per_process_gpu_memory_fraction=0.8,
allow_growth=True,
)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
allow_soft_placement=True)) as sess:
global_step = slim.create_global_step()
## data
image, ih, iw, gt_boxes, gt_masks, num_instances, img_id = \
coco.read('./data/coco/records/coco_train2014_00000-of-00040.tfrecord')
with tf.control_dependencies([image, gt_boxes, gt_masks]):
image, gt_boxes, gt_masks = coco_preprocess.preprocess_image(
image, gt_boxes, gt_masks, is_training=True)
## network
with slim.arg_scope(resnet_v1.resnet_arg_scope(weight_decay=0.0001)):
logits, end_points = resnet50(image, 1000, is_training=False)
end_points['inputs'] = image
for x in sorted(end_points.keys()):
print(x, end_points[x].name, end_points[x].shape)
pyramid = pyramid_network.build_pyramid('resnet50', end_points)
# for p in pyramid:
# print (p, pyramid[p])
summaries = set(tf.get_collection(tf.GraphKeys.SUMMARIES))
for p in pyramid:
summaries.add(tf.summary.histogram('pyramid/hist/' + p,
pyramid[p]))
summaries.add(
def deeplabv3(inputs, num_classes, layer_depth=50, is_training=True):
scope = 'resnet{}'.format(layer_depth)
with tf.variable_scope(scope, [inputs]) as sc:
end_points_collection = sc.name + '_end_points'
with slim.arg_scope(resnet_arg_scope()):
with slim.arg_scope([slim.conv2d, bottleneck],
outputs_collections=end_points_collection):
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, [3, 3], stride=2, scope='pool1')
with tf.variable_scope('block1', [net]) as sc:
base_depth = 64
for i in range(2):
with tf.variable_scope('unit_%d' % (i + 1),
values=[net]):
net = bottleneck(net,
depth=base_depth * 4,
depth_bottleneck=base_depth,
stride=1)
with tf.variable_scope('unit_3', values=[net]):
net = bottleneck(net,
depth=base_depth * 4,
depth_bottleneck=base_depth,
stride=2)
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
with tf.variable_scope('block2', [net]) as sc:
base_depth = 128
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1),
values=[net]):
net = bottleneck(net,
depth=base_depth * 4,
depth_bottleneck=base_depth,
stride=1)
with tf.variable_scope('unit_4', values=[net]):
net = bottleneck(net,
depth=base_depth * 4,
depth_bottleneck=base_depth,
stride=2)
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
with tf.variable_scope('block3', [net]) as sc:
base_depth = 256
num_units = 6
if layer_depth == 101:
num_units = 23
elif layer_depth == 152:
num_units = 36
for i in range(num_units):
with tf.variable_scope('unit_%d' % (i + 1),
values=[net]):
net = bottleneck(net,
depth=base_depth * 4,
depth_bottleneck=base_depth,
stride=1)
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
with tf.variable_scope('block4', [net]) as sc:
base_depth = 512
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1),
values=[net]):
net = bottleneck(net,
depth=base_depth * 4,
depth_bottleneck=base_depth,
stride=1,
rate=2)
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
with tf.variable_scope('block5', [net]) as sc:
base_depth = 512
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1),
values=[net]):
net = bottleneck_hdc(
net,
depth=base_depth * 4,
depth_bottleneck=base_depth,
stride=1,
rate=4)
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
with tf.variable_scope('block6', [net]) as sc:
base_depth = 512
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1),
values=[net]):
net = bottleneck_hdc(
net,
depth=base_depth * 4,
depth_bottleneck=base_depth,
stride=1,
rate=8)
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
with tf.variable_scope('block7', [net]) as sc:
base_depth = 512
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1),
values=[net]):
net = bottleneck_hdc(
net,
depth=base_depth * 4,
depth_bottleneck=base_depth,
stride=1,
rate=16)
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
with tf.variable_scope('aspp', [net]) as sc:
aspp_list = []
branch_1 = slim.conv2d(net,
256, [1, 1],
stride=1,
scope='1x1conv')
branch_1 = slim.utils.collect_named_outputs(
end_points_collection, sc.name, branch_1)
aspp_list.append(branch_1)
for i in range(3):
branch_2 = slim.conv2d(net,
256, [3, 3],
stride=1,
rate=6 * (i + 1),
scope='rate{}'.format(
6 * (i + 1)))
branch_2 = slim.utils.collect_named_outputs(
end_points_collection, sc.name, branch_2)
aspp_list.append(branch_2)
aspp = tf.add_n(aspp_list)
aspp = slim.utils.collect_named_outputs(
end_points_collection, sc.name, aspp)
with tf.variable_scope('img_pool', [net]) as sc:
"""Image Pooling
See ParseNet: Looking Wider to See Better
"""
pooled = tf.reduce_mean(net, [1, 2],
name='avg_pool',
keep_dims=True)
pooled = slim.utils.collect_named_outputs(
end_points_collection, sc.name, pooled)
pooled = slim.conv2d(pooled,
256, [1, 1],
stride=1,
scope='1x1conv')
pooled = slim.utils.collect_named_outputs(
end_points_collection, sc.name, pooled)
pooled = tf.image.resize_bilinear(
pooled,
tf.shape(net)[1:3])
pooled = slim.utils.collect_named_outputs(
end_points_collection, sc.name, pooled)
with tf.variable_scope('fusion', [aspp, pooled]) as sc:
net = tf.concat([aspp, pooled], 3)
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
net = slim.conv2d(net,
256, [1, 1],
stride=1,
scope='1x1conv')
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
net = slim.conv2d(net,
num_classes, [1, 1],
stride=1,
activation_fn=None,
scope='logits')
net = slim.utils.collect_named_outputs(
end_points_collection, sc.name, net)
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
return net, end_points
def deeplabv3(inputs,
num_classes,
depth=50,
aspp=True,
reuse=None,
is_training=True):
"""DeepLabV3
Args:
inputs: A tensor of size [batch, height, width, channels].
depth: The number of layers of the ResNet.
aspp: Whether to use ASPP module, if True, will use 4 blocks with
multi_grid=(1,2,4), if False, will use 7 blocks with multi_grid=(1,2,1).
reuse: Whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
Returns:
net: A rank-4 tensor of size [batch, height_out, width_out, channels_out].
end_points: A dictionary from components of the network to the
corresponding activation.
"""
if aspp:
multi_grid = (1,2,4)
else:
multi_grid = (1,2,1)
scope ='resnet{}'.format(depth)
with tf.variable_scope(scope, [inputs], reuse=reuse) as sc:
end_points_collection = sc.name + '_end_points'
with slim.arg_scope(resnet_arg_scope(weight_decay=args.weight_decay,
batch_norm_decay=args.bn_weight_decay)):
with slim.arg_scope([slim.conv2d, bottleneck, bottleneck_hdc],
outputs_collections=end_points_collection):
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, [3, 3], stride=2, scope='pool1')
with tf.variable_scope('block1', [net]) as sc:
base_depth = 64
for i in range(2):
with tf.variable_scope('unit_%d' % (i + 1), values=[net]):
net = bottleneck(net, depth=base_depth * 4,
depth_bottleneck=base_depth, stride=1)
with tf.variable_scope('unit_3', values=[net]):
net = bottleneck(net, depth=base_depth * 4,
depth_bottleneck=base_depth, stride=2)
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
with tf.variable_scope('block2', [net]) as sc:
base_depth = 128
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1), values=[net]):
net = bottleneck(net, depth=base_depth * 4,
depth_bottleneck=base_depth, stride=1)
with tf.variable_scope('unit_4', values=[net]):
net = bottleneck(net, depth=base_depth * 4,
depth_bottleneck=base_depth, stride=2)
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
with tf.variable_scope('block3', [net]) as sc:
base_depth = 256
num_units = 6
if depth == 101:
num_units = 23
elif depth == 152:
num_units = 36
for i in range(num_units):
with tf.variable_scope('unit_%d' % (i + 1), values=[net]):
net = bottleneck(net, depth=base_depth * 4,
depth_bottleneck=base_depth, stride=1)
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
with tf.variable_scope('block4', [net]) as sc:
base_depth = 512
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1), values=[net]):
net = bottleneck_hdc(net, depth=base_depth * 4,
depth_bottleneck=base_depth, stride=1, rate=2,
multi_grid=multi_grid)
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
if aspp:
with tf.variable_scope('aspp', [net]) as sc:
aspp_list = []
branch_1 = slim.conv2d(net, 256, [1,1], stride=1,
scope='1x1conv')
branch_1 = slim.utils.collect_named_outputs(
end_points_collection, sc.name, branch_1)
aspp_list.append(branch_1)
for i in range(3):
branch_2 = slim.conv2d(net, 256, [3,3], stride=1, rate=6*(i+1), scope='rate{}'.format(6*(i+1)))
branch_2 = slim.utils.collect_named_outputs(end_points_collection, sc.name, branch_2)
aspp_list.append(branch_2)
aspp = tf.add_n(aspp_list)
aspp = slim.utils.collect_named_outputs(end_points_collection, sc.name, aspp)
with tf.variable_scope('img_pool', [net]) as sc:
"""Image Pooling
See ParseNet: Looking Wider to See Better
"""
pooled = tf.reduce_mean(net, [1, 2], name='avg_pool',
keep_dims=True)
pooled = slim.utils.collect_named_outputs(end_points_collection,
sc.name, pooled)
pooled = slim.conv2d(pooled, 256, [1,1], stride=1, scope='1x1conv')
pooled = slim.utils.collect_named_outputs(end_points_collection,
sc.name, pooled)
pooled = tf.image.resize_bilinear(pooled, tf.shape(net)[1:3])
pooled = slim.utils.collect_named_outputs(end_points_collection,
sc.name, pooled)
with tf.variable_scope('fusion', [aspp, pooled]) as sc:
net = tf.concat([aspp, pooled], 3)
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
net = slim.conv2d(net, 256, [1,1], stride=1, scope='1x1conv')
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
else:
with tf.variable_scope('block5', [net]) as sc:
base_depth = 512
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1), values=[net]):
net = bottleneck_hdc(net, depth=base_depth * 4,
depth_bottleneck=base_depth, stride=1, rate=4)
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
with tf.variable_scope('block6', [net]) as sc:
base_depth = 512
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1), values=[net]):
net = bottleneck_hdc(net, depth=base_depth * 4,
depth_bottleneck=base_depth, stride=1, rate=8)
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
with tf.variable_scope('block7', [net]) as sc:
base_depth = 512
for i in range(3):
with tf.variable_scope('unit_%d' % (i + 1), values=[net]):
net = bottleneck_hdc(net, depth=base_depth * 4,
depth_bottleneck=base_depth, stride=1, rate=16)
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
net = slim.conv2d(net, num_classes, [1,1], stride=1,
activation_fn=None, normalizer_fn=None, scope='logits')
net = slim.utils.collect_named_outputs(end_points_collection,
sc.name, net)
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
return net, end_points
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8,
allow_growth=True,
)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
allow_soft_placement=True)) as sess:
global_step = slim.create_global_step()
## data
image, ih, iw, gt_boxes, gt_masks, num_instances, img_id = \
coco.read('./data/coco/records/coco_train2014_00000-of-00040.tfrecord')
image, gt_boxes, gt_masks = coco_preprocess.preprocess_image(image, gt_boxes, gt_masks, is_training=True)
## network
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits, end_points = resnet50(image, 1000, is_training=False)
end_points['inputs'] = image
for x in sorted(end_points.keys()):
print (x, end_points[x].name, end_points[x].shape)
pyramid = pyramid_network.build_pyramid('resnet50', end_points)
# for p in pyramid:
# print (p, pyramid[p])
summaries = set(tf.get_collection(tf.GraphKeys.SUMMARIES))
for p in pyramid:
summaries.add(tf.summary.histogram('pyramid/hist/' + p, pyramid[p]))
summaries.add(tf.summary.scalar('pyramid/means/'+ p, tf.reduce_mean(tf.abs(pyramid[p]))))