onnx转rknn出错

[复制链接] · 发表于 2020-10-9 17:24:33

--> Loading model
D:\Software\Python36\lib\site-packages\onnx_tf\common\__init__.py:87: UserWarning: FrontendHandler.get_outputs_names is deprecated. It will be removed in future release.. Use node.outputs instead.
warnings.warn(message)
E Catch exception when loading onnx model: keras_swa.onnx!
E Traceback (most recent call last):
E File "rknn\api\rknn_base.py", line 556, in rknn.api.rknn_base.RKNNBase.load_onnx
E File "rknn\base\RKNNlib\converter\convert_onnx.py", line 497, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx.__init__
E File "rknn\base\RKNNlib\converter\convert_onnx.py", line 500, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx.__init__
E File "D:\Software\Python36\lib\site-packages\onnx\checker.py", line 86, in check_model
E C.check_model(model.SerializeToString())
E onnx.onnx_cpp2py_export.checker.ValidationError: Your model ir_version is higher than the checker's.
Load onnx_model failed!
这个问题咋解决？

Load onnx_model failed!
W Not match tensor Upsample_514

ut0
E Try match Upsample_514

ut0 failed, catch exception!
W ----------------Warning(1)----------------
E Catch exception when loading onnx model: yolov5l.onnx!
E Traceback (most recent call last):
E File "rknn\base\RKNNlib\converter\convert_onnx.py", line 1130, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx.match_paragraph_and_param
E File "rknn\base\RKNNlib\converter\convert_onnx.py", line 1039, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx._onnx_push_ready_tensor
E TypeError: 'NoneType' object is not iterable
E During handling of the above exception, another exception occurred:
E Traceback (most recent call last):
E File "rknn\api\rknn_base.py", line 559, in rknn.api.rknn_base.RKNNBase.load_onnx
E File "rknn\base\RKNNlib\converter\convert_onnx.py", line 1136, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx.match_paragraph_and_param
E File "rknn\api\rknn_log.py", line 312, in rknn.api.rknn_log.RKNNLog.e
E ValueError: Try match Upsample_514

ut0 failed, catch exception!
还有这个，求大佬帮忙看看

只看该作者 · 发表于 2020-10-10 08:29:18

Try match Upsample_514 u t0 failed, catch exception!

就是说这个op不支持。你可以加入本站置顶帖qq群交流下

只看该作者 · 发表于 2020-10-10 09:06:42

jefferyzhang 发表于 2020-10-10 08:29
Try match Upsample_514 u t0 failed, catch exception!

就是说这个op不支持。你可以加入本站置顶帖qq群交 ...

--> Loading model
D:\Software\Python36\lib\site-packages\onnx_tf\common\__init__.py:87: UserWarning: FrontendHandler.get_outputs_names is deprecated. It will be removed in future release.. Use node.outputs instead.
warnings.warn(message)
E Catch exception when loading onnx model: keras_swa.onnx!
E Traceback (most recent call last):
E File "rknn\api\rknn_base.py", line 556, in rknn.api.rknn_base.RKNNBase.load_onnx
E File "rknn\base\RKNNlib\converter\convert_onnx.py", line 497, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx.__init__
E File "rknn\base\RKNNlib\converter\convert_onnx.py", line 500, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx.__init__
E File "D:\Software\Python36\lib\site-packages\onnx\checker.py", line 86, in check_model
E C.check_model(model.SerializeToString())
E onnx.onnx_cpp2py_export.checker.ValidationError: Your model ir_version is higher than the checker's.
Load onnx_model failed!
在请问一下，这个问题咋解决？

只看该作者 · 发表于 2020-10-10 09:12:23

zhw 发表于 2020-10-10 09:06
--> Loading model
D:\Software\Python36\lib\site-packages\onnx_tf\common\__init__.py:87: UserWarni ...

onnx、tf版本和rknntoolkit文档里对下，是不是太高了

只看该作者 · 发表于 2020-10-10 09:16:55

jefferyzhang 发表于 2020-10-10 09:12
onnx、tf版本和rknntoolkit文档里对下，是不是太高了

好的，感谢