def bottleneck(inputs,
depth,
depth_bottleneck,
stride,
rate=1,
outputs_collections=None,
scope=None,
use_bounded_activations=False):
with tf.variable_scope(scope, 'bottleneck_v1', [inputs]) as sc:
depth_in = slim.utils.last_dimension(inputs.get_shape(), min_rank=4)
if depth == depth_in:
shortcut = utils.subsample(inputs, stride, 'shortcut')
else:
shortcut = slim.conv2d(inputs, depth, [1, 1], stride=stride,
activation_fn=tf.nn.relu6 if use_bounded_activations else None, scope='shortcut')
residual = slim.conv2d(inputs, depth_bottleneck, [1, 1], stride=1, scope='conv1')
residual = utils.conv2d_same(residual, depth_bottleneck, 3, stride, rate=rate, scope='conv2')
residual = slim.conv2d(residual, depth, [1, 1], stride=1, activation_fn=None, scope='conv3')
if use_bounded_activations:
# Use clip_by_value to simulate bandpass activation.
residual = tf.clip_by_value(residual, -6.0, 6.0)
output = tf.nn.relu6(shortcut + residual)
else:
output = tf.nn.relu(shortcut + residual)
return slim.utils.collect_named_outputs(outputs_collections, sc.name, output)
def block(inputs, depth, stride, rate=1, outputs_collections=None, scope=None):
with tf.variable_scope(scope, 'block_v2', [inputs]) as sc:
depth_in = slim.utils.last_dimension(inputs.get_shape(), min_rank=4)
preact = slim.batch_norm(inputs, activation_fn=tf.nn.leaky_relu, scope='preact')
if depth == depth_in:
shortcut = utils.subsample(inputs, stride, 'shortcut')
else:
shortcut = slim.conv2d(preact, depth, [1, 1], stride=stride, normalizer_fn=None, activation_fn=None, scope='shortcut')
residual = utils.conv2d_same(preact, depth, 3, stride, rate=rate, scope='conv1')
residual = slim.conv2d(residual, depth, [3, 3], stride=1, normalizer_fn=None, activation_fn=None, scope='conv2')
# residual = slim.conv2d(residual, depth, [1, 1], stride=1, normalizer_fn=None, activation_fn=None, scope='conv3')
output = shortcut + residual
return slim.utils.collect_named_outputs(outputs_collections, sc.name, output)