一些 Python 个对象未绑定到检查点值

Question

我正在尝试开始使用 Tensorflow 2.0 Object Detection API. I have gone through the installation following the official tutorial，并且我通过了所有测试。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。我是这样运行的：

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

这是错误信息的开头：

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., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,

在 pipeline.config 中，我指定了这样一个检查点：

  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/的内容：

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

我已搜索 Google 但找不到任何答案。在 this issue 中，建议的解决方案已过时（他们建议替换的代码已不存在）。

问题：问题是什么，如何解决？

我在装有 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，所以如果我遗漏任何重要信息，请告诉我。

Answer 1

从您提供的文件名 (ssd_resnet50_v1_fpn_640x640_coco17_tpu-8)，我可以看出您正在尝试处理对象检测任务。因此，在您的 pipeline.config 文件中更改此行：

fine_tune_checkpoint_type: "classification"

收件人：

fine_tune_checkpoint_type: "detection"

这应该可以解决您的问题。

Answer 2

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"。它开始工作了。

一些 Python 个对象未绑定到检查点值

Some Python objects were not bound to checkpointed values

python

deep-learning

tensorflow

object-detection-api

tensorflow2.0