某些Python对象未绑定到检查点值

问题描述

我正在尝试使用Tensorflow 2.0 Object Detection API。我完成了the official tutorial之后的安装,并通过了所有测试。但是,当我尝试运行主模块时,我不断收到一条我不理解的错误消息。这是我的运行方式:

python model_main_tf2.py --model_dir=ssd_resnet50_v1_fpn_640x640_coco17_tpu-8 --pipeline_config_path=ssd_resnet50_v1_fpn_640x640_coco17_tpu-8/pipeline.config

这是错误消息的开头:

Traceback (most recent call last):
  File "model_main_tf2.py",line 113,in <module>
    tf.compat.v1.app.run()
  File "/home/hd/hd_hd/hd_rs239/.conda/envs/jan_tf2/lib/python3.7/site-packages/tensorflow/python/platform/app.py",line 40,in run
    _run(main=main,argv=argv,flags_parser=_parse_flags_tolerate_undef)
  File "/home/hd/hd_hd/hd_rs239/.conda/envs/jan_tf2/lib/python3.7/site-packages/absl/app.py",line 299,in run
    _run_main(main,args)
  File "/home/hd/hd_hd/hd_rs239/.conda/envs/jan_tf2/lib/python3.7/site-packages/absl/app.py",line 250,in _run_main
    sys.exit(main(argv))
  File "model_main_tf2.py",line 110,in main
    record_summaries=FLAGS.record_summaries)
  File "/home/hd/hd_hd/hd_rs239/.conda/envs/jan_tf2/lib/python3.7/site-packages/object_detection/model_lib_v2.py",line 569,in train_loop
    unpad_groundtruth_tensors)
  File "/home/hd/hd_hd/hd_rs239/.conda/envs/jan_tf2/lib/python3.7/site-packages/object_detection/model_lib_v2.py",line 383,in load_fine_tune_checkpoint
    ckpt.restore(checkpoint_path).assert_existing_objects_matched()
  File "/home/hd/hd_hd/hd_rs239/.conda/envs/jan_tf2/lib/python3.7/site-packages/tensorflow/python/training/tracking/util.py",line 791,in assert_existing_objects_matched
    (list(unused_python_objects),))
AssertionError: Some Python objects were not bound to checkpointed values,likely due to changes in the Python program: [SyncOnReadVariable:{
  0: <tf.Variable 'conv2_block1_0_bn/moving_variance:0' shape=(256,) dtype=float32,numpy=
array([1.,1.,

在pipeline.config中,我这样指定一个检查点:

  fine_tune_checkpoint: "ssd_resnet50_v1_fpn_640x640_coco17_tpu-8/checkpoint/ckpt-0" 

这些是ssd_resnet50_v1_fpn_640x640_coco17_tpu-8/checkpoint/内容

checkpoint  
ckpt-0.data-00000-of-00001  
ckpt-0.index

我已经搜索过Google,但是找不到任何答案。在this issue中,建议的解决方案已过时(不再建议替换的代码)。

问题:问题出在哪里,我该如何解决

我正在使用CentOS Linux 7的服务器上执行此操作。我正在使用Python 3.7。我是Tensorflow的新手,所以如果我缺少任何重要信息,请告诉我。

解决方法

从您提供的文件名(ssd_resnet50_v1_fpn_640x640_coco17_tpu-8),我可以看到您正在尝试使用对象检测任务。因此,在您的pipeline.config文件中更改以下行:

fine_tune_checkpoint_type: "classification"

收件人:

fine_tune_checkpoint_type: "detection"

这应该可以解决您的问题。

,

对我来说,检查特征提取器的类型很有用。我在 pipeline.config 中将 type: "mobilenet_v2" 更改为 type: "mobilenet_v2_fpn_sep_conv"。它开始工作。