使用论文checkpoint预训练模型（Downloading: "https://dl.fbaipublicfiles.com/detr/detr-r50-e632da11.pth" ）；
并通过torch.onnx导出onnx模型；
torch.onnx.export(model, img, 'detr.onnx', export_params=True, input_names=['input'], output_names=['output'])
在ubuntu上转换模型；
$ atc --model=detr.onnx --framework=5 --output=detr.om --soc_version=Ascend310B4
以下为报错
请问是什么问题呢？
参考连接：
https://colab.research.google.com/github/facebookresearch/detr/blob/colab/notebooks/detr_attention.ipynb#scrollTo=V1OPEeVOYTEV
点赞
收藏
回复
分享
举报
使用论文checkpoint预训练模型（Downloading: "https://dl.fbaipublicfiles.com/detr/detr-r50-e632da11.pth" ）；
并通过torch.onnx导出onnx模型；
torch.onnx.export(model, img, 'detr.onnx', export_params=True, input_names=['input'], output_names=['output'])
在ubuntu上转换模型；
$ atc --model=detr.onnx --framework=5 --output=detr.om --soc_version=Ascend310B4
以下为报错
ATC run failed, Please check the detail log, Try 'atc --help' for more information E10042: GenerateOfflineModel execute failed. TraceBack (most recent call last): op[/Concat], the input shape dims should be equal except merge axis,shapes:[[1, ], [1, 1, ], ]axis:0[FUNC:ConcatInferShapeCommon][FILE:split_combination_ops.cc][LINE:892] Call InferShapeAndType for node:/Concat(ConcatD) failed[FUNC:Infer][FILE:infershape_pass.cc][LINE:119] process pass InferShapePass on node:/Concat failed, ret:4294967295[FUNC:RunPassesOnNode][FILE:base_pass.cc][LINE:571] build graph failed, graph id:0, ret:1343242270[FUNC:BuildModelWithGraphId][FILE:ge_generator.cc][LINE:1615] GenerateOfflineModel execute failed.请问是什么问题呢？
参考连接：
https://colab.research.google.com/github/facebookresearch/detr/blob/colab/notebooks/detr_attention.ipynb#scrollTo=V1OPEeVOYTEV