tensorflow模型恢复问题——saver.restore
在恢复分类模型中出现问题，而且看起来很吓人那种。
2019-11-28 17:31:37.421411: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at save_restore_v2_ops.cc:184 : Not found: Key batch_normalization_1/beta not found in checkpoint
Traceback (most recent call last):
File "D:\python\lib\site-packages\tensorflow\python\client\session.py", line 1356, in _do_call
return fn(*args)
File "D:\python\lib\site-packages\tensorflow\python\client\session.py", line 1341, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "D:\python\lib\site-packages\tensorflow\python\client\session.py", line 1429, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.NotFoundError: Key batch_normalization_1/beta not found in checkpoint
[[{{node save/RestoreV2}}]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 1286, in restore
{self.saver_def.filename_tensor_name: save_path})
File "D:\python\lib\site-packages\tensorflow\python\client\session.py", line 950, in run
run_metadata_ptr)
File "D:\python\lib\site-packages\tensorflow\python\client\session.py", line 1173, in _run
feed_dict_tensor, options, run_metadata)
File "D:\python\lib\site-packages\tensorflow\python\client\session.py", line 1350, in _do_run
run_metadata)
File "D:\python\lib\site-packages\tensorflow\python\client\session.py", line 1370, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.NotFoundError: Key batch_normalization_1/beta not found in checkpoint
[[node save/RestoreV2 (defined at my_guess_end.py:256) ]]
Original stack trace for 'save/RestoreV2':
File "my_guess_end.py", line 271, in
tf.compat.v1.app.run()
File "D:\python\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "D:\python\lib\site-packages\absl\app.py", line 300, in run
_run_main(main, args)
File "D:\python\lib\site-packages\absl\app.py", line 251, in _run_main
sys.exit(main(argv))
File "my_guess_end.py", line 256, in main
saver = tf.compat.v1.train.Saver()
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 825, in __init__
self.build()
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 837, in build
self._build(self._filename, build_save=True, build_restore=True)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 875, in _build
build_restore=build_restore)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 508, in _build_internal
restore_sequentially, reshape)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 328, in _AddRestoreOps
restore_sequentially)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 575, in bulk_restore
return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
File "D:\python\lib\site-packages\tensorflow\python\ops\gen_io_ops.py", line 1779, in restore_v2
name=name)
File "D:\python\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "D:\python\lib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "D:\python\lib\site-packages\tensorflow\python\framework\ops.py", line 3616, in create_op
op_def=op_def)
File "D:\python\lib\site-packages\tensorflow\python\framework\ops.py", line 2005, in __init__
self._traceback = tf_stack.extract_stack()
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 1296, in restore
names_to_keys = object_graph_key_mapping(save_path)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 1614, in object_graph_key_mapping
object_graph_string = reader.get_tensor(trackable.OBJECT_GRAPH_PROTO_KEY)
File "D:\python\lib\site-packages\tensorflow\python\pywrap_tensorflow_internal.py", line 678, in get_tensor
return CheckpointReader_GetTensor(self, compat.as_bytes(tensor_str))
tensorflow.python.framework.errors_impl.NotFoundError: Key _CHECKPOINTABLE_OBJECT_GRAPH not found in checkpoint
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "my_guess_end.py", line 271, in
tf.compat.v1.app.run()
File "D:\python\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "D:\python\lib\site-packages\absl\app.py", line 300, in run
_run_main(main, args)
File "D:\python\lib\site-packages\absl\app.py", line 251, in _run_main
sys.exit(main(argv))
File "my_guess_end.py", line 257, in main
saver.restore(sess, model_checkpoint_path)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 1302, in restore
err, "a Variable name or other graph key that is missing")
tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Key batch_normalization_1/beta not found in checkpoint
[[node save/RestoreV2 (defined at my_guess_end.py:256) ]]
Original stack trace for 'save/RestoreV2':
File "my_guess_end.py", line 271, in
tf.compat.v1.app.run()
File "D:\python\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "D:\python\lib\site-packages\absl\app.py", line 300, in run
_run_main(main, args)
File "D:\python\lib\site-packages\absl\app.py", line 251, in _run_main
sys.exit(main(argv))
File "my_guess_end.py", line 256, in main
saver = tf.compat.v1.train.Saver()
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 825, in __init__
self.build()
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 837, in build
self._build(self._filename, build_save=True, build_restore=True)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 875, in _build
build_restore=build_restore)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 508, in _build_internal
restore_sequentially, reshape)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 328, in _AddRestoreOps
restore_sequentially)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 575, in bulk_restore
return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
File "D:\python\lib\site-packages\tensorflow\python\ops\gen_io_ops.py", line 1779, in restore_v2
name=name)
File "D:\python\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "D:\python\lib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "D:\python\lib\site-packages\tensorflow\python\framework\ops.py", line 3616, in create_op
op_def=op_def)
File "D:\python\lib\site-packages\tensorflow\python\framework\ops.py", line 2005, in __init__
self._traceback = tf_stack.extract_stack() 这种情况下，直接用原有方法恢复，测试下，only恢复模型，try
卧槽，老子又试了之前的恢复模型的方法，告诉我没有变量save
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 825, in __init__
self.build()
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 837, in build
self._build(self._filename, build_save=True, build_restore=True)
File "D:\python\lib\site-packages\tensorflow\python\training\saver.py", line 862, in _build
raise ValueError("No variables to save")
ValueError: No variables to save难道先加载构造的model？
是的，先加载构造好的模型，再加载训练好的模型[有模型参数]。加载成功了。
but in fact also has the first prolem,so Y ?
search for the problem,Found that they say the version is the key,but I always in the same windows ,no more than one version !!什么鬼，算了，寡人累了，先加载这个模型吧。
寡人发现这个问题应该是MTCNN引入的，在我用MTCNN检测人脸后这个程序就出现了这个鬼，可能这玩意也有模型加载，所以两个模型冲突了。我将前者搞成函数？？
果然是，经检查，引入MTCNN的确会造成模型加载失败，这是说明MTCNN是个傻逼，没做好，但加载h5模型没有问题，tf还是不行啊。但是我还是依靠小明哥的帅气，啊呸，智慧，完美解决了问题。哈哈
人生艰难，但请足够相信小明哥。
另外有相关问题可以加入QQ群讨论，不设微信群
QQ群：868373192
语音深度学习群