yuhua

[Bug] I can't run DETR and deformable DETR

3

### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmdetection/issues) and [Discussions](https://github.com/open-mmlab/mmdetection/discussions) but cannot get the expected help. - [X] I have read the [FAQ documentation](https://mmdetection.readthedocs.io/en/latest/faq.html) but cannot get the expected help....

File "/root/FastSAM/fastsam/utils.py", line 17, in adjust_bboxes_to_image_border boxes[:, 0] = torch.where(boxes[:, 0] < threshold, 0, boxes[:, 0]) # x1 RuntimeError: expected scalar type long int but found float

在使用cascadercnn+swin transformer 加载预训练权重的时候，发生以下错误 OSError: CascadeRCNN: /checkpoints/swin_tiny_patch4_window7_224.pth is not a checkpoint file

Dimension error

2

encoder_dim = encoder_out.size(3) Dimension out of range (expected to be in range of [-2, 1], but got 3)

I noticed that there is DETR+PVTv1, although its AP value is not satisfactory. Why is there no implementation of DETR+PVTv2? Is it ineffective or just not provided yet.

教师助理策略

1

尊敬的博士，您好！ 请问如果想实现教师助理策略进行蒸馏，A teach B，B teach C，我该怎么实现？ 直接分两步蒸馏就可以完成吗，还是说要进行其他的处理？

I hope to train other data sets besides coco data sets, such as tinyperson and aitod. Can you give me some advices on how to modify the code?

boolean index did not match indexed array along dimension 0; dimension is 428 but corresponding boolean dimension is 427

1

boolean index did not match indexed array along dimension 0; dimension is 428 but corresponding boolean dimension is 427

What should I do if my pkl contains a large number of images, for example, the COCO2017 verification set contains 4952 images, and the runtime displays "killed"?

DOTAv2.0训练显存不足

1

我也是3090单卡24GB，我训练DOTAv2.0使用跟您相同的配置时显存不足，发现要调小img_scale才可以，请问调小这个会显著影响性能吗？