exiawsh

May mmcv support the stack version for the multi-scale deformable attention?

2

**Describe the feature** The multi-scale deformable attention provided in mmcv is the batch version, could mmcv support the stack version? **Motivation** A clear and concise description of the motivation of...

How to draw the PR curve after evaluate the nuscenes dataset?

1

Hello, if I want to draw the PR curve and save the output for each class when evaluating the results, how should I do it?

What's the meaning of sample_reg_loss?

1

Hello! Thanks for the great work! I'm wondering the meaning of sample_reg_loss. Was it supervised during training?

The dataset format

11

Hello, Thank you for your great work if I generate the dataset correctly, what will be its folder placement structure? Could you give me an example?Just a screenshot is ok.

Hello, thanks for the great work, how to calculate the flops of the model. I have noticed that you report the flops of transformer based model, but I only found...

Hello, thanks for the great work! I have noticed that you report the results for single frame in the paper. But I didn't found the config or results in the...

Hello! Thanks for your great work! Is there a setup for the experiment that does not require CBGS？ Due to limited computing resources, I want to recreate Bevdet results on...

Question about the queue length during validation and testing

1

Hello! It seems that the queue_length during training is set to 4. But during validation and testing, the queue_length could handle all key frames of one scene (40 key frame),...

How to test speed on my own device?

7

Hi, thanks for the great work ! I want to test speed on my own RTX3090 with fp32. Which file do I need to run and where do I modify...

Details about the match_cost and loss weight?

1

Hello, thanks for your great work! I am trying to reproduce your paper. But I got bad results on azimuth and size. But under the supervision of Cartesian coordinate system,...