Блог

Главная - Вопросы по программированию - Неудачное обучение обнаружению объектов с использованием Faster-RCNN-Resnet50 (справка)

Неудачное обучение обнаружению объектов с использованием Faster-RCNN-Resnet50 (справка)

#python #tensorflow #model #faster-rcnn #mobilenet

#python #тензорный поток #Модель #быстрее-rcnn #mobilenet

Вопрос:

Используя тот же код с помощью https://github.com/nicknochnack/TFODCourse , я смог выполнить тренировку с использованием my_ssd_mobilenet . Однако, когда я пытался изменить модель на любые более быстрые модели RCNN, я получил ошибку, как показано ниже. Я видел, как кто-то публиковал это раньше, но это не работает.

Ошибка:

 (tfod) C:DeepLearningTensorflowTFODCourse>python Tensorflowmodelsresearchobject_detectionmodel_main_tf2.py --model_dir=Tensorflowworkspacemodelsmy_faster_rcnn --pipeline_config_path=Tensorflowworkspacemodelsmy_faster_rcnnpipeline.config --num_train_steps=2000
2021-12-09 23:11:22.910468: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1900] Ignoring visible gpu device (device: 0, name: GeForce 610M, pci bus id: 0000:01:00.0, compute capability: 2.1) with Cuda compute capability 2.1. The minimum required Cuda capability is 3.5.
2021-12-09 23:11:22.912317: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
WARNING:tensorflow:There are non-GPU devices in `tf.distribute.Strategy`, not using nccl allreduce.
W1209 23:11:23.156067  1028 cross_device_ops.py:1387] There are non-GPU devices in `tf.distribute.Strategy`, not using nccl allreduce.
INFO:tensorflow:Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:CPU:0',)
I1209 23:11:23.187321  1028 mirrored_strategy.py:376] Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:CPU:0',)
INFO:tensorflow:Maybe overwriting train_steps: 2000
I1209 23:11:23.234195  1028 config_util.py:552] Maybe overwriting train_steps: 2000
INFO:tensorflow:Maybe overwriting use_bfloat16: False
I1209 23:11:23.234195  1028 config_util.py:552] Maybe overwriting use_bfloat16: False
Traceback (most recent call last):
  File "Tensorflowmodelsresearchobject_detectionmodel_main_tf2.py", line 115, in <module>
    tf.compat.v1.app.run()
  File "C:UsersJJanaconda3envstfodlibsite-packagestensorflowpythonplatformapp.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "C:UsersJJanaconda3envstfodlibsite-packagesabslapp.py", line 303, in run
    _run_main(main, args)
  File "C:UsersJJanaconda3envstfodlibsite-packagesabslapp.py", line 251, in _run_main
    sys.exit(main(argv))
  File "Tensorflowmodelsresearchobject_detectionmodel_main_tf2.py", line 106, in main
    model_lib_v2.train_loop(
  File "C:UsersJJanaconda3envstfodlibsite-packagesobject_detection-0.1-py3.8.eggobject_detectionmodel_lib_v2.py", line 541, in train_loop
    detection_model = MODEL_BUILD_UTIL_MAP['detection_model_fn_base'](
  File "C:UsersJJanaconda3envstfodlibsite-packagesobject_detection-0.1-py3.8.eggobject_detectionbuildersmodel_builder.py", line 1249, in build
    return build_func(getattr(model_config, meta_architecture), is_training,
  File "C:UsersJJanaconda3envstfodlibsite-packagesobject_detection-0.1-py3.8.eggobject_detectionbuildersmodel_builder.py", line 400, in _build_ssd_model
    _check_feature_extractor_exists(ssd_config.feature_extractor.type)
  File "C:UsersJJanaconda3envstfodlibsite-packagesobject_detection-0.1-py3.8.eggobject_detectionbuildersmodel_builder.py", line 266, in _check_feature_extractor_exists
    raise ValueError('{} is not supported. See `model_builder.py` for features '
ValueError:  is not supported. See `model_builder.py` for features extractors compatible with different versions of Tensorflow
Метки: