TF-SENet icon indicating copy to clipboard operation
TF-SENet copied to clipboard

I have one issue, when i train model. Key conv1/7x7_s2/bn/beta/Momentum not found in checkpoint is not found.

Open chanyixialex opened this issue 7 years ago • 1 comments

tensorflow.python.framework.errors_impl.NotFoundError: Key conv1/7x7_s2/bn/beta/Momentum not found in checkpoint │············································· [[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)]] │············································· [[Node: save/RestoreV2/_301 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_│············································· name="edge_306_save/RestoreV2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]] │············································· │············································· Caused by op 'save/RestoreV2', defined at: │············································· File "SE_resnext.py", line 272, in │············································· saver = tf.train.Saver(tf.global_variables()) │············································· File "/vol/venvs/tf1.7/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1311, in init │············································· self.build() │············································· File "/vol/venvs/tf1.7/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 "/vol/venvs/tf1.7/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1357, in _build │············································· build_save=build_save, build_restore=build_restore) │············································· File "/vol/venvs/tf1.7/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 809, in _build_internal │············································· restore_sequentially, reshape) │············································· File "/vol/venvs/tf1.7/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 448, in _AddRestoreOps │············································· restore_sequentially) │············································· File "/vol/venvs/tf1.7/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 "/vol/venvs/tf1.7/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 "/vol/venvs/tf1.7/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper │············································· op_def=op_def) │············································· File "/vol/venvs/tf1.7/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3290, in create_op │············································· op_def=op_def) │············································· File "/vol/venvs/tf1.7/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 conv1/7x7_s2/bn/beta/Momentum not found in checkpoint │············································· [[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)]] │············································· [[Node: save/RestoreV2/_301 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_│············································· name="edge_306_save/RestoreV2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]]

chanyixialex avatar Sep 28 '18 03:09 chanyixialex

@chanyixialex Momentum is not a part of model param, it's used by optimizer, so isn't included in the provided checkpoint

HiKapok avatar Sep 28 '18 03:09 HiKapok