niranyingluofen comments

Results 2 comments of


                                            niranyingluofen

import spconv.core_cc as _ext ImportError: arg(): could not convert default argument 'workspace: tv::Tensor' in method '<class 'spconv.core_cc.csrc.sparse.convops.gemmops.GemmTunerSimple'>.run_with_tuned_result' into a Python object (type not registered yet?

I have another question： Traceback (most recent call last): File "tools/test.py", line 12, in from mmdet3d.apis import single_gpu_test File "/media/wxr/work/work/SST_maybe_ok/SST/mmdet3d/apis/__init__.py", line 1, in from .inference import (convert_SyncBN, inference_detector, File "/media/wxr/work/work/SST_maybe_ok/SST/mmdet3d/apis/inference.py",...

idx 的范围超出通道数目范围

![Screenshot from 2024-07-03 10-12-21](https://github.com/VainF/Torch-Pruning/assets/31267220/2fb166d8-3adc-4af4-95ef-e7babc3037e9) 这是出错部分的模型的截图， ![image](https://github.com/VainF/Torch-Pruning/assets/31267220/462d7cd5-21ee-4e41-8368-2616fbb197d4) 我查看了一下出错层的整个group发现在第一个concat那里就有问题，这个concat应该是64+3=67也就是[0,64,67],但是在group05中却显示ConcatOp_119[0,64]