7

如何找到 onnx 模型的输入大小？我最终想从 python 编写脚本。

使用 tensorflow，我可以恢复图形定义，从中找到输入候选节点，然后获取它们的大小。我可以用 ONNX（甚至更简单）做类似的事情吗？

谢谢

4

2 回答 2

15

是的，只要输入模型有信息。请注意，ONNX 模型的输入可能具有未知等级，或者具有固定（如 100）或符号（如“N”）或完全未知的维度的已知等级。您可以按如下方式访问：

import onnx

model = onnx.load(r"model.onnx")

# The model is represented as a protobuf structure and it can be accessed
# using the standard python-for-protobuf methods

# iterate through inputs of the graph
for input in model.graph.input:
    print (input.name, end=": ")
    # get type of input tensor
    tensor_type = input.type.tensor_type
    # check if it has a shape:
    if (tensor_type.HasField("shape")):
        # iterate through dimensions of the shape:
        for d in tensor_type.shape.dim:
            # the dimension may have a definite (integer) value or a symbolic identifier or neither:
            if (d.HasField("dim_value")):
                print (d.dim_value, end=", ")  # known dimension
            elif (d.HasField("dim_param")):
                print (d.dim_param, end=", ")  # unknown dimension with symbolic name
            else:
                print ("?", end=", ")  # unknown dimension with no name
    else:
        print ("unknown rank", end="")
    print()
于 2019-08-05T17:31:50.623 回答
6

请不要input用作变量名，因为它是一个内置函数。

想到的第一个想法是，google.protobuf.json_format.MessageToDict()如果我需要 protobuf 对象的名称、data_type 或某些属性，则使用该方法。例如：

form google.protobuf.json_format import MessageToDict

model = onnx.load("path/to/model.onnx")
for _input in model.graph.input:
    print(MessageToDict(_input))

将给出如下输出：

{'name': '0', 'type': {'tensorType': {'elemType': 2, 'shape': {'dim': [{'dimValue': '4'}, {'dimValue': '3'}, {'dimValue': '384'}, {'dimValue': '640'}]}}}}

我不是很清楚 every 是否model.graph.input是一个RepeatedCompositeContainer对象，但是for当它是一个RepeatedCompositeContainer.

然后你需要从dim字段中获取形状信息。

model = onnx.load("path/to/model.onnx")
for _input in model.graph.input:
    m_dict = MessageToDict(_input))
    dim_info = m_dict.get("type").get("tensorType").get("shape").get("dim")  # ugly but we have to live with this when using dict
    input_shape = [d.get("dimValue") for d in dim_info]  # [4,3,384,640]

如果您需要唯一的暗淡，请改用消息对象。

model = onnx.load("path/to/model.onnx")
for _input in model.graph.input:
    dim = _input.type.tensor_ype.shape.dim
    input_shape = [MessgeToDict(d).get("dimValue") for d in dim]
    # if you prefer the python naming style, using the line below
    # input_shape = [MessgeToDict(d, preserving_proto_field_name=True).get("dim_value") for d in dim]

一行版本：

model = onnx.load("path/to/model.onnx")
input_shapes = [[d.dim_value for d in _input.type.tensor_type.shape.dim] for _input in model.graph.input]

参考：

https://github.com/googleapis/python-vision/issues/70

AttributeError：“google.protobuf.pyext._message.RepeatedCompositeCo”对象没有属性“附加”

于 2021-08-02T06:22:41.117 回答