背景

在模型的部署中，为了高效利用硬件算力，常常会需要将多个输入组成一个batch同时输入网络进行推理，这个batch的大小根据系统的负载或者摄像头的路数时刻在变化，因此网络的输入batch是在动态变化的。对于pytorch等框架来说，我们并不会感受到这个问题，因为整个网络在pytorch中都是动态的。而在实际的工程化部署中，为了运行效率，却并不能有这样的灵活性。可能会有人说，那我就把batch固定在一个最大值，然后输入实际的batch，这样实际上网络是以最大batch在推理的，浪费了算力。所以我们需要能支持动态的batch，能够根据输入的batch数来运行。

一个常见的训练到部署的路径是：pytorch→onnx→tensorrt。在pytorch导出onnx时，我们可以指定输出为动态的输入：

torch_out = torch.onnx.export(model, inp,
                              save_path,input_names=["data"],output_names=["fc1"],dynamic_axes={
        "data":{0:'batch_size'},"fc1":{0:'batch_size'}
    })

而另一些时候，我们部署的模型来源于他人或开源模型，已经失去了原始的pytorch模型，此时如果onnx是静态batch的，在移植到tensorrt时，其输入就为静态输入了。想要动态输入，就需要对onnx模型本身进行修改了。另一方面，算法工程师在导模型的时候，如果没有指定输入层输出层的名称，导出的模型的层名有时候可读性比较差，比如输出是batchnorm_274这类名称，为了方便维护，也有需要对onnx的输入输出层名称进行修改。

操作

def change_input_output_dim(model):
    # Use some symbolic name not used for any other dimension
    sym_batch_dim = "batch"

    # The following code changes the first dimension of every input to be batch-dim
    # Modify as appropriate ... note that this requires all inputs to
    # have the same batch_dim
    inputs = model.graph.input
    for input in inputs:
        # Checks omitted.This assumes that all inputs are tensors and have a shape with first dim.
        # Add checks as needed.
        dim1 = input.type.tensor_type.shape.dim[0]
        # update dim to be a symbolic value
        dim1.dim_param = sym_batch_dim
        # or update it to be an actual value:
        # dim1.dim_value = actual_batch_dim

    outputs = model.graph.output
    for output in outputs:
        # Checks omitted.This assumes that all inputs are tensors and have a shape with first dim.
        # Add checks as needed.
        dim1 = output.type.tensor_type.shape.dim[0]
        # update dim to be a symbolic value
        dim1.dim_param = sym_batch_dim

model = onnx.load(onnx_path)
change_input_output_dim(model)

通过将输入层和输出层的shape的第一维修改为非数字，就可以将onnx模型改为动态batch。

def change_input_node_name(model, input_names):
    for i,input in enumerate(model.graph.input):
        input_name = input_names[i]
        for node in model.graph.node:
            for i, name in enumerate(node.input):
                if name == input.name:
                    node.input[i] = input_name
        input.name = input_name

def change_output_node_name(model, output_names):
    for i,output in enumerate(model.graph.output):
        output_name = output_names[i]
        for node in model.graph.node:
            for i, name in enumerate(node.output):
                if name == output.name:
                    node.output[i] = output_name
        output.name = output_name

代码中input_names和output_names是我们希望改到的名称，做法是遍历网络，若有node的输入层名与要修改的输入层名称相同，则改成新的输入层名。输出层类似。

import onnx
def change_input_output_dim(model):
    # Use some symbolic name not used for any other dimension
    sym_batch_dim = "batch"

    # The following code changes the first dimension of every input to be batch-dim
    # Modify as appropriate ... note that this requires all inputs to
    # have the same batch_dim
    inputs = model.graph.input
    for input in inputs:
        # Checks omitted.This assumes that all inputs are tensors and have a shape with first dim.
        # Add checks as needed.
        dim1 = input.type.tensor_type.shape.dim[0]
        # update dim to be a symbolic value
        dim1.dim_param = sym_batch_dim
        # or update it to be an actual value:
        # dim1.dim_value = actual_batch_dim

    outputs = model.graph.output
    for output in outputs:
        # Checks omitted.This assumes that all inputs are tensors and have a shape with first dim.
        # Add checks as needed.
        dim1 = output.type.tensor_type.shape.dim[0]
        # update dim to be a symbolic value
        dim1.dim_param = sym_batch_dim

def change_input_node_name(model, input_names):
    for i,input in enumerate(model.graph.input):
        input_name = input_names[i]
        for node in model.graph.node:
            for i, name in enumerate(node.input):
                if name == input.name:
                    node.input[i] = input_name
        input.name = input_name

def change_output_node_name(model, output_names):
    for i,output in enumerate(model.graph.output):
        output_name = output_names[i]
        for node in model.graph.node:
            for i, name in enumerate(node.output):
                if name == output.name:
                    node.output[i] = output_name
        output.name = output_name

onnx_path = ""
save_path = ""
model = onnx.load(onnx_path)
change_input_output_dim(model)
change_input_node_name(model, ["data"])
change_output_node_name(model, ["fc1"])

onnx.save(model, save_path)

经过修改后的onnx模型输入输出将成为动态batch，可以方便的移植到tensorrt等框架以支持高效推理。