def train(train_dir, annotations, max_step, checkpoint_dir='./checkpoint2/'):
# train the model
features = tf.placeholder("float32", shape=[None, IMAGE_SIZE, IMAGE_SIZE, IMAGE_CHANNEL], name="features")
labels = tf.placeholder("float32", [None], name="labels")
one_hot_labels = tf.one_hot(indices=tf.cast(labels, tf.int32), depth=80)
keep_prob = tf.placeholder("float32")
isTraining = tf.placeholder("bool")
#train_step, cross_entropy, logits, keep_prob = network.inference(features, one_hot_labels)
logits, _=inception_resnet_v2.inception_resnet_v2(features,80,isTraining,keep_prob)
# calculate loss
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=one_hot_labels, logits=logits))
train_step = tf.train.AdamOptimizer(LEARNINGRATE).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(one_hot_labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
image_list, label_list = scene_input2.get_files(train_dir, annotations)
image_batch, label_batch = scene_input2.get_batch(image_list, label_list, IMAGE_SIZE, IMAGE_SIZE, BATCH_SIZE)
with tf.Session() as sess:
saver = tf.train.Saver()
ckpt = tf.train.get_checkpoint_state(checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
print('Restore the model from checkpoint %s' % ckpt.model_checkpoint_path)
# Restores from checkpoint
saver.restore(sess, ckpt.model_checkpoint_path)
start_step = int(ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
else:
sess.run(tf.global_variables_initializer())
start_step = 0
print('start training from new state')
logger = scene_input.train_log(LOGNAME)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
try:
# Check if stop was requested.
step=start_step
while not coord.should_stop() and step<start_step + max_step:
start_time = time.time()
x, y = sess.run([image_batch, label_batch])
#y = tf.one_hot(indices=tf.cast(y, tf.int32), depth=80)
#y = sess.run(y)
sess.run(train_step, feed_dict={features: x, labels: y, isTraining: True, keep_prob: 0.5})
if step % 50 == 0:
train_accuracy = sess.run(accuracy, feed_dict={features: x, labels: y, isTraining: False, keep_prob: 1})
train_loss = sess.run(cross_entropy, feed_dict={features: x, labels: y, isTraining:False, keep_prob: 1})
duration = time.time() - start_time
logger.info("step %d: training accuracy %g, loss is %g (%0.3f sec)" % (step, train_accuracy, train_loss, duration))
if step % 1000 == 1:
saver.save(sess, CHECKFILE, global_step=step)
print('writing checkpoint at step %s' % step)
step=step+1
except tf.errors.OutOfRangeError:
print('done!')
finally:
#Request that the threads stop.After this is called, calls to should_stop() will return True.
coord.request_stop()
coord.join(threads)
Traceback (most recent call last):
File "scene2.py", line 245, in <module>
train(FLAGS.train_dir, FLAGS. annotations, FLAGS.max_step)
File "scene2.py", line 82, in train
logits, _=inception_resnet_v2.inception_resnet_v2(features,80,isTraining,keep_prob)
File "/home/vision/inception_resnet_v2.py", line 357, in inception_resnet_v2
scope='Dropout')
File "/usr/local/lib/python3.4/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
return func(*args, **current_args)
File "/usr/local/lib/python3.4/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1216, in dropout
_scope=sc)
File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/layers/core.py", line 247, in __init__
self.rate = min(1., max(0., rate))
File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/ops.py", line 564, in __bool__
raise TypeError("Using a `tf.Tensor` as a Python `bool` is not allowed. "
TypeError: Using a `tf.Tensor` as a Python `bool` is not allowed. Use `if t is not None:` instead of `if t:` to test if a tensor is defined, and use TensorFlow ops such as tf.cond to execute subgraphs conditioned on the value of a tensor.
vision@Hjl:~/$ CUDA_VISIBLE_DEVICES=0 python3 scene2.py --mode train
Traceback (most recent call last):
File "scene2.py", line 245, in <module>
train(FLAGS.train_dir, FLAGS. annotations, FLAGS.max_step)
File "scene2.py", line 82, in train
logits, _=inception_resnet_v2.inception_resnet_v2(features,80,isTraining,keep_prob)
File "/home/vision/inception_resnet_v2.py", line 357, in inception_resnet_v2
scope='Dropout')
File "/usr/local/lib/python3.4/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
return func(*args, **current_args)
File "/usr/local/lib/python3.4/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1216, in dropout
_scope=sc)
File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/layers/core.py", line 247, in __init__
self.rate = min(1., max(0., rate))
File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/ops.py", line 564, in __bool__
raise TypeError("Using a `tf.Tensor` as a Python `bool` is not allowed. "
TypeError: Using a `tf.Tensor` as a Python `bool` is not allowed. Use `if t is not None:` instead of `if t:` to test if a tensor is defined, and use TensorFlow ops such as tf.cond to execute subgraphs conditioned on the value of a tensor.
当我将keep_prob和keep_prob传递给inception_resnet_v2.inception_resnet_v2（功能，80，ISTRAINing，keep_prob）时，发生了错误。我该如何解决这个问题？当我训练网络时，我想设置keep_prob = 0.5，instraining = true，但与此同时，每50步，我想观看模型的train_accuracy和train_loss，所以我应该设置keep_prob = 1.0，istraining，istraining = false，我对吗？我该如何实施？
如果您的最终目标是同时进行培训和评估，并且您正在使用TF-SLIM库提供的神经网络实现，那么最容易遵循TF-SLIM合着者NathanSilberman
处方的方法。
Ineval_image_classifier.py，您将需要替换代码：
if tf.gfile.IsDirectory(FLAGS.checkpoint_path):
checkpoint_path = tf.train.latest_checkpoint(FLAGS.checkpoint_path)
else:
checkpoint_path = FLAGS.checkpoint_path
tf.logging.info('Evaluating %s' % checkpoint_path)
slim.evaluation.evaluate_once(
master=FLAGS.master,
checkpoint_path=checkpoint_path,
logdir=FLAGS.eval_dir,
num_evals=num_batches,
eval_op=list(names_to_updates.values()),
variables_to_restore=variables_to_restore)
代码：
tf.logging.info('Evaluating %s' % FLAGS.checkpoint_path)
slim.evaluation.evaluation_loop(
master=FLAGS.master,
checkpoint_dir=FLAGS.checkpoint_path,
logdir=FLAGS.eval_dir,
num_evals=num_batches,
eval_op=list(names_to_updates.values()),
variables_to_restore=variables_to_restore)
如果您希望这两个进程都可以使用GPU而不遇到OOM错误，则可以通过创建一个configproto对象并将其作为
session_config或
slim.learning.train()参数的参数传递给每个过程。有关参考对
slim.evaluation.evaluation_loop()
is_trainingTrue
作为其参数传递给
False.的
is_trainingnets_factory.get_netowrk_fn()的参数化，nets_factory不会揭示Slim Nets的keep_prob
参数。取而代之的是，
dropout_keep_prob接受
slim.dropout()作为参数，并替换构成身份函数的辍学的计算。换句话说，tf-slim真是太棒了，以至于当您传递到
is_training时，它会自动“禁用”辍学，就像eval_image_classifier.py.中的情况一样。
如果您想直接暴露于Train_image_classifier.py（例如，用于超参数调整目的），则必须摆弄
is_training=False.的实现。
如果您使用的是this方法，那么它会期望一个python
nets_factory.get_netowrk_fn()dropout_keep_probnets_factory.get_network_fn()booleanfloat
update
但是，如果您需要在培训时间喂养它们，我认为最简单的方法是在此line