NS-5

No grad accumulator for a saved leaf

4

I get an error. ../torch/csrc/autograd/saved_variable.cpp":216, please report a bug to PyTorch. No grad accumulator for a saved leaf. It's thrown at mamba_ssm\ops\selective_scan_interface.py `backward(ctx, dout)` ``` (xz, conv1d_weight, conv1d_bias, x_dbl, x_proj_weight,...

No grad accumulator for a saved leaf

1

I get an error. ../torch/csrc/autograd/saved_variable.cpp":216, please report a bug to PyTorch. No grad accumulator for a saved leaf. It's thrown at mamba_ssm\ops\selective_scan_interface.py `backward(ctx, dout)` ``` (xz, conv1d_weight, conv1d_bias, x_dbl, x_proj_weight,...

win10安装mmdet3d v0.17.1报错

1

win10 按照文档步骤进行安装，所有库包的版本都跟文档中一样，最后一步安装mmdetection3d v0.17.1一直报错没有解决。 报错如下： running build_ext E:\tool_develop\anaconda3\envs\bevformer_v8\lib\site-packages\torch\utils\cpp_extension.py:305: UserWarning: Error checking compiler version for cl: [WinError 2] 系统找不到指定的文件。 warnings.warn(f'Error checking compiler version for {compiler}: {error}') building 'mmdet3d.ops.spconv.sparse_conv_ext' extension creating C:\Users\asus\AppData\Local\Temp\pip-install-j9kkp1tu\mmdet3d_7e26acf016624840bafafb0d4d4d00df\build\temp.win-amd64-cpython-38 creating...

Can you provide a small dataset for training demo? thx.

BUG: Target_col count for each category was wrong

3

After I converted df to dataset, the target_col count for each category was wrong `dataset_train = Dataset(dataset_train, col_to_stype=col_to_stype, target_col="label")` My project is a bit urgent, I hope you can tell...