Question

大家好，我是机器学习的新手，我正在尝试在CPU上构建自定义对象检测模型。但是，键入以下内容后，我会在下面收到此错误：

python train.py --logtostderr --train_dir=training/ -pipeline_config_path=training/ssd_mobilenet_v1_coco.config.

任何输入将不胜感激。我的路径已配置，但问题似乎出现了。

Traceback (most recent call last):
  File "train.py", line 184, in <module>
    tf.app.run()
  File "C:\Users\Thremane\Anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\platform\app.py", line 124, in run
    _sys.exit(main(argv))
  File "C:\Users\Thremane\Anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\util\deprecation.py", line 136, in new_func
    return func(*args, **kwargs)
  File "train.py", line 180, in main
    graph_hook_fn=graph_rewriter_fn)
  File "C:\Users\Thremane\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.5.egg\object_detection\legacy\trainer.py", line 304, in train
    train_config.optimizer)
  File "C:\Users\Thremane\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.5.egg\object_detection\builders\optimizer_builder.py", line 45, in build
    global_step=global_step)
  File "C:\Users\Thremane\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.5.egg\object_detection\builders\optimizer_builder.py", line 113, in _create_learning_rate
    staircase=config.staircase)
  File "C:\Users\Thremane\Anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.5.egg\object_detection\utils\learning_schedules.py", line 79, in exponential_decay_with_burnin
    if tf.executing_eagerly():
AttributeError: module 'tensorflow' has no attribute 'executing_eagerly'

Answer 1

我弄清楚了问题所在。 TensorFlow的版本和预训练模型必须兼容。我在我的环境中安装了Tensorflow v1.5和相应的Comit软件包。现在，我正在训练我的模型。

AttributeError：模块“ tensorflow”没有属性“ executing_eagerly”

1 个答案: