def resnet_v1_101(inputs, output_stride=8, is_training=True):
blocks = [
resnet_v1.resnet_v1_block('block1',
base_depth=64,
num_units=3,
stride=1),
resnet_v1.resnet_v1_block('block2',
base_depth=128,
num_units=4,
stride=2),
resnet_v1.resnet_v1_block('block3',
base_depth=256,
num_units=23,
stride=2),
resnet_v1.resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=2),
]
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
with tf.variable_scope('resnet_v1_101', 'resnet_v1', [inputs]) as sc:
end_points_collection = sc.original_name_scope + '_end_points'
with slim.arg_scope([
slim.conv2d, resnet_v1.bottleneck,
resnet_utils.stack_blocks_dense
],
outputs_collections=end_points_collection):
with slim.arg_scope([slim.batch_norm],
is_training=is_training):
net = inputs
output_stride /= 4
net = resnet_utils.conv2d_same(net,
64,
7,
stride=2,
scope='conv1')
net = slim.max_pool2d(net, [2, 2], stride=2, scope='pool1')
net = resnet_utils.stack_blocks_dense(
net, blocks, output_stride)
# Convert end_points_collection into a dictionary of end_points.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
outputs = {}
outputs['conv1'] = end_points['resnet_v1_101/conv1']
outputs['conv2'] = end_points['resnet_v1_101/block1']
outputs['conv3'] = end_points['resnet_v1_101/block2']
outputs['conv4'] = end_points['resnet_v1_101/block3']
outputs['conv5'] = end_points['resnet_v1_101/block4']
return outputs
def resnet_v1_50(inputs, is_training=True):
blocks = [
resnet_v1.resnet_v1_block('block1',
base_depth=64,
num_units=3,
stride=2),
resnet_v1.resnet_v1_block('block2',
base_depth=128,
num_units=4,
stride=2),
resnet_v1.resnet_v1_block('block3',
base_depth=256,
num_units=6,
stride=2),
resnet_v1.resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1),
]
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
with tf.variable_scope('resnet_v1_50', 'resnet_v1', [inputs]):
with slim.arg_scope([
slim.conv2d, resnet_v1.bottleneck,
resnet_utils.stack_blocks_dense
]):
with slim.arg_scope([slim.batch_norm],
is_training=is_training):
net = inputs
net = resnet_utils.conv2d_same(net,
64,
7,
stride=2,
scope='conv1')
net = slim.max_pool2d(net, [2, 2], stride=2, scope='pool1')
net = resnet_utils.stack_blocks_dense(net, blocks)
net = tf.reduce_mean(net, [1, 2],
name='pool5',
keepdims=True)
return net