Failed to convert .pth model to .onnx

[missu123]

Thank you for this great work! I used the bevdet-export repo to convert 'bevdet-lt-d-ft-nearest.pth' or 'bevdet-r50-4dlongterm-depth-cbgs.pth' to onnx format, but got an error as follow:

"./BEVDet-export/mmdet3d/models/detectors/trt_model.py", line 67, in forward
x, mlp_bn, con_se, depth_se = self.img_view_transformer.depth_net(r, mlp_input)
ValueError: not enough values to unpack (expected 4, got 2)

could you help me to solve the problem or give me some advices?

[upupdd]

I encountered the same problem, do you know how to solve it now @missu123 @LCH1238

[upupdd]

I am using your code, but the environment is configured according to BEVDet dev3.0. Is the problem here? @LCH1238

[lyxbyr]

I encountered the same problem, do you know how to solve it now @missu123 @LCH1238

[lyxbyr]

I am using your code, but the environment is configured according to BEVDet dev3.0. Is the problem here? @LCH1238

has solved it ?

[vilon888]

大概率是环境问题，确认环境正常吗？

[lyxbyr]

确认是正常的

…

---- 回复的原邮件 ---- | 发件人 | ***@***.***> | | 日期 | 2024年04月26日 19:37 | | 收件人 | ***@***.***> | | 抄送至 | ***@***.***>***@***.***> | | 主题 | Re: [LCH1238/bevdet-tensorrt-cpp] Failed to convert .pth model to .onnx (Issue #25) | 大概率是环境问题，确认环境正常吗？ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***>

[persuelx]

@LCH1238 @missu123 你好请问这个问题解决了嘛？我是按照博主的环境配置的，只有torch，cuda版本有点区别。还有在执行dockerfile的时候出现了 => ERROR [internal] load metadata for nvcr.io/nvidia/tensorrt:22.07-py3 请问这个错误是什么原因呢