ONNX:机器学习模型通用格式

电脑技术 电脑技术 1338 人阅读 | 1 人回复 | 2022-04-04

马上注册,结交更多好友,享用更多功能,让你轻松玩转社区。

您需要 登录 才可以下载或查看,没有账号?立即注册

x
Python示例:
import numpy
from onnx import numpy_helper, TensorProto
from onnx.helper import (
    make_model, make_node, set_model_props, make_tensor,
    make_graph, make_tensor_value_info)
from mlprodict.plotting.text_plot import onnx_simple_text_plot

# inputs

# 'X' is the name, TensorProto.FLOAT the type, [None, None] the shape
X = make_tensor_value_info('X', TensorProto.FLOAT, [None, None])
A = make_tensor_value_info('A', TensorProto.FLOAT, [None, None])
B = make_tensor_value_info('B', TensorProto.FLOAT, [None, None])

# outputs, the shape is left undefined

Y = make_tensor_value_info('Y', TensorProto.FLOAT, None)

# nodes

# It creates a node defined by the operator type MatMul,
# 'X', 'A' are the inputs of the node, 'XA' the output.
node1 = make_node('MatMul', ['X', 'A'], ['XA'])
node2 = make_node('Add', ['XA', 'B'], ['Y'])

# from nodes to graph
# the graph is built from the list of nodes, the list of inputs,
# the list of outputs and a name.

graph = make_graph([node1, node2],  # nodes
                   'lr',  # a name
                   [X, A, B],  # inputs
                   [Y])  # outputs

# onnx graph
# there is no metata in this case.

onnx_model = make_model(graph)

# the work is done, let's display it...
print(onnx_simple_text_plot(onnx_model))

回答|共 1 个

willsonlincake 发表于 2022-4-4 20:54:02| 字数 33 来自手机 | 显示全部楼层

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

热门推荐