3. Scopes
除了TF原生的 name_scope和variable_scope之外，TF Slim添加了arg_scope，这种scope允许用户在arg_scope中指定若干操作符以及一批参数，这些参数会传给这个scope下的所有操作符中。参见以下代码：
net = slim.conv2d(inputs, 64, [11, 11], 4, padding='SAME',
weights_initializer=tf.truncated_normal_initializer(stddev=0.01),
weights_regularizer=slim.l2_regularizer(0.0005), scope='conv1')
net = slim.conv2d(net, 128, [11, 11], padding='VALID',
weights_initializer=tf.truncated_normal_initializer(stddev=0.01),
weights_regularizer=slim.l2_regularizer(0.0005), scope='conv2')
net = slim.conv2d(net, 256, [11, 11], padding='SAME',
weights_initializer=tf.truncated_normal_initializer(stddev=0.01),
weights_regularizer=slim.l2_regularizer(0.0005), scope='conv3')
'''
相当于：
'''
with slim.arg_scope([slim.conv2d], padding='SAME',
weights_initializer=tf.truncated_normal_initializer(stddev=0.01)
weights_regularizer=slim.l2_regularizer(0.0005)):
net = slim.conv2d(inputs, 64, [11, 11], scope='conv1')
net = slim.conv2d(net, 128, [11, 11], padding='VALID', scope='conv2')
net = slim.conv2d(net, 256, [11, 11], scope='conv3')注意，在arg_scope中被指定的参数值，也可以在局部位置进行覆盖。比如，padding参数设置为’SAME’, 而第二个卷积层仍然可以通过把它设为’VALID’而覆盖掉arg_scope中的默认设置。
arg_scope也可以嵌套：
with slim.arg_scope([slim.conv2d, slim.fully_connected],
activation_fn=tf.nn.relu,
weights_initializer=tf.truncated_normal_initializer(stddev=0.01),
weights_regularizer=slim.l2_regularizer(0.0005)):
with slim.arg_scope([slim.conv2d], stride=1, padding='SAME'):
net = slim.conv2d(inputs, 64, [11, 11], 4, padding='VALID', scope='conv1')
net = slim.conv2d(net, 256, [5, 5],
weights_initializer=tf.truncated_normal_initializer(stddev=0.03),
scope='conv2')
net = slim.fully_connected(net, 1000, activation_fn=None, scope='fc')在这个例子中，第一个arg_scope对处于它的scope中的conv2d和fully_connected操作层应用相同的weights_initializer andweights_regularizer参数。在第二个arg_scope中，默认参数只是在conv2d中指定。
- [x] 一个例子：VGG16
def vgg16(inputs):
with slim.arg_scope([slim.conv2d, slim.fully_connected],
activation_fn=tf.nn.relu,
weights_initializer=tf.truncated_normal_initializer(0.0, 0.01),
weights_regularizer=slim.l2_regularizer(0.0005)):
net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
net = slim.max_pool2d(net, [2, 2], scope='pool1')
net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
net = slim.max_pool2d(net, [2, 2], scope='pool2')
net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
net = slim.max_pool2d(net, [2, 2], scope='pool3')
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
net = slim.max_pool2d(net, [2, 2], scope='pool4')
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
net = slim.max_pool2d(net, [2, 2], scope='pool5')
net = slim.fully_connected(net, 4096, scope='fc6')
net = slim.dropout(net, 0.5, scope='dropout6')
net = slim.fully_connected(net, 4096, scope='fc7')
net = slim.dropout(net, 0.5, scope='dropout7')
net = slim.fully_connected(net, 1000, activation_fn=None, scope='fc8')
return net4. Train Models
4.1 Losses
- slim.losses.softmax_cross_entropy( )
- slim.losses.sum_of_squares( )
- slim.losses.get_total_loss( )
我们既可以通过相加得到total_loss，也可以通过slim.losses.get_total_loss()得到total_loss。这是怎么做到的呢？当你通过TF-Slim创建一个损失函数时，TF-Slim会把损失加入到一个特殊的Tensorflow的损失函数集合中。这样你既可以手动管理损失函数，也可以托管给TF-Slim。
def softmax_cross_entropy(logits,
onehot_labels,
weights=1.0,
label_smoothing=0,
scope=None):
"""Creates a cross-entropy loss using tf.nn.softmax_cross_entropy_with_logits.
`weights` acts as a coefficient for the loss. If a scalar is provided,
then the loss is simply scaled by the given value. If `weights` is a
tensor of size [`batch_size`], then the loss weights apply to each
corresponding sample.
If `label_smoothing` is nonzero, smooth the labels towards 1/num_classes:
new_onehot_labels = onehot_labels * (1 - label_smoothing)
+ label_smoothing / num_classes
Args:
logits: [batch_size, num_classes] logits outputs of the network .
onehot_labels: [batch_size, num_classes] one-hot-encoded labels.
weights: Coefficients for the loss. The tensor must be a scalar or a tensor
of shape [batch_size].
label_smoothing: If greater than 0 then smooth the labels.
scope: the scope for the operations performed in computing the loss.
Returns:
A scalar `Tensor` representing the mean loss value.
Raises:
ValueError: If the shape of `logits` doesn't match that of `onehot_labels`
or if the shape of `weights` is invalid or if `weights` is None.
"""4.2 Training Loop
在learning.py中，TF-Slim提供了简单却非常强大的训练模型的工具集。包括Train函数，可以重复地测量损失，计算梯度以及保存模型到磁盘中，还有一些方便的函数用于操作梯度。例如，当我们定义好了模型、损失函数以及优化方式，我们就可以调用slim.learning.create_train_op和slim.learning.train去执行优化：
g = tf.Graph()
# Create the model and specify the losses...
...
total_loss = slim.losses.get_total_loss()
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
# create_train_op ensures that each time we ask for the loss, the update_ops
# are run and the gradients being computed are applied too.
train_op = slim.learning.create_train_op(total_loss, optimizer)
logdir = ... # Where checkpoints are stored.
slim.learning.train(
train_op,
logdir,
number_of_steps=1000,
save_summaries_secs=300,
save_interval_secs=600):4.3 一个例子
import tensorflow as tf
import tensorflow.contrib.slim.nets as nets
slim = tf.contrib.slim
vgg = nets.vgg
... ...
train_log_dir = ...
if not tf.gfile.Exists(train_log_dir):
tf.gfile.MakeDirs(train_log_dir)
with tf.Graph().as_default():
# Set up the data loading:
images, labels = ...
# Define the model:
predictions = vgg.vgg_16(images, is_training=True)
# Specify the loss function:
slim.losses.softmax_cross_entropy(predictions, labels)
total_loss = slim.losses.get_total_loss()
tf.summary.scalar('losses/total_loss', total_loss)
# Specify the optimization scheme:
optimizer = tf.train.GradientDescentOptimizer(learning_rate=.001)
# create_train_op that ensures that when we evaluate it to get the loss,
# the update_ops are done and the gradient updates are computed.
train_tensor = slim.learning.create_train_op(total_loss, optimizer)
# Actually runs training.
slim.learning.train(train_tensor, train_log_dir)