为什么keras2onnx.convert_keras()函数不断让我出错“'KerasTensor'对象没有属性'graph'”

我有一个经过训练的模型（我自己训练过），它是 .h5 格式，它本身可以正常工作，但我需要将其转换为 .onnx 格式以便在 Unity Engine 中部署它，我搜索了如何转换 .h5 模型到 .onnx 格式并偶然发现了 keras2onnx 库，按照一些教程我得到了这个：

!pip install git+https://github.com/microsoft/onnxconverter-common
!pip install git+https://github.com/onnx/keras-onnx

import keras
import keras2onnx
import onnx
from tensorflow.keras.models import load_model
model = load_model('/content/drive/MyDrive/Sae/TesisProgra/CNNs/ParagrapshVsDrawings/REDPropiaFinal.h5')  
onnx_model = keras2onnx.convert_keras(model, model.name)
temp_model_file = '/content/drive/MyDrive/Sae/TesisProgra/CNNs/ParagrapshVsDrawings/REDPropiaFinal.onnx'
onnx.save_model(onnx_model, temp_model_file)

问题是我不断收到错误代码：
AttributeError: 'KerasTensor' object has no attribute 'graph'，我尝试了不同的代码实现，但不断收到相同的错误，所以也许我的训练模型有问题？我真的不知道，我很迷茫，有人帮忙吗？这是我第一次处理 .onnx 格式，

如果您想在此处查看我的模型，它是一个 链接，我的模型接受过分析图像和区分具有绘图的图像与具有笔迹的图像的训练。最后，我的 CNN model.summary() 是这样的：

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input (Conv2D)               (None, 436, 308, 64)      640       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 218, 154, 64)      0         
_________________________________________________________________
conv2d (Conv2D)              (None, 216, 152, 32)      18464     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 108, 76, 32)       0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 106, 74, 16)       4624      
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 53, 37, 16)        0         
_________________________________________________________________
flatten (Flatten)            (None, 31376)             0         
_________________________________________________________________
dense (Dense)                (None, 64)                2008128   
_________________________________________________________________
dense_1 (Dense)              (None, 32)                2080      
_________________________________________________________________
dense_2 (Dense)              (None, 16)                528       
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 17        
=================================================================
Total params: 2,034,481
Trainable params: 2,034,481
Non-trainable params: 0
_________________________________________________________________

我目前正在使用 Google colaboratory 进行此代码实现，此外，我的图是使用 tensorflow 2.0 进行训练的

回答

# Install helper packages:
!pip install tf2onnx onnx onnxruntime

# Load model from .h5 and save as Saved Model:
import tensorflow as tf
model = tf.keras.models.load_model("REDPropiaFinal.h5")
tf.saved_model.save(model, "tmp_model")

# Convert in bash:
!python -m tf2onnx.convert --saved-model tmp_model --output "REDPropiaFinal.onnx"

# Get original output
noise = tf.random.uniform((1, *model.input_shape[1:]))
original_out = model.predict(noise)
print(original_out)  # [[1.]]

# Get converted output:
import onnxruntime

onnx_session = onnxruntime.InferenceSession("REDPropiaFinal.onnx")
onnx_inputs = {onnx_session.get_inputs()[0].name: noise.numpy()}
onnx_output = onnx_session.run(None, onnx_inputs)[0]
print(onnx_output)  # [[1.]]

# Assure the same:
tf.debugging.assert_near(original_out, onnx_output)