|
运行环境:台式机上的CentOS
RKNN-TOOLKIT:1.4.0
目的:将NanoDet模型转成RKNN, 已经从PyTorch转成了ONNX
指令和输出:
(rknn) [jtma3@localhost nanodet]$ python test.py
--> config model
done
--> Loading model
/home/jtma3/Downloads/onnx-tensorflow-1.2.1/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: nanodet_1_3_320_320.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 "/home/jtma3/anaconda3/envs/rknn/lib/python3.6/site-packages/onnx/checker.py", line 86, in check_model
E C.check_model(model.SerializeToString())
E onnx.onnx_cpp2py_export.checker.ValidationError: Node () has input size 4 not in range [min=1, max=1].
E ==> Context: Bad node spec: input: "567" input: "569" input: "570" input: "568" output: "571" op_type: "Slice"
Load nanodet failed!
所以,RKNN目前是不支持slice操作码?转过其他模型也报过类似的错误,卡在了slice这里
|
|