harrylin

 Wonderful work! I have a question about the computation of quality focal loss. I notice the negative part of the quality focal loss is computed via the whole indices...

As mentioned above.

Can dla be used？

1

I run dla be backbone, but model do not have load_pretrained_model function!

 I set the number of GPUs to 1, and then the predicted quality values of iou all become 0, making the training unable to proceed normally. Whether it can...

I use CSPDarknet as the backbone of my detection on mmdetection, but the inference time of CSPDarknet is slower than Darknet when batchsize is 1. However, when batchsize increases 8...

Question about how to get the OW-DETR's results under the evaluation of this paper

3

Wonderful job! I notice you evaluate the performance of OW-DETR under the evaluation of this paper. I want to know how can I get the results.

Why Panoptic-FlashOcc can be faster so much than FlashOcc?

3

Great work! It appears that Panoptic-FlashOcc is built on FlashOcc with an additional centerness branch. Why is Panoptic-FlashOcc significantly faster than FlashOcc?