thanks

Evaluation on machine without sudo

16

Dear Authors, Thanks for sharing code for this excellent work. I tried to use "pt_eval_ckpt.bash" for the evaluation. But I did not have the sudo. How can I install all...

Dear Authors, Thanks for sharing this great work. I want to know how to count the success rate, and Error breakdown of components as shown in the paper. Best, Jian...

https://github.com/sooftware/attentions/blob/b1dd65be8f12fbe19525bc4ae0dbbc14975778a7/attentions.py#L286 It seems the mask is not correct. Since there is a permute of query, key, and value. The mask should also has a permute.