使用脚本跑slim的train_image_classifier.py文件出现问题

yizhangbiao 2018-06-20 03:41:25

使用脚本跑slim的train_image_classifier.py文件,跑得是resnet出现问题如下

INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.NotFoundError'>, Key resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta not found in checkpoint

	 [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_INT64, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]



Caused by op 'save/RestoreV2', defined at:

  File "/home/yizhangbiao/PycharmProjects/resnet/slim/train_image_classifier.py", line 581, in <module>

    tf.app.run()

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run

    _sys.exit(main(argv))

  File "/home/yizhangbiao/PycharmProjects/resnet/slim/train_image_classifier.py", line 577, in main

    sync_optimizer=optimizer if FLAGS.sync_replicas else None)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/learning.py", line 658, in train

    saver = saver or tf_saver.Saver()

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1311, in __init__

    self.build()

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1320, in build

    self._build(self._filename, build_save=True, build_restore=True)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1357, in _build

    build_save=build_save, build_restore=build_restore)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 809, in _build_internal

    restore_sequentially, reshape)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 448, in _AddRestoreOps

    restore_sequentially)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 860, in bulk_restore

    return io_ops.restore_v2(filename_tensor, names, slices, dtypes)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1458, in restore_v2

    shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper

    op_def=op_def)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3290, in create_op

    op_def=op_def)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1654, in __init__

    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access



NotFoundError (see above for traceback): Key resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta not found in checkpoint

	 [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_INT64, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]



Traceback (most recent call last):

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call

    return fn(*args)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1312, in _run_fn

    options, feed_dict, fetch_list, target_list, run_metadata)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1420, in _call_tf_sessionrun

    status, run_metadata)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 516, in __exit__

    c_api.TF_GetCode(self.status.status))

tensorflow.python.framework.errors_impl.NotFoundError: Key resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta not found in checkpoint

	 [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_INT64, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]



During handling of the above exception, another exception occurred:



Traceback (most recent call last):

  File "/home/yizhangbiao/PycharmProjects/resnet/slim/train_image_classifier.py", line 581, in <module>

    tf.app.run()

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run

    _sys.exit(main(argv))

  File "/home/yizhangbiao/PycharmProjects/resnet/slim/train_image_classifier.py", line 577, in main

    sync_optimizer=optimizer if FLAGS.sync_replicas else None)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/learning.py", line 747, in train

    master, start_standard_services=False, config=session_config) as sess:

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/contextlib.py", line 81, in __enter__

    return next(self.gen)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/supervisor.py", line 1000, in managed_session

    self.stop(close_summary_writer=close_summary_writer)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/supervisor.py", line 828, in stop

    ignore_live_threads=ignore_live_threads)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/coordinator.py", line 389, in join

    six.reraise(*self._exc_info_to_raise)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/six.py", line 693, in reraise

    raise value

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/supervisor.py", line 989, in managed_session

    start_standard_services=start_standard_services)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/supervisor.py", line 726, in prepare_or_wait_for_session

    init_feed_dict=self._init_feed_dict, init_fn=self._init_fn)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/session_manager.py", line 275, in prepare_session

    config=config)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/session_manager.py", line 207, in _restore_checkpoint

    saver.restore(sess, ckpt.model_checkpoint_path)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1775, in restore

    {self.saver_def.filename_tensor_name: save_path})

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 905, in run

    run_metadata_ptr)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1140, in _run

    feed_dict_tensor, options, run_metadata)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run

    run_metadata)

  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call

    raise type(e)(node_def, op, message)

tensorflow.python.framework.errors_impl.NotFoundError: Key resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta not found in checkpoint

	 [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_INT64, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]

请问是怎么回事

...全文

327 3 打赏收藏转发到动态举报

写回复

用AI写文章

3 条回复

切换为时间正序

请发表友善的回复…

发表回复

BryceRui 2021-01-08

打赏
举报

https://github.com/tensorflow/models/issues/4940 设置from_detection_checkpoint为true试试

m0_45192492 2021-01-08

打赏
举报

您好，请问解决了么

yizhangbiao 2018-06-20

打赏
举报

这是剩下的报错


Caused by op 'save/RestoreV2', defined at:
  File "/home/yizhangbiao/PycharmProjects/resnet/slim/train_image_classifier.py", line 581, in <module>
    tf.app.run()
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run
    _sys.exit(main(argv))
  File "/home/yizhangbiao/PycharmProjects/resnet/slim/train_image_classifier.py", line 577, in main
    sync_optimizer=optimizer if FLAGS.sync_replicas else None)
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/learning.py", line 658, in train
    saver = saver or tf_saver.Saver()
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1311, in __init__
    self.build()
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1320, in build
    self._build(self._filename, build_save=True, build_restore=True)
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1357, in _build
    build_save=build_save, build_restore=build_restore)
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 809, in _build_internal
    restore_sequentially, reshape)
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 448, in _AddRestoreOps
    restore_sequentially)
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 860, in bulk_restore
    return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1458, in restore_v2
    shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3290, in create_op
    op_def=op_def)
  File "/home/yizhangbiao/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1654, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

NotFoundError (see above for traceback): Key resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta not found in checkpoint
	 [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_INT64, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]