ns2250225 / python3_tf_slim_image_classify Goto Github PK

在终端敲入 python train_image_classifier.py
--checkpoint_exclude_scopes=InceptionV3/Logits,InceptionV3/AuxLogits
--trainable_scopes=InceptionV3/Logits,InceptionV3/AuxLogits
这个是训练最后一层的fine tune， ！！我想训练的可能是 最后三层！！，该如何fine tune呢，看了很久的源码，也没找到。
请帮忙解答一下.谢谢

我想训练全部层，而不只是最后一层。
所以我删去了trainable_scopes,

echo "1 epoch"
python slim/train_image_classifier.py \
  --train_dir=train_log \
  --dataset_name=gesture \
  --train_image_size=256 \
  --dataset_split_name=train \
  --dataset_dir=/data/workspace/MobilenetV2_image_classify-master/data_prepare/pic \
  --model_name="mobilenet_v2_140" \
  --checkpoint_path=pretrained/mobilenet_v2_1.4_224.ckpt \
  --checkpoint_exclude_scope=MobilenetV2/Logits, MobilenetV2/AuxLogits \
  --max_number_of_steps=10000 \
  --batch_size=16 \
  --learning_rate=0.001 \
  --learning_rate_decay_type=fixed \
  --save_interval_secs=300 \
  --save_summaries_secs=2 \
  --log_every_n_steps=10 \
  --optimizer=rmsprop \
  --weight_decay=0.00004 \
  --label_smoothing=0.1 \
  --num_clones=1 \
  --num_epochs_per_decay=2.5 \
  --moving_average_decay=0.9999 \
  --learning_rate_decay_factor=0.98 \
  --preprocessing_name="inception_v2"

运行时会报错：

INFO:tensorflow:Restoring parameters from pretrained/mobilenet_v2_1.4_224.ckpt
INFO:tensorflow:Error reported to Coordinator: <class '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= [6] rhs shape= [1001]
[[Node: save/Assign_10 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV2/Logits/Conv2d_1c_1x1/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MobilenetV2/Logits/Conv2d_1c_1x1/biases, save/RestoreV2:10)]]
Caused by op 'save/Assign_10', defined at:
File "slim/train_image_classifier.py", line 587, in
tf.app.run()
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "slim/train_image_classifier.py", line 574, in main
init_fn=_get_init_fn(),
File "slim/train_image_classifier.py", line 372, in _get_init_fn
ignore_missing_vars=FLAGS.ignore_missing_vars)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 695, in assign_from_checkpoint_fn
write_version=saver_pb2.SaverDef.V1)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1281, in init
self.build()
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1293, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1330, in _build
build_save=build_save, build_restore=build_restore)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 778, in _build_internal
restore_sequentially, reshape)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 419, in _AddRestoreOps
assign_ops.append(saveable.restore(saveable_tensors, shapes))
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 112, in restore
self.op.get_shape().is_fully_defined())
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/ops/state_ops.py", line 216, in assign
validate_shape=validate_shape)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/ops/gen_state_ops.py", line 60, in assign
use_locking=use_locking, name=name)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 454, in new_func
return func(*args, **kwargs)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3155, in create_op
op_def=op_def)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1717, in init
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): 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= [6] rhs shape= [1001]
[[Node: save/Assign_10 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV2/Logits/Conv2d_1c_1x1/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MobilenetV2/Logits/Conv2d_1c_1x1/biases, save/RestoreV2:10)]]
Traceback (most recent call last):
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1278, in _do_call
return fn(*args)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1263, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1350, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [6] rhs shape= [1001]
[[Node: save/Assign_10 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV2/Logits/Conv2d_1c_1x1/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MobilenetV2/Logits/Conv2d_1c_1x1/biases, save/RestoreV2:10)]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1725, in restore
{self.saver_def.filename_tensor_name: save_path})
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 877, in run
run_metadata_ptr)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1100, in _run
feed_dict_tensor, options, run_metadata)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1272, in _do_run
run_metadata)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1291, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [6] rhs shape= [1001]
[[Node: save/Assign_10 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV2/Logits/Conv2d_1c_1x1/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MobilenetV2/Logits/Conv2d_1c_1x1/biases, save/RestoreV2:10)]]
Caused by op 'save/Assign_10', defined at:
File "slim/train_image_classifier.py", line 587, in
tf.app.run()
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "slim/train_image_classifier.py", line 574, in main
init_fn=_get_init_fn(),
File "slim/train_image_classifier.py", line 372, in _get_init_fn
ignore_missing_vars=FLAGS.ignore_missing_vars)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 695, in assign_from_checkpoint_fn
write_version=saver_pb2.SaverDef.V1)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1281, in init
self.build()
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1293, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1330, in _build
build_save=build_save, build_restore=build_restore)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 778, in _build_internal
restore_sequentially, reshape)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 419, in _AddRestoreOps
assign_ops.append(saveable.restore(saveable_tensors, shapes))
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 112, in restore
self.op.get_shape().is_fully_defined())
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/ops/state_ops.py", line 216, in assign
validate_shape=validate_shape)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/ops/gen_state_ops.py", line 60, in assign
use_locking=use_locking, name=name)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 454, in new_func
return func(*args, **kwargs)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3155, in create_op
op_def=op_def)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1717, in init
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [6] rhs shape= [1001]
[[Node: save/Assign_10 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV2/Logits/Conv2d_1c_1x1/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MobilenetV2/Logits/Conv2d_1c_1x1/biases, save/RestoreV2:10)]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "slim/train_image_classifier.py", line 587, in
tf.app.run()
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "slim/train_image_classifier.py", line 580, in main
sync_optimizer=optimizer if FLAGS.sync_replicas else None)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/learning.py", line 748, in train
master, start_standard_services=False, config=session_config) as sess:
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/contextlib.py", line 81, in enter
return next(self.gen)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/supervisor.py", line 1005, in managed_session
self.stop(close_summary_writer=close_summary_writer)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/supervisor.py", line 833, in stop
ignore_live_threads=ignore_live_threads)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/coordinator.py", line 389, in join
six.reraise(*self._exc_info_to_raise)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/six.py", line 693, in reraise
raise value
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/supervisor.py", line 994, in managed_session
start_standard_services=start_standard_services)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/supervisor.py", line 731, in prepare_or_wait_for_session
init_feed_dict=self._init_feed_dict, init_fn=self._init_fn)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/session_manager.py", line 289, in prepare_session
init_fn(sess)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 697, in callback
saver.restore(session, model_path)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1759, 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= [6] rhs shape= [1001]
[[Node: save/Assign_10 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV2/Logits/Conv2d_1c_1x1/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MobilenetV2/Logits/Conv2d_1c_1x1/biases, save/RestoreV2:10)]]
Caused by op 'save/Assign_10', defined at:
File "slim/train_image_classifier.py", line 587, in
tf.app.run()
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "slim/train_image_classifier.py", line 574, in main
init_fn=_get_init_fn(),
File "slim/train_image_classifier.py", line 372, in _get_init_fn
ignore_missing_vars=FLAGS.ignore_missing_vars)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 695, in assign_from_checkpoint_fn
write_version=saver_pb2.SaverDef.V1)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1281, in init
self.build()
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1293, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1330, in _build
build_save=build_save, build_restore=build_restore)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 778, in _build_internal
restore_sequentially, reshape)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 419, in _AddRestoreOps
assign_ops.append(saveable.restore(saveable_tensors, shapes))
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 112, in restore
self.op.get_shape().is_fully_defined())
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/ops/state_ops.py", line 216, in assign
validate_shape=validate_shape)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/ops/gen_state_ops.py", line 60, in assign
use_locking=use_locking, name=name)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 454, in new_func
return func(*args, **kwargs)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3155, in create_op
op_def=op_def)
File "/data/zhaowenlin/anaconda3/envs/tf10_mobilenet/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1717, in init
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): 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= [6] rhs shape= [1001]
[[Node: save/Assign_10 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV2/Logits/Conv2d_1c_1x1/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MobilenetV2/Logits/Conv2d_1c_1x1/biases, save/RestoreV2:10)]]

这里用的模型是官方提供的。
请问我应该怎么解决这个问题？