text-to-image
text-to-image copied to clipboard
paarthneekhara
Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint.
i try to use pre trained model and got erro below:
Traceback (most recent call last): File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call return fn(*args) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1319, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "d_bn1/moving_mean" not found in checkpoint files Data/Models/latest_model_flowers_temp.ckpt [[{{node save/RestoreV2}} = RestoreV2[dtypes=[DT_FLOAT, 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/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1546, in restore {self.saver_def.filename_tensor_name: save_path}) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 929, in run run_metadata_ptr) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1152, in _run feed_dict_tensor, options, run_metadata) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1328, in _do_run run_metadata) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1348, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "d_bn1/moving_mean" not found in checkpoint files Data/Models/latest_model_flowers_temp.ckpt [[node save/RestoreV2 (defined at generate_images.py:67) = RestoreV2[dtypes=[DT_FLOAT, 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 "generate_images.py", line 107, in
NotFoundError (see above for traceback): Tensor name "d_bn1/moving_mean" not found in checkpoint files Data/Models/latest_model_flowers_temp.ckpt [[node save/RestoreV2 (defined at generate_images.py:67) = RestoreV2[dtypes=[DT_FLOAT, 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/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1556, in restore names_to_keys = object_graph_key_mapping(save_path) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1830, in object_graph_key_mapping checkpointable.OBJECT_GRAPH_PROTO_KEY) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 371, in get_tensor status) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 528, in exit c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.NotFoundError: _CHECKPOINTABLE_OBJECT_GRAPH not found in checkpoint file
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "generate_images.py", line 107, in
Tensor name "d_bn1/moving_mean" not found in checkpoint files Data/Models/latest_model_flowers_temp.ckpt [[node save/RestoreV2 (defined at generate_images.py:67) = RestoreV2[dtypes=[DT_FLOAT, 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 "generate_images.py", line 107, in
NotFoundError (see above for traceback): 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:
Tensor name "d_bn1/moving_mean" not found in checkpoint files Data/Models/latest_model_flowers_temp.ckpt [[node save/RestoreV2 (defined at generate_images.py:67) = RestoreV2[dtypes=[DT_FLOAT, 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)]]
I also encountered the same error message. Have you solved it?
我尝试使用预先训练过的模型，并在下面得到错误：
回溯（最近一次调用最后一次）： 文件“/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py”，第1334行，在_do_call中 返回fn（* args） 文件“/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py”，第1319行，在_run_fn 选项中，feed_dict，fetch_list，target_list，run_metadata） 文件“/ home / lucao /anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py“，第1407行，在_call_tf_sessionrun run_metadata中） tensorflow.python.framework.errors_impl.NotFoundError：未找到张量名称”d_bn1 / moving_mean“在检查点文件Data / Models / latest_model_flowers_temp.ckpt中 [[{{node save / RestoreV2}} = RestoreV2 [dtypes = [DT_FLOAT，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）]]
在处理上述异常期间，发生了另一个异常：
Traceback（最近一次调用最后一次）： 文件“/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py”，第1546行，在restore {self.saver_def.filename_tensor_name： save_path}） 文件“/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py”，第929行，运行 run_metadata_ptr） 文件“/ home / lucao / anaconda3 / lib /python3.6/site-packages/tensorflow/python/client/session.py“，第1152行，在_run feed_dict_tensor，options，run_metadata中） 文件”/home/lucao/anaconda3/lib/python3.6/site-packages/ tensorflow / python / client / session.py“，第1328行，在_do_run run_metadata中） 文件”/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session。py“，第1348行，在_do_call中 raise type（e）（node_def，op，message） tensorflow.python.framework.errors_impl.NotFoundError：在检查点文件中找不到Tensor名称“d_bn1 / moving_mean”Data / Models / latest_model_flowers_temp.ckpt [[node save / RestoreV2（定义于generate_images.py:67）= RestoreV2 [dtypes = [DT_FLOAT，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 "generate_images.py", line 107, in main() File "generate_images.py", line 67, in main saver = tf.train.Saver() File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1102, in init self.build() File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1114, in build self._build(self._filename, build_save=True, build_restore=True) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1151, in _build build_save=build_save, build_restore=build_restore) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 795, in _build_internal restore_sequentially, reshape) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 406, in _AddRestoreOps restore_sequentially) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 862, in bulk_restore return io_ops.restore_v2(filename_tensor, names, slices, dtypes) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1466, in restore_v2 shape_and_slices=shape_and_slices, dtypes=dtypes, name=name) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper op_def=op_def) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func return func(*args, **kwargs) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op op_def=op_def) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in init self._traceback = tf_stack.extract_stack()
NotFoundError (see above for traceback): Tensor name "d_bn1/moving_mean" not found in checkpoint files Data/Models/latest_model_flowers_temp.ckpt [[node save/RestoreV2 (defined at generate_images.py:67) = RestoreV2[dtypes=[DT_FLOAT, 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/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1556, in restore names_to_keys = object_graph_key_mapping(save_path) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1830, in object_graph_key_mapping checkpointable.OBJECT_GRAPH_PROTO_KEY) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 371, in get_tensor status) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 528, in exit c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.NotFoundError: _CHECKPOINTABLE_OBJECT_GRAPH not found in checkpoint file
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "generate_images.py", line 107, in main() File "generate_images.py", line 68, in main saver.restore(sess, args.model_path) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1562, 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:
Tensor name "d_bn1/moving_mean" not found in checkpoint files Data/Models/latest_model_flowers_temp.ckpt [[node save/RestoreV2 (defined at generate_images.py:67) = RestoreV2[dtypes=[DT_FLOAT, 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 "generate_images.py", line 107, in main() File "generate_images.py", line 67, in main saver = tf.train.Saver() File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1102, in init self.build() File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1114, in build self._build(self._filename, build_save=True, build_restore=True) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1151, in _build build_save=build_save, build_restore=build_restore) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 795, in _build_internal restore_sequentially, reshape) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 406, in _AddRestoreOps restore_sequentially) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 862, in bulk_restore return io_ops.restore_v2(filename_tensor, names, slices, dtypes) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1466, in restore_v2 shape_and_slices=shape_and_slices, dtypes=dtypes, name=name) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper op_def=op_def) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func return func(*args, **kwargs) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op op_def=op_def) File "/home/lucao/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in init self._traceback = tf_stack.extract_stack()
NotFoundError（参见上面的回溯）：从检查点恢复失败。这很可能是由于检查点中缺少变量名称或其他图形键。请确保您没有根据检查点更改预期的图表。原始错误：
在检查点文件中找不到张量名“d_bn1 / moving_mean”Data / Models / latest_model_flowers_temp.ckpt [[node save / RestoreV2（在generate_images.py:67中定义）= RestoreV2 [dtypes = [DT_FLOAT，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）]]
I also encountered the same error message. Have you solved it?
Did you guys solve this? I could really use help here. I get the same error @coderzjw @caolusg
Writing tf.reset_default_graph() before training and saving could have made the checkpoint restorable @coderzjw @caolusg
Writing tf.reset_default_graph() before training and saving could have made the checkpoint restorable @coderzjw @caolusg
Hey so where should I write it?
Writing tf.reset_default_graph() before training and saving could have made the checkpoint restorable @coderzjw @caolusg
: Tensor("moments/moments_1/mean:0", shape=(512,), dtype=float32) must be from the same graph as Tensor("g_bn0/g_bn0/moments/moments_1/mean/ExponentialMovingAverage:0", shape=(512,), dtype=float32_ref).
I get this error when I write the above line, help!