bev模型生成bev.onnx的问题

[weibao1001]

您好，在使用您给的export_model_to_onnx_static()当中我修改了文件不知道是不是您官网提供的bev.pth，图片是随便找的带有人体的图片，我修改了这两个路径，但是给出了以下的警告，但没有报错。

/romp/simple_romp/bev/model.py:79: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations map_coord_range_each_level = (np.array([2/64., 25/64., 3/64., 2/64.], dtype=np.float32) * centermap_size).astype(np.int) Threshold for positive center detection: 0.1 /romp/simple_romp/bev/model.py:238: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results. if len(center_preds_info_3d[0])==0: /romp/simple_romp/bev/model.py:93: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results. scale_num = len(cam3dmap_anchor) /romp/simple_romp/bev/model.py:94: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results. if len(cam_params) != 0: \lib\site-packages\torch\onnx\symbolic_opset9.py:5408: UserWarning: Exporting aten::index operator of advanced indexing in opset 12 is achieved by combination of multiple ONNX operators, including Reshape, Transpose, Concat, and Gather. If indices include negative values, the exported graph will produce incorrect results. warnings.warn(

当我打开bev.onnx查看时出现了奇怪的输出，不知道是不是我的操作有问题，还请您方便的时候给予答复，谢谢

[TitansWhale]

您好，在使用您给的export_model_to_onnx_static()当中我修改了文件不知道是不是您官网提供的bev.pth，图片是随便找的带有人体的图片，我修改了这两个路径，但是给出了以下的警告，但没有报错。

/romp/simple_romp/bev/model.py:79: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations map_coord_range_each_level = (np.array([2/64., 25/64., 3/64., 2/64.], dtype=np.float32) * centermap_size).astype(np.int) Threshold for positive center detection: 0.1 /romp/simple_romp/bev/model.py:238: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results. if len(center_preds_info_3d[0])==0: /romp/simple_romp/bev/model.py:93: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results. scale_num = len(cam3dmap_anchor) /romp/simple_romp/bev/model.py:94: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results. if len(cam_params) != 0: \lib\site-packages\torch\onnx\symbolic_opset9.py:5408: UserWarning: Exporting aten::index operator of advanced indexing in opset 12 is achieved by combination of multiple ONNX operators, including Reshape, Transpose, Concat, and Gather. If indices include negative values, the exported graph will produce incorrect results. warnings.warn(

当我打开bev.onnx查看时出现了奇怪的输出，不知道是不是我的操作有问题，还请您方便的时候给予答复，谢谢

have you found a solution?

[weibao1001]

你找到解决方案了吗？

您好，在使用您给的export_model_to_onnx_static()当中我修改了文件不知道是不是您官网提供的bev.pth，图片是随便找的带有人体的图片，我修改了这两个路径，但是给出了以下的警告，但没有报错。 /romp/simple_romp/bev/model.py:79: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations map_coord_range_each_level = (np.array([2/64., 25/64., 3/64., 2/64.], dtype=np.float32) * centermap_size).astype(np.int) Threshold for positive center detection: 0.1 /romp/simple_romp/bev/model.py:238: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results. if len(center_preds_info_3d[0])==0: /romp/simple_romp/bev/model.py:93: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results. scale_num = len(cam3dmap_anchor) /romp/simple_romp/bev/model.py:94: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results. if len(cam_params) != 0: \lib\site-packages\torch\onnx\symbolic_opset9.py:5408: UserWarning: Exporting aten::index operator of advanced indexing in opset 12 is achieved by combination of multiple ONNX operators, including Reshape, Transpose, Concat, and Gather. If indices include negative values, the exported graph will produce incorrect results. warnings.warn( 当我打开bev.onnx查看时出现了奇怪的输出，不知道是不是我的操作有问题，还请您方便的时候给予答复，谢谢

have you found a solution?

Without finding a solution, I was new to onnx