Question

我正在尝试训练一个预训练的对象检测模型，以从我的自定义数据集中检测对象。一切都在Google Colab上运行。我准备了图像，创建了用于培训和测试的TFRecord文件，从源代码安装了Tensorflow对象检测API，并对其进行了测试。

首先，我怀疑这是PYTHONPATH问题，但是即使将带有config的文件夹添加到path上，它也不起作用。

这是我的命令行（如文档所示，我从研究文件夹调用脚本）：

#From the tensorflow/models/research/ directory
PIPELINE_CONFIG_PATH='/content/gdrive/My\ Drive/AI/grape4/work/model/ssd_mobilenet_v2_oid_v4.config'
MODEL_DIR=os.path.join('/content/gdrive/My\ Drive/AI/grape4/work', 'model')
NUM_TRAIN_STEPS=5000
NUM_EVAL_STEPS=1000

!python object_detection/model_main.py \
    --pipeline_config_path=${PIPELINE_CONFIG_PATH} \
    --model_dir=${MODEL_DIR} \
    --num_train_steps=${NUM_TRAIN_STEPS} \
    --num_eval_steps=${NUM_EVAL_STEPS} \
    --alsologtostderr

以下是我遇到的错误。我确认提到的文件存在于文件夹中。但是对我来说奇怪的是在跟踪中添加了$符号（美元符号）：

Traceback (most recent call last):
  File "object_detection/model_main.py", line 109, in <module>
    tf.app.run()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 300, in run
    _run_main(main, args)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "object_detection/model_main.py", line 71, in main
    FLAGS.sample_1_of_n_eval_on_train_examples))
  File "/usr/local/lib/python3.6/dist-packages/object_detection-0.1-py3.6.egg/object_detection/model_lib.py", line 605, in create_estimator_and_inputs
    pipeline_config_path, config_override=config_override)
  File "/usr/local/lib/python3.6/dist-packages/object_detection-0.1-py3.6.egg/object_detection/utils/config_util.py", line 103, in get_configs_from_pipeline_file
    proto_str = f.read()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/lib/io/file_io.py", line 122, in read
    self._preread_check()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/lib/io/file_io.py", line 84, in _preread_check
    compat.as_bytes(self.__name), 1024 * 512)
tensorflow.python.framework.errors_impl.NotFoundError: $/content/gdrive/My Drive/AI/grape4/work/model/ssd_mobilenet_v2_oid_v4.config; No such file or directory

有人知道问题可能在哪里吗？

Answer 1

我无法确切指出问题所在。但我认为可能存在两个问题：

1. The path thats pointing to the .config file might be wrong.
2. The .config file might be corrupted.

请查看这个问题，其中问题#1和#2的讨论非常清楚。我希望这会有所帮助！

tensorflow.python.framework.errors_impl.NotFoundError添加$符号

1 个答案: