onnx.onnx_cpp2py_export.checker.ValidationError

最新推荐文章于 2024-07-24 15:02:05 发布

原创最新推荐文章于 2024-07-24 15:02:05 发布 · 6.8k 阅读

2 ·

本内容遵循CC 4.0 BY-SA版权协议

onnx 同时被 2 个专栏收录

100 篇文章

订阅专栏

mxnet

58 篇文章

订阅专栏

本文介绍了一个在使用ONNX将MXNet模型转换为ONNX格式过程中遇到的ValidationError错误及其解决方法。错误主要源于BatchNormalization操作符中存在未识别属性'spatial'，通过调整ONNX版本并未解决问题。文章提供了详细的代码示例及错误信息。

onnx.onnx_cpp2py_export.checker.ValidationError

报错代码：

    import mxnet as mx
    import numpy as np
    from mxnet.contrib import onnx as onnx_mxnet
    import logging

    logging.basicConfig(level=logging.INFO)
    from onnx import checker
    import onnx

    syms = './mxnet/new_model-symbol.json'
    params = './mxnet/new_model-0000.params'

    input_shape = (1, 3, 112, 112)

    onnx_file = './mnist.onnx'

    # Invoke export model API. It returns path of the converted onnx model
    converted_model_path = onnx_mxnet.export_model(syms, params, [input_shape], np.float32, onnx_file)

    # Load onnx model
    model_proto = onnx.load_model(converted_model_path)

网上解决方法：pip install onnx==1.5.0

换完后，报更多的错：

onnx.onnx_cpp2py_export.checker.ValidationError: Unrecognized attribute: spatial for operator BatchNormalization
==> Context: Bad node spec: input: "conv_1_conv2d" input: "conv_1_batchnorm_gamma" input: "conv_1_batchnorm_beta" input: "conv_1_batchnorm_moving_mean" input: "conv_1_batchnorm_moving_var" output: "conv_1_batchnorm" name: "conv_1_batchnorm" op_type: "BatchNormalization" attribute { name: "epsilon" f: 0.001 type: FLOAT } attribute { name: "momentum" f: 0.9 type: FLOAT } attribute { name: "spatial" i: 0 type: INT }