it seems the pretrained model architecture is different from the architecutre in train_nets.py
Traceback (most recent call last):
File "train_nets.py", line 212, in
saver.restore(sess, ckpt.model_checkpoint_path)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1322, in restore
err, "a mismatch between the current graph and the graph")
tensorflow.python.framework.errors_impl.InvalidArgumentError: Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Assign requires shapes of both tensors to match. lhs shape= [128] rhs shape= [192]
[[node save/Assign_190 (defined at train_nets.py:201) ]]
Errors may have originated from an input operation.
Input Source operations connected to node save/Assign_190:
MobileFaceNet/Logits/LinearConv1x1/BatchNorm/moving_variance (defined at /DATA/app/OCR/zhangfs/mobile/MobileFaceNet_TF-master/nets/MobileFaceNet.py:231)
Original stack trace for 'save/Assign_190':
File "train_nets.py", line 201, in
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=args.saver_maxkeep)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 825, in init
self.build()
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 837, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 875, in _build
build_restore=build_restore)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 508, in _build_internal
restore_sequentially, reshape)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 350, in _AddRestoreOps
assign_ops.append(saveable.restore(saveable_tensors, shapes))
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saving/saveable_object_util.py", line 72, in restore
self.op.get_shape().is_fully_defined())
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/state_ops.py", line 227, in assign
validate_shape=validate_shape)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_state_ops.py", line 66, in assign
use_locking=use_locking, name=name)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
op_def=op_def)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2005, in init
self._traceback = tf_stack.extract_stack()
it seems the pretrained model architecture is different from the architecutre in train_nets.py
Traceback (most recent call last): File "train_nets.py", line 212, in
saver.restore(sess, ckpt.model_checkpoint_path)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1322, in restore
err, "a mismatch between the current graph and the graph")
tensorflow.python.framework.errors_impl.InvalidArgumentError: Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Assign requires shapes of both tensors to match. lhs shape= [128] rhs shape= [192] [[node save/Assign_190 (defined at train_nets.py:201) ]]
Errors may have originated from an input operation. Input Source operations connected to node save/Assign_190: MobileFaceNet/Logits/LinearConv1x1/BatchNorm/moving_variance (defined at /DATA/app/OCR/zhangfs/mobile/MobileFaceNet_TF-master/nets/MobileFaceNet.py:231)
Original stack trace for 'save/Assign_190': File "train_nets.py", line 201, in
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=args.saver_maxkeep)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 825, in init
self.build()
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 837, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 875, in _build
build_restore=build_restore)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 508, in _build_internal
restore_sequentially, reshape)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 350, in _AddRestoreOps
assign_ops.append(saveable.restore(saveable_tensors, shapes))
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saving/saveable_object_util.py", line 72, in restore
self.op.get_shape().is_fully_defined())
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/state_ops.py", line 227, in assign
validate_shape=validate_shape)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_state_ops.py", line 66, in assign
use_locking=use_locking, name=name)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
op_def=op_def)
File "/DATA/app/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2005, in init
self._traceback = tf_stack.extract_stack()