1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
|
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
"""
.. _l-example-profiling:
Profile the execution of a simple model
=======================================
*ONNX Runtime* can profile the execution of the model.
This example shows how to interpret the results.
"""
import numpy
import onnx
import onnxruntime as rt
from onnxruntime.datasets import get_example
def change_ir_version(filename, ir_version=6):
"onnxruntime==1.2.0 does not support opset <= 7 and ir_version > 6"
with open(filename, "rb") as f:
model = onnx.load(f)
model.ir_version = 6
if model.opset_import[0].version <= 7:
model.opset_import[0].version = 11
return model
#########################
# Let's load a very simple model and compute some prediction.
example1 = get_example("mul_1.onnx")
onnx_model = change_ir_version(example1)
onnx_model_str = onnx_model.SerializeToString()
sess = rt.InferenceSession(onnx_model_str, providers=rt.get_available_providers())
input_name = sess.get_inputs()[0].name
x = numpy.array([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]], dtype=numpy.float32)
res = sess.run(None, {input_name: x})
print(res)
#########################
# We need to enable to profiling
# before running the predictions.
options = rt.SessionOptions()
options.enable_profiling = True
sess_profile = rt.InferenceSession(onnx_model_str, options, providers=rt.get_available_providers())
input_name = sess.get_inputs()[0].name
x = numpy.array([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]], dtype=numpy.float32)
sess.run(None, {input_name: x})
prof_file = sess_profile.end_profiling()
print(prof_file)
###########################
# The results are stored un a file in JSON format.
# Let's see what it contains.
import json # noqa: E402
with open(prof_file) as f:
sess_time = json.load(f)
import pprint # noqa: E402
pprint.pprint(sess_time)
|
