Pengguang He

ImportError: cannot import name 'Di1stributedDataParallel' from 'apex.parallel'

2

The paltform is window10, and there is only one GPU=RTX GeForce 3080 pytorch version==1.7.1, tensorboard version ==1.15.0, apex version==0.1 Q: Every time when i tried to train with the command...

运行mmdetection image_demo.py时报错 unknown argument {'texts', 'custom_entities'} for `preprocess`, `forward`, `visualize` and `postprocess`

8

运行mmdetection image_demo.py 时报错 unknown argument {'texts', 'custom_entities'} for `preprocess`, `forward`, `visualize` and `postprocess` 提前下载好了配置文件和权重文件 运行命令|：python image_demo.py demo.jpg rtmdet_tiny_8xb32-300e_coco.py --weights rtmdet_tiny_8xb32-300e_coco_20220902_112414-78e30dcc.pth --show --device cpu   不知道问题出在哪，请教各位大佬！感谢！

[Bug] RuntimeError: Trying to create tensor with negative dimension -512: [-512]

1

### Describe the bug A clear and concise description of what the bug is. 当我在运行剪枝任务，group fisher时，遇到了该错误，无法解决 ### To Reproduce The command you executed. ```shell python .\tools\train.py .\configs\pruning\base\group_fisher\group_fisher_prune_feces.py ``` ### Post...

When I ran the script pruning/get_channel_units.py, I got this error: TypeError: expected Tensor as element 0 in argument 0, but got tuple.

4

### Describe the bug A clear and concise description of what the bug is. When I ran the script pruning/get_channel_units.py, I got this error: TypeError: expected Tensor as element 0...

What should I do to prune my own segmentation model with my own datasets?

2

Could you please give us an example how to prune own segmentation model from scratch? Thank you so much.

KeyError: "class `IterBasedTrainLoop` in mmengine/runner/loops.py: 'ZihaoDataset is not in the dataset registry. Please check whether the value of `ZihaoDataset` is correct or it was registered as expected. More details can...

AttributeError: 'SegDataSample' object has no attribute 'gt_edge_map'

3

Thanks for your error report and we appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. The bug has not been...