IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[IE Samples] OV2.0 API python ngraph_function_creation_sample (#9440)

Browse Source 
* [IE Python Speech Sample] Migrate to OV 2.0 API

* improvements

* flake notes

* improved code style like as C++

* linters changes

* changed data.py

* sync output with C++ sample

Co-authored-by: Maxim Gordeev <maxim.gordeev@intel.com>
This commit is contained in:
Vladimir Dudnik
2021-12-27 09:19:18 +03:00
committed by GitHub
co-authored by Maxim Gordeev
parent b454076a56
commit a9cee5f101
2 changed files with 514 additions and 145 deletions
Download Patch File Download Diff File Expand all files Collapse all files
samples/python/ngraph_function_creation_sample/data.py
+420
View File
@@ -0,0 +1,420 @@
# -*- coding: utf-8 -*-
# Copyright (C) 2018-2021 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
import numpy
digits = numpy.array([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x0b, 0x96, 0xfd, 0xca, 0x1f, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x25, 0xfb, 0xfb, 0xfd, 0x6b, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0x15, 0xc5, 0xfb, 0xfb, 0xfd, 0x6b, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x6e, 0xbe, 0xfb,
0xfb, 0xfb, 0xfd, 0xa9, 0x6d, 0x3e, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0xfd, 0xfb, 0xfb, 0xfb, 0xfb, 0xfd, 0xfb, 0xfb, 0xdc, 0x33, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xb6, 0xff, 0xfd, 0xfd, 0xfd,
0xfd, 0xea, 0xde, 0xfd, 0xfd, 0xfd, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0x3f, 0xdd, 0xfd, 0xfb, 0xfb, 0xfb, 0x93, 0x4d, 0x3e, 0x80, 0xfb, 0xfb, 0x69, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x20, 0xe7, 0xfb, 0xfd, 0xfb, 0xdc, 0x89, 0x0a,
0, 0, 0x1f, 0xe6, 0xfb, 0xf3, 0x71, 0x05, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0x25, 0xfb, 0xfb, 0xfd, 0xbc, 0x14, 0, 0, 0, 0, 0, 0x6d, 0xfb, 0xfd, 0xfb, 0x23, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x25, 0xfb, 0xfb, 0xc9, 0x1e, 0, 0, 0, 0,
0, 0, 0x1f, 0xc8, 0xfd, 0xfb, 0x23, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x25, 0xfd, 0xfd, 0, 0, 0, 0, 0, 0, 0, 0, 0x20, 0xca, 0xff, 0xfd, 0xa4, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0x8c, 0xfb, 0xfb, 0, 0, 0, 0, 0, 0, 0,
0, 0x6d, 0xfb, 0xfd, 0xfb, 0x23, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xd9,
0xfb, 0xfb, 0, 0, 0, 0, 0, 0, 0x15, 0x3f, 0xe7, 0xfb, 0xfd, 0xe6, 0x1e, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0xd9, 0xfb, 0xfb, 0, 0, 0, 0, 0, 0, 0x90, 0xfb,
0xfb, 0xfb, 0xdd, 0x3d, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xd9, 0xfb,
0xfb, 0, 0, 0, 0, 0, 0xb6, 0xdd, 0xfb, 0xfb, 0xfb, 0xb4, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0xda, 0xfd, 0xfd, 0x49, 0x49, 0xe4, 0xfd, 0xfd, 0xff, 0xfd, 0xfd, 0xfd,
0xfd, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x71, 0xfb, 0xfb,
0xfd, 0xfb, 0xfb, 0xfb, 0xfb, 0xfd, 0xfb, 0xfb, 0xfb, 0x93, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0x1f, 0xe6, 0xfb, 0xfd, 0xfb, 0xfb, 0xfb, 0xfb, 0xfd, 0xe6, 0xbd, 0x23, 0x0a,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x3e, 0x8e, 0xfd,
0xfb, 0xfb, 0xfb, 0xfb, 0xfd, 0x6b, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0x48, 0xae, 0xfb, 0xad, 0x47, 0x48, 0x1e, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x26, 0xfe, 0x6d, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x57, 0xfc, 0x52, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x87, 0xf1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x2d, 0xf4, 0x96, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x54, 0xfe, 0x3f, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xca, 0xdf, 0x0b, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x20, 0xfe, 0xd8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x5f, 0xfe, 0xc3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x8c, 0xfe, 0x4d, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x39, 0xed, 0xcd, 0x08, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x7c, 0xff, 0xa5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xab, 0xfe, 0x51, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x18, 0xe8, 0xd7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x78, 0xfe, 0x9f, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x97, 0xfe, 0x8e, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xe4, 0xfe, 0x42, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x3d, 0xfb, 0xfe, 0x42, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x8d, 0xfe, 0xcd, 0x03, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x0a, 0xd7, 0xfe, 0x79, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x05, 0xc6, 0xb0, 0x0a, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x74,
0x7d, 0xab, 0xff, 0xff, 0x96, 0x5d, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0xa9, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xda, 0x1e, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xa9, 0xfd, 0xfd, 0xfd,
0xd5, 0x8e, 0xb0, 0xfd, 0xfd, 0x7a, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0x34, 0xfa, 0xfd, 0xd2, 0x20, 0x0c, 0, 0x06, 0xce, 0xfd, 0x8c, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x4d, 0xfb, 0xd2, 0x19, 0, 0,
0, 0x7a, 0xf8, 0xfd, 0x41, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0x1f, 0x12, 0, 0, 0, 0, 0xd1, 0xfd, 0xfd, 0x41, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x75,
0xf7, 0xfd, 0xc6, 0x0a, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x4c, 0xf7, 0xfd, 0xe7, 0x3f, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x80, 0xfd, 0xfd,
0x90, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0xb0, 0xf6, 0xfd, 0x9f, 0x0c, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x19, 0xea, 0xfd, 0xe9, 0x23, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0xc6, 0xfd, 0xfd, 0x8d, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x4e, 0xf8, 0xfd, 0xbd, 0x0c, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x13, 0xc8, 0xfd, 0xfd, 0x8d, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0x86, 0xfd, 0xfd, 0xad, 0x0c, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xf8,
0xfd, 0xfd, 0x19, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0xf8, 0xfd, 0xfd, 0x2b, 0x14, 0x14, 0x14, 0x14, 0x05, 0, 0x05,
0x14, 0x14, 0x25, 0x96, 0x96, 0x96, 0x93, 0x0a, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xf8, 0xfd,
0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xa8, 0x8f, 0xa6, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0x7b, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0xae, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd,
0xf9, 0xf7, 0xf7, 0xa9, 0x75, 0x75, 0x39, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x76, 0x7b,
0x7b, 0x7b, 0xa6, 0xfd, 0xfd, 0xfd, 0x9b, 0x7b, 0x7b, 0x29, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0x15, 0x71, 0xc1, 0xfe, 0xfd, 0xfe, 0xfd, 0xfe, 0xac, 0x52, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xb7, 0xfd, 0xfc, 0xfd, 0xfc, 0xfd,
0xfc, 0xfd, 0xfc, 0xf3, 0x28, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0xcb, 0xff, 0xe9, 0xb7, 0x66, 0xcb, 0xcb, 0xea, 0xfd, 0xfe, 0x97, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x51, 0x97, 0x32, 0, 0, 0, 0x29,
0xc1, 0xfc, 0xfd, 0x6f, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x0b, 0xd5, 0xfe, 0xfd, 0xcb, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x7b, 0xd5, 0xfc, 0xfd,
0xfc, 0x51, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0x33, 0xfd, 0xfe, 0xfd, 0xfe, 0x97, 0x15, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x0a, 0xd4, 0xfd, 0xfc, 0xfd, 0xe8,
0xdf, 0x7a, 0x52, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0x7b, 0xdf, 0xfe, 0xfd, 0xfe, 0xfd, 0xfe, 0x47, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x14, 0x32, 0x83, 0xd5,
0xfc, 0xfd, 0xc0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0x15, 0xa2, 0xfe, 0xfd, 0x66, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x15, 0xcb,
0xfd, 0xfc, 0x3d, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x84, 0xfd, 0xfe, 0x5b, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x15, 0x8e, 0xfd, 0xfc, 0xe9,
0x1e, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0x29, 0xd6, 0xfd, 0xfe, 0xd5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xa3, 0xf3, 0xfd, 0xfc, 0xac, 0x0a, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x0b, 0xad, 0xad,
0xfd, 0xff, 0xfd, 0xe0, 0x51, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0x84, 0xfc, 0xfd, 0xfc, 0xfd, 0xab, 0x14, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x99, 0xfd, 0xf4, 0xcb,
0x52, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0x5c, 0xc0, 0x7a, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x32, 0xe0,
0, 0, 0, 0, 0, 0, 0, 0x46, 0x1d, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x79, 0xe7, 0, 0, 0, 0, 0, 0, 0, 0x94, 0xa8, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x04, 0xc3, 0xe7, 0,
0, 0, 0, 0, 0, 0, 0x60, 0xd2, 0x0b, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0x45, 0xfc, 0x86, 0, 0, 0, 0, 0, 0, 0, 0x72, 0xfc, 0x15, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x2d, 0xec, 0xd9, 0x0c, 0, 0,
0, 0, 0, 0, 0, 0xc0, 0xfc, 0x15, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0xa8, 0xf7, 0x35, 0, 0, 0, 0, 0, 0, 0, 0x12, 0xff, 0xfd, 0x15, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x54, 0xf2, 0xd3, 0, 0, 0, 0, 0,
0, 0, 0, 0x8d, 0xfd, 0xbd, 0x05, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0xa9, 0xfc, 0x6a, 0, 0, 0, 0, 0, 0, 0, 0x20, 0xe8, 0xfa, 0x42, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0x0f, 0xe1, 0xfc, 0, 0, 0, 0, 0, 0, 0,
0, 0x86, 0xfc, 0xd3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x16,
0xfc, 0xa4, 0, 0, 0, 0, 0, 0, 0, 0, 0xa9, 0xfc, 0xa7, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0x09, 0xcc, 0xd1, 0x12, 0, 0, 0, 0, 0, 0, 0x16,
0xfd, 0xfd, 0x6b, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xa9,
0xfc, 0xc7, 0x55, 0x55, 0x55, 0x55, 0x81, 0xa4, 0xc3, 0xfc, 0xfc, 0x6a, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0x29, 0xaa, 0xf5, 0xfc, 0xfc, 0xfc, 0xfc, 0xe8, 0xe7, 0xfb, 0xfc,
0xfc, 0x09, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x31, 0x54, 0x54, 0x54, 0x54, 0, 0, 0xa1, 0xfc, 0xfc, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x7f, 0xfc, 0xfc,
0x2d, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0x80, 0xfd, 0xfd, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x7f, 0xfc, 0xfc, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0x87, 0xfc, 0xf4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xe8, 0xec, 0x6f, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0xb3, 0x42, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x33, 0x84, 0xd6, 0xfd, 0xfe, 0xfd, 0xcb, 0xa2, 0x29,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x66, 0x8e, 0xcb, 0xcb,
0xfd, 0xfc, 0xfd, 0xfc, 0x97, 0x46, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0xfe, 0xfd, 0xf4, 0xcb, 0x8e, 0x66, 0x52, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xac, 0xfc, 0xcb, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0x15, 0xdf, 0xea, 0x1e, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x7a, 0xfd, 0x32, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0x7b, 0xfe, 0x5b, 0x33, 0x33, 0x33, 0x0a, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x15, 0xdf, 0xfd, 0xfc, 0xfd, 0xfc, 0xfd,
0xac, 0x52, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0x15, 0xd6, 0xfd, 0xcb, 0xa2, 0x66, 0x66, 0xcb, 0xdf, 0xfe, 0xfd, 0x33, 0x0a, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x3d, 0xfd, 0xab, 0, 0, 0, 0, 0, 0x14,
0x70, 0xc0, 0xfd, 0xd4, 0x29, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x66, 0xcb, 0xea, 0x33, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0x14, 0xd5, 0xe8, 0x52, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x3e, 0xcb, 0xea, 0x70, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0x14, 0xd5, 0xfc, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x99, 0xfd, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0x29, 0xe9, 0xd4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x71, 0x5c,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x1f, 0xad, 0xf4, 0x28, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0x52, 0xfd, 0x97, 0, 0, 0, 0, 0, 0, 0x15, 0x66, 0x66, 0xb7,
0xe9, 0xd4, 0x51, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x52, 0xff, 0xfd, 0xea,
0x98, 0x99, 0xc1, 0xad, 0xfd, 0xfe, 0xfd, 0xfe, 0xd5, 0x8e, 0x14, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0x47, 0x97, 0x97, 0xe8, 0xfd, 0xd4, 0xc0, 0x97, 0x83, 0x32, 0x32, 0x0a, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x07,
0xcc, 0xfd, 0xb0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x07, 0x96, 0xfc, 0xfc, 0x7d, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x75, 0xfc, 0xba,
0x38, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0x8d, 0xfc, 0x76, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x9a, 0xf7, 0x32, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0x1a, 0xfd, 0xc4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x96, 0xfd, 0xc4, 0, 0, 0,
0, 0, 0, 0, 0x39, 0x55, 0x55, 0x26, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0xe1, 0xfd, 0x60, 0, 0, 0, 0, 0, 0x97, 0xe2, 0xf3, 0xfc, 0xfc, 0xee, 0x7d, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x0a, 0xe5, 0xe2, 0, 0, 0, 0x04, 0x36,
0xe5, 0xfd, 0xff, 0xea, 0xaf, 0xe1, 0xff, 0xe4, 0x1f, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0x6e, 0xfc, 0x96, 0, 0, 0x1a, 0x80, 0xfc, 0xfc, 0xe3, 0x86, 0x1c, 0, 0, 0xb2, 0xfc, 0x38, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x9f, 0xfc, 0x71, 0, 0, 0x96, 0xfd, 0xfc, 0xba,
0x2b, 0, 0, 0, 0, 0x8d, 0xfc, 0x38, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0xb9, 0xfc, 0x71, 0, 0x26, 0xed, 0xfd, 0x97, 0x06, 0, 0, 0, 0, 0, 0x8d, 0xca, 0x06, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0xc6, 0xfd, 0x72, 0, 0x93, 0xfd, 0xa3, 0, 0, 0,
0, 0, 0, 0, 0x9a, 0xc5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xc5,
0xfc, 0x71, 0, 0xac, 0xfc, 0xbc, 0, 0, 0, 0, 0, 0, 0x1a, 0xfd, 0xab, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0xc5, 0xfc, 0x71, 0, 0x13, 0xe7, 0xf7, 0x7a, 0x13, 0, 0,
0, 0, 0xc8, 0xf4, 0x38, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x1a, 0xde, 0xfc,
0x71, 0, 0, 0x19, 0xcb, 0xfc, 0xc1, 0x0d, 0, 0x4c, 0xc8, 0xf9, 0x7d, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0xb9, 0xfd, 0xb3, 0x0a, 0, 0, 0, 0x4c, 0x23, 0x1d, 0x9a, 0xfd,
0xf4, 0x7d, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x1c, 0xd1, 0xfd,
0xc4, 0x52, 0x39, 0x39, 0x83, 0xc5, 0xfc, 0xfd, 0xd6, 0x51, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x19, 0xd8, 0xfc, 0xfc, 0xfc, 0xfd, 0xfc, 0xfc, 0xfc, 0x9c, 0x13, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x10, 0x67,
0x8b, 0xf0, 0x8c, 0x8b, 0x8b, 0x28, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x54, 0xb9, 0x9f, 0x97, 0x3c, 0x24, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0xde, 0xfe, 0xfe, 0xfe, 0xfe, 0xf1, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xaa, 0x34, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x43, 0x72, 0x48, 0x72, 0xa3, 0xe3, 0xfe, 0xe1,
0xfe, 0xfe, 0xfe, 0xfa, 0xe5, 0xfe, 0xfe, 0x8c, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0x11, 0x42, 0x0e, 0x43, 0x43, 0x43, 0x3b, 0x15, 0xec, 0xfe, 0x6a, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0x53, 0xfd, 0xd1, 0x12, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x16, 0xe9, 0xff, 0x53, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0x81, 0xfe, 0xee, 0x2c, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0x3b, 0xf9, 0xfe, 0x3e, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x85,
0xfe, 0xbb, 0x05, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x09, 0xcd, 0xf8, 0x3a, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x7e, 0xfe, 0xb6,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0x4b, 0xfb, 0xf0, 0x39, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x13, 0xdd, 0xfe, 0xa6, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0x03, 0xcb, 0xfe, 0xdb, 0x23, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x26, 0xfe, 0xfe, 0x4d, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x1f, 0xe0, 0xfe, 0x73, 0x01, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0x85, 0xfe, 0xfe, 0x34, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x3d, 0xf2,
0xfe, 0xfe, 0x34, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x79, 0xfe, 0xfe, 0xdb, 0x28, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x79, 0xfe, 0xcf,
0x12, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0x06, 0x4b, 0, 0x62, 0xb9, 0xb2, 0x5e, 0x13, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x0f, 0x6f, 0xc3, 0xee, 0x5e, 0, 0xd0, 0xf9, 0xfe,
0xfe, 0x74, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x14, 0x32, 0x6b,
0xc5, 0xf6, 0xb7, 0x19, 0, 0, 0x51, 0xf5, 0xfe, 0xf9, 0x5b, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0x12, 0x54, 0xe6, 0xfe, 0xfe, 0xdd, 0x56, 0, 0, 0x01, 0x7d, 0xfd, 0xfe, 0xb2, 0x35,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x85, 0xfe, 0xfe, 0xd9, 0x76, 0x04,
0, 0, 0x3e, 0xca, 0xfe, 0xf1, 0x83, 0x08, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0x6b, 0xf4, 0xfe, 0xd5, 0x2d, 0, 0, 0, 0x3e, 0xf0, 0xfe, 0xdc, 0x1d, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x2c, 0xf6, 0xfe, 0xd1, 0x31, 0, 0, 0, 0x1f,
0xf1, 0xfe, 0xdd, 0x1b, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x5f, 0xfe, 0xfe, 0x37, 0, 0, 0, 0x11, 0xc6, 0xfe, 0xda, 0x1c, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0x1b, 0xdb, 0xfe, 0xe9, 0x90, 0x27, 0x2a, 0xcc, 0xfe, 0xcd,
0x0a, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x73, 0xf8, 0xfe, 0xfe, 0xf4, 0xe9, 0xfe, 0xdf, 0x18, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x26, 0x54, 0xa8, 0xf5, 0xfe, 0xfe, 0xfe, 0xcf, 0x73,
0x09, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0x0e, 0xec, 0xfe, 0xe6, 0xa3, 0xed, 0xf4, 0xd3, 0x50, 0x01, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x63, 0xfe, 0xfe, 0x63, 0, 0, 0x25, 0xe1,
0xfe, 0x82, 0x08, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0x47, 0xfe, 0xe5, 0x0c, 0, 0, 0, 0x02, 0xaa, 0xfe, 0x33, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x60, 0xfe, 0xfe, 0x12, 0, 0, 0, 0, 0x51,
0xfe, 0xc6, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x50, 0xfe, 0xfe, 0x12, 0, 0, 0, 0, 0x83, 0xfe, 0x77, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0x05, 0xd6, 0xfe, 0x4e, 0, 0, 0, 0x01, 0xb7, 0xf4,
0x3f, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x40, 0xfd, 0xdf, 0x18, 0, 0x02, 0x7e, 0xfe, 0xb2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x57, 0xee, 0xde, 0x77, 0xb1, 0xfe, 0xd9, 0x1b, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0x12, 0x9a, 0xc4, 0xc4, 0x65, 0x19, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x24, 0x38, 0x89, 0xc9, 0xc7, 0x5f, 0x25, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x2d, 0x98, 0xea, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfa, 0xd3, 0x97, 0x06,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x2e, 0x99, 0xf0, 0xfe, 0xfe,
0xe3, 0xa6, 0x85, 0xfb, 0xc8, 0xfe, 0xe5, 0xe1, 0x68, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0x99, 0xea, 0xfe, 0xfe, 0xbb, 0x8e, 0x08, 0, 0, 0xbf, 0x28, 0xc6, 0xf6, 0xdf, 0xfd, 0x15,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x7e, 0xfd, 0xfe, 0xe9, 0x80, 0x0b, 0, 0,
0, 0, 0xd2, 0x2b, 0x46, 0xfe, 0xfe, 0xfe, 0x15, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0x48, 0xf3, 0xfe, 0xe4, 0x36, 0, 0, 0, 0, 0x03, 0x20, 0x74, 0xe1, 0xf2, 0xfe, 0xff, 0xa2, 0x05, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0x4b, 0xf0, 0xfe, 0xdf, 0x6d, 0x8a, 0xb2, 0xb2, 0xa9, 0xd2,
0xfb, 0xe7, 0xfe, 0xfe, 0xfe, 0xe8, 0x26, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x09,
0xaf, 0xf4, 0xfd, 0xff, 0xfe, 0xfe, 0xfb, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfc, 0xab, 0x19, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x10, 0x88, 0xc3, 0xb0, 0x92, 0x99, 0xc8, 0xfe, 0xfe,
0xfe, 0xfe, 0x96, 0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0xa2, 0xfe, 0xfe, 0xf1, 0x63, 0x03, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x76, 0xfa, 0xfe, 0xfe, 0x5a,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0x64, 0xf2, 0xfe, 0xfe, 0xd3, 0x07, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x36, 0xf1, 0xfe, 0xfe, 0xf2, 0x3b, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0x83, 0xfe, 0xfe, 0xf4, 0x40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0x0d, 0xf9, 0xfe, 0xfe, 0x98, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x0c, 0xe4,
0xfe, 0xfe, 0xd0, 0x08, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0x4e, 0xff, 0xfe, 0xfe, 0x42, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xd1, 0xfe, 0xfe,
0x89, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0xe3, 0xff, 0xe9, 0x19, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x71, 0xff, 0x6c, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0]])
samples/python/ngraph_function_creation_sample/ngraph_function_creation_sample.py
+94 -145
View File
@@ -2,110 +2,67 @@
# -*- coding: utf-8 -*-
# Copyright (C) 2018-2021 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
import argparse
import logging as log
import struct as st
import sys
import typing
from functools import reduce
import cv2
import ngraph
from ngraph.opset1 import max_pool
import numpy as np
from openvino.inference_engine import IECore, IENetwork
from openvino.preprocess import PrePostProcessor
from openvino.runtime import Core, Layout, Type, Model, Shape, PartialShape
import openvino
from data import digits
def parse_args() -> argparse.Namespace:
"""Parse and return command line arguments"""
parser = argparse.ArgumentParser(add_help=False)
args = parser.add_argument_group('Options')
# fmt: off
args.add_argument('-h', '--help', action='help', help='Show this help message and exit.')
args.add_argument('-m', '--model', required=True, type=str,
help='Required. Path to a file with network weights.')
args.add_argument('-i', '--input', required=True, type=str, nargs='+', help='Required. Path to an image file.')
args.add_argument('-d', '--device', default='CPU', type=str,
help='Optional. Specify the target device to infer on; CPU, GPU, MYRIAD, HDDL or HETERO: '
'is acceptable. The sample will look for a suitable plugin for device specified. '
'Default value is CPU.')
args.add_argument('--labels', default=None, type=str, help='Optional. Path to a labels mapping file.')
args.add_argument('-nt', '--number_top', default=10, type=int, help='Optional. Number of top results.')
# fmt: on
return parser.parse_args()
def read_image(image_path: str) -> np.ndarray:
"""Read and return an image as grayscale (one channel)"""
image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
# Try to open image as ubyte
if image is None:
with open(image_path, 'rb') as f:
st.unpack('>4B', f.read(4)) # need to skip 4 bytes
nimg = st.unpack('>I', f.read(4))[0] # number of images
nrow = st.unpack('>I', f.read(4))[0] # number of rows
ncolumn = st.unpack('>I', f.read(4))[0] # number of column
nbytes = nimg * nrow * ncolumn * 1 # each pixel data is 1 byte
if nimg != 1:
raise Exception('Sample supports ubyte files with 1 image inside')
image = np.asarray(st.unpack('>' + 'B' * nbytes, f.read(nbytes))).reshape((nrow, ncolumn))
return image
def create_ngraph_function(args: argparse.Namespace) -> ngraph.impl.Function:
def create_ngraph_function(model_path: str) -> Model:
"""Create a network on the fly from the source code using ngraph"""
def shape_and_length(shape: list) -> typing.Tuple[list, int]:
length = reduce(lambda x, y: x * y, shape)
return shape, length
weights = np.fromfile(args.model, dtype=np.float32)
weights = np.fromfile(model_path, dtype=np.float32)
weights_offset = 0
padding_begin = padding_end = [0, 0]
# input
input_shape = [64, 1, 28, 28]
param_node = ngraph.parameter(input_shape, np.float32, 'Parameter')
param_node = openvino.runtime.op.Parameter(Type.f32, Shape(input_shape))
# convolution 1
conv_1_kernel_shape, conv_1_kernel_length = shape_and_length([20, 1, 5, 5])
conv_1_kernel = ngraph.constant(weights[0:conv_1_kernel_length].reshape(conv_1_kernel_shape))
conv_1_kernel = openvino.runtime.op.Constant(Type.f32, Shape(conv_1_kernel_shape), weights[0:conv_1_kernel_length].tolist())
weights_offset += conv_1_kernel_length
conv_1_node = ngraph.convolution(param_node, conv_1_kernel, [1, 1], padding_begin, padding_end, [1, 1])
conv_1_node = openvino.runtime.opset8.convolution(param_node, conv_1_kernel, [1, 1], padding_begin, padding_end, [1, 1])
# add 1
add_1_kernel_shape, add_1_kernel_length = shape_and_length([1, 20, 1, 1])
add_1_kernel = ngraph.constant(
weights[weights_offset : weights_offset + add_1_kernel_length].reshape(add_1_kernel_shape),
)
add_1_kernel = openvino.runtime.op.Constant(Type.f32, Shape(add_1_kernel_shape),
weights[weights_offset : weights_offset + add_1_kernel_length])
weights_offset += add_1_kernel_length
add_1_node = ngraph.add(conv_1_node, add_1_kernel)
add_1_node = openvino.runtime.opset8.add(conv_1_node, add_1_kernel)
# maxpool 1
maxpool_1_node = max_pool(add_1_node, [2, 2], padding_begin, padding_end, [2, 2], 'ceil')
maxpool_1_node = openvino.runtime.opset1.max_pool(add_1_node, [2, 2], padding_begin, padding_end, [2, 2], 'ceil')
# convolution 2
conv_2_kernel_shape, conv_2_kernel_length = shape_and_length([50, 20, 5, 5])
conv_2_kernel = ngraph.constant(
weights[weights_offset : weights_offset + conv_2_kernel_length].reshape(conv_2_kernel_shape),
)
conv_2_kernel = openvino.runtime.op.Constant(Type.f32, Shape(conv_2_kernel_shape),
weights[weights_offset : weights_offset + conv_2_kernel_length],
)
weights_offset += conv_2_kernel_length
conv_2_node = ngraph.convolution(maxpool_1_node, conv_2_kernel, [1, 1], padding_begin, padding_end, [1, 1])
conv_2_node = openvino.runtime.opset8.convolution(maxpool_1_node, conv_2_kernel, [1, 1], padding_begin, padding_end, [1, 1])
# add 2
add_2_kernel_shape, add_2_kernel_length = shape_and_length([1, 50, 1, 1])
add_2_kernel = ngraph.constant(
weights[weights_offset : weights_offset + add_2_kernel_length].reshape(add_2_kernel_shape),
)
add_2_kernel = openvino.runtime.op.Constant(Type.f32, Shape(add_2_kernel_shape),
weights[weights_offset : weights_offset + add_2_kernel_length],
)
weights_offset += add_2_kernel_length
add_2_node = ngraph.add(conv_2_node, add_2_kernel)
add_2_node = openvino.runtime.opset8.add(conv_2_node, add_2_kernel)
# maxpool 2
maxpool_2_node = max_pool(add_2_node, [2, 2], padding_begin, padding_end, [2, 2], 'ceil')
maxpool_2_node = openvino.runtime.opset1.max_pool(add_2_node, [2, 2], padding_begin, padding_end, [2, 2], 'ceil')
# reshape 1
reshape_1_dims, reshape_1_length = shape_and_length([2])
@@ -114,142 +71,134 @@ def create_ngraph_function(args: argparse.Namespace) -> ngraph.impl.Function:
weights[weights_offset : weights_offset + 2 * reshape_1_length],
dtype=np.int64,
)
reshape_1_kernel = ngraph.constant(dtype_weights)
reshape_1_kernel = openvino.runtime.op.Constant(Type.i64, Shape(list(dtype_weights.shape)), dtype_weights)
weights_offset += 2 * reshape_1_length
reshape_1_node = ngraph.reshape(maxpool_2_node, reshape_1_kernel, True)
reshape_1_node = openvino.runtime.opset8.reshape(maxpool_2_node, reshape_1_kernel, True)
# matmul 1
matmul_1_kernel_shape, matmul_1_kernel_length = shape_and_length([500, 800])
matmul_1_kernel = ngraph.constant(
weights[weights_offset : weights_offset + matmul_1_kernel_length].reshape(matmul_1_kernel_shape),
)
matmul_1_kernel = openvino.runtime.op.Constant(Type.f32, Shape(matmul_1_kernel_shape),
weights[weights_offset : weights_offset + matmul_1_kernel_length],
)
weights_offset += matmul_1_kernel_length
matmul_1_node = ngraph.matmul(reshape_1_node, matmul_1_kernel, False, True)
matmul_1_node = openvino.runtime.opset8.matmul(reshape_1_node, matmul_1_kernel, False, True)
# add 3
add_3_kernel_shape, add_3_kernel_length = shape_and_length([1, 500])
add_3_kernel = ngraph.constant(
weights[weights_offset : weights_offset + add_3_kernel_length].reshape(add_3_kernel_shape),
)
add_3_kernel = openvino.runtime.op.Constant(Type.f32, Shape(add_3_kernel_shape),
weights[weights_offset : weights_offset + add_3_kernel_length],
)
weights_offset += add_3_kernel_length
add_3_node = ngraph.add(matmul_1_node, add_3_kernel)
add_3_node = openvino.runtime.opset8.add(matmul_1_node, add_3_kernel)
# ReLU
relu_node = ngraph.relu(add_3_node)
relu_node = openvino.runtime.opset8.relu(add_3_node)
# reshape 2
reshape_2_kernel = ngraph.constant(dtype_weights)
reshape_2_node = ngraph.reshape(relu_node, reshape_2_kernel, True)
reshape_2_kernel = openvino.runtime.op.Constant(Type.i64, Shape(list(dtype_weights.shape)), dtype_weights)
reshape_2_node = openvino.runtime.opset8.reshape(relu_node, reshape_2_kernel, True)
# matmul 2
matmul_2_kernel_shape, matmul_2_kernel_length = shape_and_length([10, 500])
matmul_2_kernel = ngraph.constant(
weights[weights_offset : weights_offset + matmul_2_kernel_length].reshape(matmul_2_kernel_shape),
)
matmul_2_kernel = openvino.runtime.op.Constant(Type.f32, Shape(matmul_2_kernel_shape),
weights[weights_offset : weights_offset + matmul_2_kernel_length],
)
weights_offset += matmul_2_kernel_length
matmul_2_node = ngraph.matmul(reshape_2_node, matmul_2_kernel, False, True)
matmul_2_node = openvino.runtime.opset8.matmul(reshape_2_node, matmul_2_kernel, False, True)
# add 4
add_4_kernel_shape, add_4_kernel_length = shape_and_length([1, 10])
add_4_kernel = ngraph.constant(
weights[weights_offset : weights_offset + add_4_kernel_length].reshape(add_4_kernel_shape),
)
add_4_kernel = openvino.runtime.op.Constant(Type.f32, Shape(add_4_kernel_shape),
weights[weights_offset : weights_offset + add_4_kernel_length],
)
weights_offset += add_4_kernel_length
add_4_node = ngraph.add(matmul_2_node, add_4_kernel)
add_4_node = openvino.runtime.opset8.add(matmul_2_node, add_4_kernel)
# softmax
softmax_axis = 1
softmax_node = ngraph.softmax(add_4_node, softmax_axis)
softmax_node = openvino.runtime.opset8.softmax(add_4_node, softmax_axis)
# result
result_node = ngraph.result(softmax_node)
return ngraph.impl.Function(result_node, [param_node], 'lenet')
return Model(softmax_node, [param_node], 'lenet')
def main():
log.basicConfig(format='[ %(levelname)s ] %(message)s', level=log.INFO, stream=sys.stdout)
args = parse_args()
# Parsing and validation of input arguments
if len(sys.argv) != 3:
log.info('Usage: <path_to_model> <device_name>')
return 1
model_path = sys.argv[1]
device_name = sys.argv[2]
labels = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
number_top = 1
# ---------------------------Step 1. Initialize inference engine core--------------------------------------------------
log.info('Creating Inference Engine')
ie = IECore()
log.info('Creating OpenVINO Runtime Core')
core = Core()
# ---------------------------Step 2. Read a model in OpenVINO Intermediate Representation------------------------------
log.info(f'Loading the network using ngraph function with weights from {args.model}')
ngraph_function = create_ngraph_function(args)
net = IENetwork(ngraph.impl.Function.to_capsule(ngraph_function))
# ---------------------------Step 3. Configure input & output----------------------------------------------------------
log.info('Configuring input and output blobs')
log.info(f'Loading the network using ngraph function with weights from {model_path}')
model = create_ngraph_function(model_path)
# ---------------------------Step 3. Apply preprocessing----------------------------------------------------------
# Get names of input and output blobs
input_blob = next(iter(net.input_info))
out_blob = next(iter(net.outputs))
ppp = PrePostProcessor(model)
# 1) Set input tensor information:
# - input() provides information about a single model input
# - precision of tensor is supposed to be 'u8'
# - layout of data is 'NHWC'
ppp.input().tensor() \
.set_element_type(Type.u8) \
.set_layout(Layout('NHWC')) # noqa: N400
# Set input and output precision manually
net.input_info[input_blob].precision = 'U8'
net.outputs[out_blob].precision = 'FP32'
# 2) Here we suppose model has 'NCHW' layout for input
ppp.input().model().set_layout(Layout('NCHW'))
# 3) Set output tensor information:
# - precision of tensor is supposed to be 'f32'
ppp.output().tensor().set_element_type(Type.f32)
# Set a batch size to a equal number of input images
net.batch_size = len(args.input)
# 4) Apply preprocessing modifing the original 'model'
model = ppp.build()
# Set a batch size equal to number of input images
model.reshape({model.input().get_any_name(): PartialShape((digits.shape[0], model.input().shape[1], model.input().shape[2], model.input().shape[3]))})
# ---------------------------Step 4. Loading model to the device-------------------------------------------------------
log.info('Loading the model to the plugin')
exec_net = ie.load_network(network=net, device_name=args.device)
compiled_model = core.compile_model(model, device_name)
# ---------------------------Step 5. Create infer request--------------------------------------------------------------
# load_network() method of the IECore class with a specified number of requests (default 1) returns an ExecutableNetwork
# instance which stores infer requests. So you already created Infer requests in the previous step.
# ---------------------------Step 6. Prepare input---------------------------------------------------------------------
n, c, h, w = net.input_info[input_blob].input_data.shape
# ---------------------------Step 5. Prepare input---------------------------------------------------------------------
n, c, h, w = model.input().shape
input_data = np.ndarray(shape=(n, c, h, w))
for i in range(n):
image = read_image(args.input[i])
light_pixel_count = np.count_nonzero(image > 127)
dark_pixel_count = np.count_nonzero(image < 127)
is_light_image = (light_pixel_count - dark_pixel_count) > 0
if is_light_image:
log.warning(f'Image {args.input[i]} is inverted to white over black')
image = cv2.bitwise_not(image)
if image.shape != (h, w):
log.warning(f'Image {args.input[i]} is resized from {image.shape} to {(h, w)}')
image = cv2.resize(image, (w, h))
image = digits[i].reshape(28, 28)
image = image[:, :, np.newaxis]
input_data[i] = image
# ---------------------------Step 7. Do inference----------------------------------------------------------------------
# ---------------------------Step 6. Do inference----------------------------------------------------------------------
log.info('Starting inference in synchronous mode')
res = exec_net.infer(inputs={input_blob: input_data})
results = compiled_model.infer_new_request({0: input_data})
# ---------------------------Step 8. Process output--------------------------------------------------------------------
# Generate a label list
if args.labels:
with open(args.labels, 'r') as f:
labels = [line.split(',')[0].strip() for line in f]
res = res[out_blob]
# ---------------------------Step 7. Process output--------------------------------------------------------------------
predictions = next(iter(results.values()))
log.info(f'Top {number_top} results: ')
for i in range(n):
probs = res[i]
# Get an array of args.number_top class IDs in descending order of probability
top_n_idexes = np.argsort(probs)[-args.number_top :][::-1]
probs = predictions[i]
# Get an array of number_top class IDs in descending order of probability
top_n_idexes = np.argsort(probs)[-number_top :][::-1]
header = 'classid probability'
header = header + ' label' if args.labels else header
header = header + ' label' if labels else header
log.info(f'Image path: {args.input[i]}')
log.info(f'Top {args.number_top} results: ')
log.info(f'Image {i}')
log.info('')
log.info(header)
log.info('-' * len(header))
for class_id in top_n_idexes:
probability_indent = ' ' * (len('classid') - len(str(class_id)) + 1)
label_indent = ' ' * (len('probability') - 8) if args.labels else ''
label = labels[class_id] if args.labels else ''
label_indent = ' ' * (len('probability') - 8) if labels else ''
label = labels[class_id] if labels else ''
log.info(f'{class_id}{probability_indent}{probs[class_id]:.7f}{label_indent}{label}')
log.info('')