python — экспорт обученных моделей TensorFlow в переполнение стека

Я пытаюсь экспортировать обученные модели TensorFlow в C ++, используя freeze_graph.py. Я пытаюсь экспортировать модель ssd_mobilenet_v1_coco_2017_11_17, используя следующий синтаксис:

bazel build tensorflow/python/tools:freeze_graph && \
bazel-bin/tensorflow/python/tools/freeze_graph \
--input_graph=frozen_inference_graph.pb \
--input_checkpoint=model.ckpt \
--output_graph=/tmp/frozen_graph.pb --output_node_names=softmax

Терминал сказал, что сборка прошла успешно, но показала следующую ошибку:

Traceback (most recent call last):
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/tools/freeze_graph.py", line 350, in <module>
app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 124, in run
_sys.exit(main(argv))
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/tools/freeze_graph.py", line 249, in main
FLAGS.saved_model_tags)
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/tools/freeze_graph.py", line 227, in freeze_graph
input_graph_def = _parse_input_graph_proto(input_graph, input_binary)
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/tools/freeze_graph.py", line 171, in _parse_input_graph_proto
text_format.Merge(f.read(), input_graph_def)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 525, in Merge
descriptor_pool=descriptor_pool)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 579, in MergeLines
return parser.MergeLines(lines, message)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 612, in MergeLines
self._ParseOrMerge(lines, message)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 627, in _ParseOrMerge
self._MergeField(tokenizer, message)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 671, in _MergeField
name = tokenizer.ConsumeIdentifierOrNumber()
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 1144, in ConsumeIdentifierOrNumber
raise self.ParseError('Expected identifier or number, got %s.' % result)
google.protobuf.text_format.ParseError: 2:1 : Expected identifier or number, got `.

При повторном запуске этой команды я получил следующее сообщение:

WARNING: /home/my_username/tensorflow/tensorflow/core/BUILD:1814:1: in includes attribute of cc_library rule //tensorflow/core:framework_headers_lib: '../../external/nsync/public' resolves to 'external/nsync/public' not below the relative path of its package 'tensorflow/core'. This will be an error in the future. Since this rule was created by the macro 'cc_header_only_library', the error might have been caused by the macro implementation in /home/my_username/tensorflow/tensorflow/tensorflow.bzl:1138:30
WARNING: /home/my_username/tensorflow/tensorflow/core/BUILD:1814:1: in includes attribute of cc_library rule //tensorflow/core:framework_headers_lib: '../../external/nsync/public' resolves to 'external/nsync/public' not below the relative path of its package 'tensorflow/core'. This will be an error in the future. Since this rule was created by the macro 'cc_header_only_library', the error might have been caused by the macro implementation in /home/my_username/tensorflow/tensorflow/tensorflow.bzl:1138:30
WARNING: /home/my_username/tensorflow/tensorflow/contrib/learn/BUILD:15:1: in py_library rule //tensorflow/contrib/learn:learn: target '//tensorflow/contrib/learn:learn' depends on deprecated target '//tensorflow/contrib/session_bundle:exporter': No longer supported. Switch to SavedModel immediately.
WARNING: /home/my_username/tensorflow/tensorflow/contrib/learn/BUILD:15:1: in py_library rule //tensorflow/contrib/learn:learn: target '//tensorflow/contrib/learn:learn' depends on deprecated target '//tensorflow/contrib/session_bundle:gc': No longer supported. Switch to SavedModel immediately.
INFO: Analysed target //tensorflow/python/tools:freeze_graph (0 packages loaded).
INFO: Found 1 target...
Target //tensorflow/python/tools:freeze_graph up-to-date:
bazel-bin/tensorflow/python/tools/freeze_graph
INFO: Elapsed time: 0.419s, Critical Path: 0.00s
INFO: Build completed successfully, 1 total action
Traceback (most recent call last):
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/tools/freeze_graph.py", line 350, in <module>
app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 124, in run
_sys.exit(main(argv))
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/tools/freeze_graph.py", line 249, in main
FLAGS.saved_model_tags)
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/tools/freeze_graph.py", line 227, in freeze_graph
input_graph_def = _parse_input_graph_proto(input_graph, input_binary)
File "/home/my_username/tensorflow/bazel-bin/tensorflow/python/tools/freeze_graph.runfiles/org_tensorflow/tensorflow/python/tools/freeze_graph.py", line 171, in _parse_input_graph_proto
text_format.Merge(f.read(), input_graph_def)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 525, in Merge
descriptor_pool=descriptor_pool)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 579, in MergeLines
return parser.MergeLines(lines, message)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 612, in MergeLines
self._ParseOrMerge(lines, message)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 627, in _ParseOrMerge
self._MergeField(tokenizer, message)
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 671, in _MergeField
name = tokenizer.ConsumeIdentifierOrNumber()
File "/home/my_username/.cache/bazel/_bazel_my_username/3572bc2aff1de1dd37356cf341944e54/execroot/org_tensorflow/bazel-out/k8-opt/bin/tensorflow/python/tools/freeze_graph.runfiles/protobuf_archive/python/google/protobuf/text_format.py", line 1144, in ConsumeIdentifierOrNumber
raise self.ParseError('Expected identifier or number, got %s.' % result)
google.protobuf.text_format.ParseError: 2:1 : Expected identifier or number, got `.

Я экспортирую ssd_mobilenet_v1_coco_2017_11_17 так же, как для практики. Я намерен экспортировать мои собственные обученные модели и проверить результаты с этим программа.
Я построил TensorFlow 1.5 с использованием Bazel v0.11.1. Я подтвердил установку, используя следующий фрагмент кода, представленный на веб-сайте TensorFlow;

# Python
import tensorflow as tf
hello = tf.constant('Hello, TensorFlow!')
sess = tf.Session()
print(sess.run(hello))

Я также запустил пример ноутбука iPython для обнаружения объектов, и это сработало.

Я использую Ubuntu 17.10.1 на ноутбуке с процессором Intel Core i5-8250U, 8 ГБ ОЗУ, 1 ТБ HDD и графическим процессором NVIDIA MX150 (2 ГБ). Пожалуйста помоги. Как экспортировать обученную модель в C ++?