onnx转换错误

[复制链接] · 发表于 2020-9-17 15:04:05

转换mobilefacenet模型，pytorch转onnx，onnx模型测试没问题
onnx转RKNN时报错：
E ValueError: Dimensions must be equal, but are 64 and 56 for 'PRelu_PRelu_2_144_1/mul' (op: 'Mul') with input shapes: [64,1,1], [1,56,56,64].

是Prelu算子有什么要求吗？需要怎么修改呢

只看该作者 · 发表于 2020-9-18 13:27:52

你好，经过调试我把PRelu [64,1,1]，改成[64]后转换报错：
E ValueError: Incompatible type conversion requested to type 'float32' for variable of type 'float64_ref'
E During handling of the above exception, another exception occurred:
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 895, in rknn.api.rknn_base.RKNNBase.build
E File "rknn/api/rknn_base.py", line 1797, in rknn.api.rknn_base.RKNNBase._quantize2
E File "rknn/base/RKNNlib/app/medusa/quantization.py", line 105, in rknn.base.RKNNlib.app.medusa.quantization.Quantization.run
E File "rknn/base/RKNNlib/app/medusa/quantization.py", line 44, in rknn.base.RKNNlib.app.medusa.quantization.Quantization._run_quantization
E File "rknn/base/RKNNlib/app/medusa/workspace.py", line 139, in rknn.base.RKNNlib.app.medusa.workspace.Workspace.run
E File "rknn/base/RKNNlib/app/medusa/workspace.py", line 109, in rknn.base.RKNNlib.app.medusa.workspace.Workspace._setup_graph
E File "rknn/base/RKNNlib/app/medusa/workspace.py", line 110, in rknn.base.RKNNlib.app.medusa.workspace.Workspace._setup_graph
E File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 274, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build
E File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 278, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build
E File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 305, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer
E File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 305, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer
E File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 305, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer
E [Previous line repeated 3 more times]
E File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 331, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer
E File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 336, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer
E File "rknn/base/RKNNlib/layer/RKNNlayer.py", line 287, in rknn.base.RKNNlib.layer.RKNNlayer.RKNNLayer.compute_tensor
E File "rknn/base/RKNNlib/layer/fullconnect.py", line 104, in rknn.base.RKNNlib.layer.fullconnect.FullConnect.compute_out_tensor
E File "/home/zengwb/anaconda3/envs/rk/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 301, in add
E "Add", x=x, y=y, name=name)
E File "/home/zengwb/anaconda3/envs/rk/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 546, in _apply_op_helper
E inferred_from[input_arg.type_attr]))
E TypeError: Input 'y' of 'Add' Op has type float64 that does not match type float32 of argument 'x'.

QQ群里问过饶洪叫我论坛提交模型debug，帮忙看看问题，急！谢谢