Knighthy

Hi,your mask dataset URL=https://nv-adlr.github.io/publication/partialconv-inpainting .is right?

> > Hi,your mask dataset URL=https://nv-adlr.github.io/publication/partialconv-inpainting .is right? > > I think it is right ok...，sorry Whether y train yourself dataset, or.. author provide Places2, CelebA and Paris Street-View ?

I got some difficulities,my used the ulr author's [--mask_root]dataset ,but happended to some problems above. why the tensor sizes is [1,1,256,384].

> Hello, thank you for your code, > I meet this problem when i was training, how can i figure it? >  I have the same problem  if...

Nice , solve my problem.hhh

> I meet same problem. > > I changed below configuration when training pytorch model. > > ```yaml > voxel_size: [0.075, 0.1389, 0.2] > point_cloud_range: [-54.0, -100.0, -5.0, 54.0, 100.0,...

> > I meet same problem. > > I changed below configuration when training pytorch model. > > ```yaml > > voxel_size: [0.075, 0.1389, 0.2] > > point_cloud_range: [-54.0, -100.0,...

> > 使用的是bevdet最新的代码https://github.com/HuangJunJie2017/BEVDet > > 我fork的是较早版本的BEVDet官方仓库，源码部分可能有些不同。 大佬，你这份代码的mmdet3d/datasets/pipelines /loading.py 用的是官方2.1的代码，但是view_transformer.py get_mlp 用的是2.0的代码，我把它都换成2.0的这有影响吗

> 使用[https://github.com/LCH1238/BEVDet/tree/export中的export_onnx.py，权重使用https://drive.google.com/drive/folders/1jSGT0PhKOmW3fibp6fvlJ7EY6mIBVv6i路径中的bevdet-lt-d-ft-nearest.pth导出onnx，最终的img_stage_lt_d.onnx如下图所示，与作者您提供的img_stage_lt_d.onnx不一致](https://github.com/LCH1238/BEVDet/tree/export%E4%B8%AD%E7%9A%84export_onnx.py%EF%BC%8C%E6%9D%83%E9%87%8D%E4%BD%BF%E7%94%A8https://drive.google.com/drive/folders/1jSGT0PhKOmW3fibp6fvlJ7EY6mIBVv6i%E8%B7%AF%E5%BE%84%E4%B8%AD%E7%9A%84bevdet-lt-d-ft-nearest.pth%E5%AF%BC%E5%87%BAonnx%EF%BC%8C%E6%9C%80%E7%BB%88%E7%9A%84img_stage_lt_d.onnx%E5%A6%82%E4%B8%8B%E5%9B%BE%E6%89%80%E7%A4%BA%EF%BC%8C%E4%B8%8E%E4%BD%9C%E8%80%85%E6%82%A8%E6%8F%90%E4%BE%9B%E7%9A%84img_stage_lt_d.onnx%E4%B8%8D%E4%B8%80%E8%87%B4)  修改tools/export/export_onnx.py文件第115-116行 ```python rot = torch.rand([1, 6, 4, 4], dtype=torch.float, device=f'cuda:{args.gpu_id}') tran = torch.rand([1, 6, 4], dtype=torch.float, device=f'cuda:{args.gpu_id}') ```

> 只修改这个地方会报错 > > ``` > Traceback (most recent call last): > File "tools/export/export_onnx.py", line 146, in > torch.onnx.export( > File "/opt/conda/lib/python3.8/site-packages/torch/onnx/__init__.py", line 316, in export > return utils.export(model, args,...