GPh*_*ilo 17 python tensorflow tensorflow-estimator
我正在尝试使用我自己的数据集和类进行在imagenet上预训练的Inception-resnet v2模型的传输学习.我的原始代码库是对tf.slim样本的修改,我找不到了,现在我正在尝试使用tf.estimator.*框架重写相同的代码.
但是,我正在运行从预训练检查点加载一些权重的问题,用其默认初始值设定项初始化剩余的层.
研究这个问题,我发现了这个GitHub问题和这个问题,都提到了需要tf.train.init_from_checkpoint在我的问题中使用model_fn.我试过了,但由于两者都没有例子,我想我错了.
这是我的最小例子:
import sys
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
import tensorflow as tf
import numpy as np
import inception_resnet_v2
NUM_CLASSES = 900
IMAGE_SIZE = 299
def input_fn(mode, num_classes, batch_size=1):
# some code that loads images, reshapes them to 299x299x3 and batches them
return tf.constant(np.zeros([batch_size, 299, 299, 3], np.float32)), tf.one_hot(tf.constant(np.zeros([batch_size], np.int32)), NUM_CLASSES)
def model_fn(images, labels, num_classes, mode):
with tf.contrib.slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope()):
logits, end_points = inception_resnet_v2.inception_resnet_v2(images,
num_classes,
is_training=(mode==tf.estimator.ModeKeys.TRAIN))
predictions = {
'classes': tf.argmax(input=logits, axis=1),
'probabilities': tf.nn.softmax(logits, name='softmax_tensor')
}
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
exclude = ['InceptionResnetV2/Logits', 'InceptionResnetV2/AuxLogits']
variables_to_restore = tf.contrib.slim.get_variables_to_restore(exclude=exclude)
scopes = { os.path.dirname(v.name) for v in variables_to_restore }
tf.train.init_from_checkpoint('inception_resnet_v2_2016_08_30.ckpt',
{s+'/':s+'/' for s in scopes})
tf.losses.softmax_cross_entropy(onehot_labels=labels, logits=logits)
total_loss = tf.losses.get_total_loss() #obtain the regularization losses as well
# Configure the training op
if mode == tf.estimator.ModeKeys.TRAIN:
global_step = tf.train.get_or_create_global_step()
optimizer = tf.train.AdamOptimizer(learning_rate=0.00002)
train_op = optimizer.minimize(total_loss, global_step)
else:
train_op = None
return tf.estimator.EstimatorSpec(
mode=mode,
predictions=predictions,
loss=total_loss,
train_op=train_op)
def main(unused_argv):
# Create the Estimator
classifier = tf.estimator.Estimator(
model_fn=lambda features, labels, mode: model_fn(features, labels, NUM_CLASSES, mode),
model_dir='model/MCVE')
# Train the model
classifier.train(
input_fn=lambda: input_fn(tf.estimator.ModeKeys.TRAIN, NUM_CLASSES, batch_size=1),
steps=1000)
# Evaluate the model and print results
eval_results = classifier.evaluate(
input_fn=lambda: input_fn(tf.estimator.ModeKeys.EVAL, NUM_CLASSES, batch_size=1))
print()
print('Evaluation results:\n %s' % eval_results)
if __name__ == '__main__':
tf.app.run(main=main, argv=[sys.argv[0]])
这里inception_resnet_v2是在Tensorflow的模型库中的模型实现.
如果我运行这个脚本,我会收到一堆信息日志init_from_checkpoint,但是,在会话创建时,似乎它会尝试Logits从检查点加载权重并因为形状不兼容而失败.这是完整的追溯:
Traceback (most recent call last):
File "<ipython-input-6-06fadd69ae8f>", line 1, in <module>
runfile('C:/Users/1/Desktop/transfer_learning_tutorial-master/MCVE.py', wdir='C:/Users/1/Desktop/transfer_learning_tutorial-master')
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile
execfile(filename, namespace)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "C:/Users/1/Desktop/transfer_learning_tutorial-master/MCVE.py", line 77, in <module>
tf.app.run(main=main, argv=[sys.argv[0]])
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\platform\app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "C:/Users/1/Desktop/transfer_learning_tutorial-master/MCVE.py", line 68, in main
steps=1000)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\estimator\estimator.py", line 302, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\estimator\estimator.py", line 780, in _train_model
log_step_count_steps=self._config.log_step_count_steps) as mon_sess:
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\monitored_session.py", line 368, in MonitoredTrainingSession
stop_grace_period_secs=stop_grace_period_secs)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\monitored_session.py", line 673, in __init__
stop_grace_period_secs=stop_grace_period_secs)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\monitored_session.py", line 493, in __init__
self._sess = _RecoverableSession(self._coordinated_creator)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\monitored_session.py", line 851, in __init__
_WrappedSession.__init__(self, self._create_session())
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\monitored_session.py", line 856, in _create_session
return self._sess_creator.create_session()
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\monitored_session.py", line 554, in create_session
self.tf_sess = self._session_creator.create_session()
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\monitored_session.py", line 428, in create_session
init_fn=self._scaffold.init_fn)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\session_manager.py", line 279, in prepare_session
sess.run(init_op, feed_dict=init_feed_dict)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 889, in run
run_metadata_ptr)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1317, in _do_run
options, run_metadata)
File "C:\Users\1\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [900] rhs shape= [1001] [[Node: Assign_1145 = Assign[T=DT_FLOAT,
_class=["loc:@InceptionResnetV2/Logits/Logits/biases"], use_locking=true, validate_shape=true,
_device="/job:localhost/replica:0/task:0/device:CPU:0"](InceptionResnetV2/Logits/Logits/biases, checkpoint_initializer_1145)]]
使用时我做错了什么init_from_checkpoint？我们究竟应该如何"使用"它model_fn？为什么估算器试图Logits在我明确告诉它时不要从检查点加载'权重？
在评论中提出建议后,我尝试了其他方式来打电话tf.train.init_from_checkpoint.
{v.name: v.name}如果,如评论中所建议的,我替换了调用{v.name:v.name for v in variables_to_restore},我收到此错误:
ValueError: Assignment map with scope only name InceptionResnetV2/Conv2d_2a_3x3 should map
to scope only InceptionResnetV2/Conv2d_2a_3x3/weights:0. Should be 'scope/': 'other_scope/'.
{v.name: v}相反,如果我尝试使用name:variable映射,我会收到以下错误:
ValueError: Tensor InceptionResnetV2/Conv2d_2a_3x3/weights:0 is not found in
inception_resnet_v2_2016_08_30.ckpt checkpoint
{'InceptionResnetV2/Repeat_2/block8_4/Branch_1/Conv2d_0c_3x1/BatchNorm/moving_mean': [256],
'InceptionResnetV2/Repeat/block35_9/Branch_0/Conv2d_1x1/BatchNorm/beta': [32], ...
错误继续列出我认为检查点中的所有变量名称(或者它可能是范围而不是？).
上述这里检查最新的错误后,我看到InceptionResnetV2/Conv2d_2a_3x3/weights 是在设置检查点变量列表.问题是:0最后!
我现在将验证这是否确实解决了问题,并在这种情况下发布答案.
感谢@ KathyWu的评论,我走上正轨,发现了问题.
实际上,我计算的方式scopes将包括InceptionResnetV2/范围,这将触发范围内"(在网络中的所有变量)"下的所有变量的加载.然而,用正确的字典替换它并非易事.
在可能的范围模式init_from_checkpoint接受中,我必须使用的是'scope_variable_name': variable一个,但不使用实际variable.name属性.
的variable.name样子:'some_scope/variable_name:0'.这:0不是检查点变量的名称,因此使用scopes = {v.name:v.name for v in variables_to_restore}将引发"未找到变量"错误.
使其工作的诀窍是从名称中剥离张量索引:
tf.train.init_from_checkpoint('inception_resnet_v2_2016_08_30.ckpt',
{v.name.split(':')[0]: v for v in variables_to_restore})