在 OpenCV 上使用 Tensorflow 2.X 模型

Question

我必须使用带有 OpenCV 框架的 Tensorflow 2.X 模型（带有 C++ 的 v.4.X）。

为此，我需要一个.pb文件或一个.pb和一个.pbtxt文件，而不是像我拥有的​​那样的 Tensorflow 保存模型。

所以我的问题是：有没有办法将保存的模型转换为 OpenCV 可以读取的格式？比如，也许，一个caffe模型？

我尝试使用MMdnn但它给了我一个奇怪的错误：

Traceback (most recent call last):
  File "/usr/local/bin/mmconvert", line 8, in <module>
    sys.exit(_main())
  File "/usr/local/lib/python3.5/dist-packages/mmdnn/conversion/_script/convert.py", line 102, in _main
    ret = convertToIR._convert(ir_args)
  File "/usr/local/lib/python3.5/dist-packages/mmdnn/conversion/_script/convertToIR.py", line 62, in _convert
    from mmdnn.conversion.tensorflow.tensorflow_parser import TensorflowParser
  File "/usr/local/lib/python3.5/dist-packages/mmdnn/conversion/tensorflow/tensorflow_parser.py", line 15, in <module>
    from tensorflow.tools.graph_transforms import TransformGraph
ImportError: No module named 'tensorflow.tools.graph_transforms'

我想这是因为它是用 Tensorflow 1.X 开发和测试的。

---

编辑：我也有相对的 Keras 模型（现在它与 Tensorflow 2 集成），但它也与 OpenCV DNN 框架不兼容。尝试使用 MMdnn 转换它时出现此错误：

Traceback (most recent call last):
  File "/usr/local/bin/mmconvert", line 8, in <module>
    sys.exit(_main())
  File "/usr/local/lib/python3.5/dist-packages/mmdnn/conversion/_script/convert.py", line 102, in _main
    ret = convertToIR._convert(ir_args)
  File "/usr/local/lib/python3.5/dist-packages/mmdnn/conversion/_script/convertToIR.py", line 46, in _convert
    parser = Keras2Parser(model)
  File "/usr/local/lib/python3.5/dist-packages/mmdnn/conversion/keras/keras2_parser.py", line 126, in __init__
    model = self._load_model(model[0], model[1])
  File "/usr/local/lib/python3.5/dist-packages/mmdnn/conversion/keras/keras2_parser.py", line 78, in _load_model
    'DepthwiseConv2D': layers.DepthwiseConv2D})
  File "/usr/local/lib/python3.5/dist-packages/keras/engine/saving.py", line 664, in model_from_json
    return deserialize(config, custom_objects=custom_objects)
  File "/usr/local/lib/python3.5/dist-packages/keras/layers/__init__.py", line 168, in deserialize
    printable_module_name='layer')
  File "/usr/local/lib/python3.5/dist-packages/keras/utils/generic_utils.py", line 147, in deserialize_keras_object
    list(custom_objects.items())))
  File "/usr/local/lib/python3.5/dist-packages/keras/engine/network.py", line 1056, in from_config
    process_layer(layer_data)
  File "/usr/local/lib/python3.5/dist-packages/keras/engine/network.py", line 1042, in process_layer
    custom_objects=custom_objects)
  File "/usr/local/lib/python3.5/dist-packages/keras/layers/__init__.py", line 168, in deserialize
    printable_module_name='layer')
  File "/usr/local/lib/python3.5/dist-packages/keras/utils/generic_utils.py", line 149, in deserialize_keras_object
    return cls.from_config(config['config'])
  File "/usr/local/lib/python3.5/dist-packages/keras/engine/base_layer.py", line 1179, in from_config
    return cls(**config)
  File "/usr/local/lib/python3.5/dist-packages/keras/legacy/interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/keras/layers/convolutional.py", line 484, in __init__
    **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/keras/layers/convolutional.py", line 117, in __init__
    self.kernel_initializer = initializers.get(kernel_initializer)
  File "/usr/local/lib/python3.5/dist-packages/keras/initializers.py", line 515, in get
    return deserialize(identifier)
  File "/usr/local/lib/python3.5/dist-packages/keras/initializers.py", line 510, in deserialize
    printable_module_name='initializer')
  File "/usr/local/lib/python3.5/dist-packages/keras/utils/generic_utils.py", line 140, in deserialize_keras_object
    ': ' + class_name)
ValueError: Unknown initializer: GlorotUniform

---

编辑 04/2021：现在评论中提到的 ONNX 转换器与 OpenCV 4.5.1 一起正常工作（4.5.0 版在某些 ONNX 网络中存在错误）。

Answer 1

如果您有该.h5文件，则可以使用 TensorFlow 尝试此方法，而不是MMdnn使用 TensorFlow。该函数将当前会话转换为静态计算图以捕获当前状态。.pb然后您可以使用 格式编写图表tf.train.write_graph。

model = load_model('./model/keras_model.h5')您可以在冻结图表之前加载预训练模型。还有一篇博客文章提供了进一步的解释。