def testEndPointsV1(self):
"""Test the end points of a tiny v1 bottleneck network."""
blocks = [
resnet_v1.resnet_v1_block('block1',
base_depth=1,
num_units=2,
stride=2),
resnet_v1.resnet_v1_block('block2',
base_depth=2,
num_units=2,
stride=1),
]
inputs = create_test_input(2, 32, 16, 3)
with arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = self._resnet_plain(inputs, blocks, scope='tiny')
expected = [
'tiny/block1/unit_1/bottleneck_v1/shortcut',
'tiny/block1/unit_1/bottleneck_v1/conv1',
'tiny/block1/unit_1/bottleneck_v1/conv2',
'tiny/block1/unit_1/bottleneck_v1/conv3',
'tiny/block1/unit_2/bottleneck_v1/conv1',
'tiny/block1/unit_2/bottleneck_v1/conv2',
'tiny/block1/unit_2/bottleneck_v1/conv3',
'tiny/block2/unit_1/bottleneck_v1/shortcut',
'tiny/block2/unit_1/bottleneck_v1/conv1',
'tiny/block2/unit_1/bottleneck_v1/conv2',
'tiny/block2/unit_1/bottleneck_v1/conv3',
'tiny/block2/unit_2/bottleneck_v1/conv1',
'tiny/block2/unit_2/bottleneck_v1/conv2',
'tiny/block2/unit_2/bottleneck_v1/conv3'
]
self.assertItemsEqual(expected, end_points)
def testEndPointsV1(self):
"""Test the end points of a tiny v1 bottleneck network."""
blocks = [
resnet_v1.resnet_v1_block(
'block1', base_depth=1, num_units=2, stride=2),
resnet_v1.resnet_v1_block(
'block2', base_depth=2, num_units=2, stride=1),
]
inputs = create_test_input(2, 32, 16, 3)
with arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = self._resnet_plain(inputs, blocks, scope='tiny')
expected = [
'tiny/block1/unit_1/bottleneck_v1/shortcut',
'tiny/block1/unit_1/bottleneck_v1/conv1',
'tiny/block1/unit_1/bottleneck_v1/conv2',
'tiny/block1/unit_1/bottleneck_v1/conv3',
'tiny/block1/unit_2/bottleneck_v1/conv1',
'tiny/block1/unit_2/bottleneck_v1/conv2',
'tiny/block1/unit_2/bottleneck_v1/conv3',
'tiny/block2/unit_1/bottleneck_v1/shortcut',
'tiny/block2/unit_1/bottleneck_v1/conv1',
'tiny/block2/unit_1/bottleneck_v1/conv2',
'tiny/block2/unit_1/bottleneck_v1/conv3',
'tiny/block2/unit_2/bottleneck_v1/conv1',
'tiny/block2/unit_2/bottleneck_v1/conv2',
'tiny/block2/unit_2/bottleneck_v1/conv3']
self.assertItemsEqual(expected, end_points)
def resnet_v1_50(inputs,
num_classes=None,
is_training=True,
global_pool=True,
output_stride=None,
include_root_block=True,
reuse=None,
scope='resnet_v1_50'):
"""
ResNet-50 model of [1]. See resnet_v1() for arg and return description.
(same as what's in slim library now but reversing the 1 stride to accommodate the unet model)
"""
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=6, stride=2),
resnet_v1.resnet_v1_block('block4', base_depth=512, num_units=3, stride=2),
]
return resnet_v1.resnet_v1(
inputs,
blocks,
num_classes,
is_training=is_training,
global_pool=global_pool,
output_stride=output_stride,
include_root_block=include_root_block,
reuse=reuse,
scope=scope)
def _decide_blocks(self):
# configuration of blocks for 41 layers - a shallower ResNet
# tested in Experiment 4 in project report
# units in blocks: 3 x 64 + 3 x 128 + 4 x 256 + 3 x 512
if self._num_layers == 41:
self._blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2),
resnet_v1_block('block2',
base_depth=128,
num_units=3,
stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3',
base_depth=256,
num_units=4,
stride=1),
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1)
]
else:
# other numbers are not supported
raise NotImplementedError
def _decide_blocks(self):
# choose different blocks for different number of layers
self._blocks = [
resnet_v1_block('block1', base_depth=16, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=32, num_units=4, stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3', base_depth=64, num_units=6, stride=1),
resnet_v1_block('block4', base_depth=128, num_units=3, stride=1)
]
def __init__(self, is_training):
self.name = self.__class__.__name__.lower()
self.vars = {}
self.layers = []
self.activations = []
self.visualize = {}
self.intermediate = {}
self.predictions = {}
self.losses = {}
self.score_summaries = {}
self.event_summaries = {}
self.image = tf.placeholder(tf.float32, shape=[1, None, None, 3], name = 'image')
self.H_boxes = tf.placeholder(tf.float32, shape=[None , 5], name = 'H_boxes')
self.O_boxes = tf.placeholder(tf.float32, shape=[None , 5], name = 'O_boxes')
self.H_boxes_enc = tf.placeholder(tf.float32, shape=[None , 4], name = 'H_boxes_enc')
self.O_boxes_enc = tf.placeholder(tf.float32, shape=[None , 4], name = 'O_boxes_enc')
self.HO_boxes_enc= tf.placeholder(tf.float32, shape=[None , 4], name = 'HO_boxes_enc')
self.gt_class_H = tf.placeholder(tf.float32, shape=[None, 26], name = 'gt_class_H')
self.gt_class_HO = tf.placeholder(tf.float32, shape=[None, 26], name = 'gt_class_HO')
self.Mask_HO = tf.placeholder(tf.float32, shape=[None, 26], name = 'HO_mask')
self.Mask_H = tf.placeholder(tf.float32, shape=[None, 26], name = 'H_mask')
self.H_num = tf.placeholder(tf.int32) # pos
self.ivs = tf.placeholder(tf.int32, shape=[26], name = 'idx_GT_verbs')
self.inputs = tf.placeholder(tf.float32, shape=[None, 300], name = 'embedding')
self.support = [tf.sparse_placeholder(tf.float32) for _ in range(1)]
self.num_nonzero = tf.placeholder(tf.int32)
self.in_dim = 300
self.hidden_dim = 512
self.out_dim = 512
self.num_classes = 26
self.scope = 'resnet_v1_50'
self.stride = [16, ]
self.train = is_training
self.now_lr = None
self.optimizer = None
self.opt_op = None
if tf.__version__ == '1.1.0':
self.blocks = [resnet_utils.Block('block1', resnet_v1.bottleneck,[(256, 64, 1)] * 2 + [(256, 64, 2)]),
resnet_utils.Block('block2', resnet_v1.bottleneck,[(512, 128, 1)] * 3 + [(512, 128, 2)]),
resnet_utils.Block('block3', resnet_v1.bottleneck,[(1024, 256, 1)] * 5 + [(1024, 256, 1)]),
resnet_utils.Block('block4', resnet_v1.bottleneck,[(2048, 512, 1)] * 3),
resnet_utils.Block('block5', resnet_v1.bottleneck,[(2048, 512, 1)] * 3)]
else:
from tensorflow.contrib.slim.python.slim.nets.resnet_v1 import resnet_v1_block
self.blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=6, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1),
resnet_v1_block('block5', base_depth=512, num_units=3, stride=1)]
self.build_all()
def build(self,
inputs,
input_pixel_size,
is_training,
scope='resnet_v1_101'): ## scope is important variable to set
""" resnet
args:
inputs: a tensor of size [batch_size, height, width, channels].
input_pixel_size: size of the input (H x W)
is_training: True for training, False for validation/testing.
scope: Optional scope for the variables.
Returns:
The last op containing the log predictions and end_points dict.
"""
res_config = self.config
fixed_block = res_config.fixed_block
self._scope = scope
import pudb
pudb.set_trace() # XXX BREAKPOINT
with slim.arg_scope(resnet_arg_scope(is_training=False)):
net_base = self._build_base(inputs)
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=23, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)
]
with slim.arg_scope(resnet_arg_scope(is_training=False)):
net_conv1, net_dict1 = resnet_v1.resnet_v1(
net_base,
blocks[0:fixed_block],
global_pool=False,
include_root_block=False, ## no resue
scope=self._scope)
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
net_conv2, net_dict2 = resnet_v1.resnet_v1(
net_conv1,
blocks[fixed_block:],
global_pool=False,
include_root_block=False,
scope=self._scope)
feature_maps_out = net_conv2 # pyramid_fusion3 #pyramid_fusion1
#end_points = slim.utils.convert_collection_to_dict(
# end_points_collection)
return feature_maps_out, net_dict2 #end_points
def __init__(self):
self.visualize = {}
self.intermediate = {}
self.predictions = {}
self.score_summaries = {}
self.event_summaries = {}
self.train_summaries = []
self.losses = {}
self.image = tf.placeholder(tf.float32, shape=[1, None, None, 3], name = 'image')
self.spatial = tf.placeholder(tf.float32, shape=[None, 64, 64, 3], name = 'sp') # Pattern.reshape( num_pos_neg, 64, 64, 3)
self.Hsp_boxes = tf.placeholder(tf.float32, shape=[None, 5], name = 'Hsp_boxes')
self.O_boxes = tf.placeholder(tf.float32, shape=[None, 5], name = 'O_boxes') #Object_augmented[:num_pos].reshape(num_pos, 5)
self.gt_class_H = tf.placeholder(tf.float32, shape=[None, 29], name = 'gt_class_H')
self.gt_class_HO = tf.placeholder(tf.float32, shape=[None, 29], name = 'gt_class_HO')
self.gt_class_sp = tf.placeholder(tf.float32, shape=[None, 29], name = 'gt_class_sp')
self.Mask_HO = tf.placeholder(tf.float32, shape=[None, 29], name = 'HO_mask')
self.Mask_H = tf.placeholder(tf.float32, shape=[None, 29], name = 'H_mask')
self.Mask_sp = tf.placeholder(tf.float32, shape=[None, 29], name = 'sp_mask')
self.gt_binary_label = tf.placeholder(tf.float32, shape=[None, 2], name = 'gt_binary_label')
self.H_num = tf.placeholder(tf.int32)
self.HO_weight = np.array([3.3510249, 3.4552405, 4.0257854, 0.0, 4.088436,
3.4370995, 3.85842, 4.637334, 3.5487218, 3.536237,
2.5578923, 3.342811, 3.8897269, 4.70686, 3.3952892,
3.9706533, 4.504736, 0.0, 1.4873443, 3.700363,
4.1058283, 3.6298118, 0.0, 6.490651, 5.0808263,
1.520838, 3.3888445, 0.0, 3.9899964], dtype = 'float32').reshape(1,29)
self.H_weight = np.array([4.0984106, 4.102459, 4.0414762, 4.060745, 4.0414762,
3.9768186, 4.23686, 5.3542085, 3.723717, 3.4699364,
2.4587274, 3.7167964, 4.08836, 5.050695, 3.9077065,
4.534647, 3.4699364, 2.9466882, 1.8585607, 3.9433942,
3.9433942, 4.3523254, 3.8368235, 6.4963055, 5.138182,
1.7807873, 4.080392, 1.9544303, 4.5761204],dtype = 'float32').reshape(1,29)
self.binary_weight = np.array([1.0986122886681098, 0.4054651081081644], dtype = 'float32').reshape(1,2)
self.num_classes = 29
self.num_binary = 2 # existence (0 or 1) of HOI
self.num_fc = 1024
self.scope = 'resnet_v1_50'
self.stride = [16, ]
self.lr = tf.placeholder(tf.float32)
if tf.__version__ == '1.1.0':
self.blocks = [resnet_utils.Block('block1', resnet_v1.bottleneck,[(256, 64, 1)] * 2 + [(256, 64, 2)]),
resnet_utils.Block('block2', resnet_v1.bottleneck,[(512, 128, 1)] * 3 + [(512, 128, 2)]),
resnet_utils.Block('block3', resnet_v1.bottleneck,[(1024, 256, 1)] * 5 + [(1024, 256, 1)]),
resnet_utils.Block('block4', resnet_v1.bottleneck,[(2048, 512, 1)] * 3),
resnet_utils.Block('block5', resnet_v1.bottleneck,[(2048, 512, 1)] * 3)]
else:
from tensorflow.contrib.slim.python.slim.nets.resnet_v1 import resnet_v1_block
self.blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=6, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1),
resnet_v1_block('block5', base_depth=512, num_units=3, stride=1)]
def _decide_block(self):
# choose different blocks for different number of layers
base_depths = list()
strides = list()
self.blocks = list()
scopes = ["block1", "block2", "block3", "block4"]
for i in range(2):
base_depths.append(int(math.pow(2, i+6)))
strides.append(2)
for i in range(2):
base_depths.append(int(math.pow(2, i + 8)))
strides.append(1)
if self.num_layers == 50:
num_units = [3, 4, 6, 3]
elif self.num_layers == 101:
num_units = [3, 4, 23, 3]
elif self.num_layers == 152:
num_units = [3, 8, 36, 3]
else:
# other numbers are not supported
raise NotImplementedError
for i in range(4):
self.blocks.append(resnet_v1_block(
scope=scopes[i], base_depth=base_depths[i],
num_units=num_units[i], stride=strides[i]))
def resnet_faster_rcnn_head(input, params):
"""
Derived from https://github.com/DetectionTeamUCAS/Faster-RCNN_Tensorflow
Args:
input:
params:
Returns:
"""
with tf.variable_scope('resnet_head', reuse=tf.AUTO_REUSE):
block4 = [
resnet_v1_block('block4', base_depth=256, num_units=3, stride=1)
]
with slim.arg_scope(norm_arg_scope(params)):
C5, _ = resnet_v1.resnet_v1(input,
block4,
global_pool=False,
include_root_block=False,
scope='resnet_v1_50',
reuse=tf.AUTO_REUSE)
return C5
def restnet_head(input, is_training, scope_name, stage):
if stage == 'stage1':
block4 = [
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)
]
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C5, _ = resnet_v1.resnet_v1(input,
block4,
global_pool=False,
include_root_block=False,
scope=scope_name)
# C5 = tf.Print(C5, [tf.shape(C5)], summarize=10, message='C5_shape')
flatten = tf.reduce_mean(C5,
axis=[1, 2],
keep_dims=False,
name='global_average_pooling')
# C5_flatten = tf.Print(C5_flatten, [tf.shape(C5_flatten)], summarize=10, message='C5_flatten_shape')
# global average pooling C5 to obtain fc layers
else:
fc_flatten = slim.flatten(input)
net = slim.fully_connected(fc_flatten,
1024,
scope='fc_1_{}'.format(stage))
net = slim.dropout(net,
keep_prob=0.5,
is_training=is_training,
scope='dropout_{}'.format(stage))
flatten = slim.fully_connected(net,
1024,
scope='fc_2_{}'.format(stage))
return flatten
def _decide_blocks(self):
self._blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=23, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
self._blocks2 = [resnet_v1_block('block1_prev', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2_prev', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3_prev', base_depth=256, num_units=23, stride=1),
resnet_v1_block('block4_prev', base_depth=512, num_units=3, stride=1)]
def resnet_v1_101_c4(inputs,
num_classes=None,
is_training=True,
global_pool=True,
output_stride=None,
spatial_squeeze=True,
reuse=None,
scope='resnet_v1_101'):
"""ResNet-101 model of [1]. See resnet_v1() for arg and return description."""
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3, stride=1),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=23, stride=2)
]
return resnet_v1.resnet_v1(inputs, blocks, num_classes, is_training,
global_pool=global_pool, output_stride=output_stride,
include_root_block=True,
reuse=reuse, scope=scope)
def __init__(self):
self.visualize = {}
self.intermediate = {}
self.predictions = {}
self.score_summaries = {}
self.event_summaries = {}
self.train_summaries = []
self.losses = {}
self.image = tf.placeholder(tf.float32, shape=[1, None, None, 3], name = 'image')
self.spatial = tf.placeholder(tf.float32, shape=[None, 64, 64, 2], name = 'sp')
self.Hsp_boxes = tf.placeholder(tf.float32, shape=[None, 5], name = 'Hsp_boxes')
self.O_boxes = tf.placeholder(tf.float32, shape=[None, 5], name = 'O_boxes')
self.gt_class_H = tf.placeholder(tf.float32, shape=[None, 29], name = 'gt_class_H')
self.gt_class_HO = tf.placeholder(tf.float32, shape=[None, 29], name = 'gt_class_HO')
self.gt_class_sp = tf.placeholder(tf.float32, shape=[None, 29], name = 'gt_class_sp')
self.Mask_HO = tf.placeholder(tf.float32, shape=[None, 29], name = 'HO_mask')
self.Mask_H = tf.placeholder(tf.float32, shape=[None, 29], name = 'H_mask')
self.Mask_sp = tf.placeholder(tf.float32, shape=[None, 29], name = 'sp_mask')
self.H_num = tf.placeholder(tf.int32)
self.num_classes = 29
self.num_fc = 1024
self.scope = 'resnet_v1_50'
self.stride = [16, ]
self.lr = tf.placeholder(tf.float32)
if tf.__version__ == '1.1.0':
self.blocks = [resnet_utils.Block('block1', resnet_v1.bottleneck,[(256, 64, 1)] * 2 + [(256, 64, 2)]),
resnet_utils.Block('block2', resnet_v1.bottleneck,[(512, 128, 1)] * 3 + [(512, 128, 2)]),
resnet_utils.Block('block3', resnet_v1.bottleneck,[(1024, 256, 1)] * 5 + [(1024, 256, 1)]),
resnet_utils.Block('block4', resnet_v1.bottleneck,[(2048, 512, 1)] * 3),
resnet_utils.Block('block5', resnet_v1.bottleneck,[(2048, 512, 1)] * 3)]
else:
from tensorflow.contrib.slim.python.slim.nets.resnet_v1 import resnet_v1_block
self.blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=6, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1),
resnet_v1_block('block5', base_depth=512, num_units=3, stride=1)]
def restnet_head(input, is_training, scope_name):
block4 = [resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C5, _ = resnet_v1.resnet_v1(input,
block4,
global_pool=False,
include_root_block=False,
scope=scope_name)
# C5 = tf.Print(C5, [tf.shape(C5)], summarize=10, message='C5_shape')
# C5_flatten = tf.reduce_mean(C5, axis=[1, 2], keep_dims=False, name='global_average_pooling')
# C5_flatten = tf.Print(C5_flatten, [tf.shape(C5_flatten)], summarize=10, message='C5_flatten_shape')
# global average pooling C5 to obtain fc layers
return C5
def _decide_blocks(self):
# choose different blocks for different number of layers
if self._num_layers == 50:
self._blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3', base_depth=256, num_units=6, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
elif self._num_layers == 101:
self._blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3', base_depth=256, num_units=23, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
else:
# other numbers are not supported
raise NotImplementedError
def restnet_head(self, inputs, scope_name, is_training):
block4 = [
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)
]
with slim.arg_scope(self.resnet_arg_scope(is_training=is_training)):
net, _ = resnet_v1.resnet_v1(inputs,
block4,
global_pool=False,
include_root_block=False,
scope=scope_name)
net_flatten = tf.reduce_mean(net,
axis=[1, 2],
keep_dims=False,
name='global_average_pooling')
# global average pooling C5 to obtain fc layers
return net_flatten
def resnet_base(img_batch, scope_name, is_training=True):
if scope_name == 'resnet_v1_50':
middle_num_units = 6
elif scope_name == 'resnet_v1_101':
middle_num_units = 23
else:
raise NotImplementedError(
'We only support resnet_v1_50 or resnet_v1_101. ')
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3',
base_depth=256,
num_units=middle_num_units,
stride=2),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)
]
# when use fpn . stride list is [1, 2, 2]
with slim.arg_scope(resnet_arg_scope(is_training=False)):
with tf.variable_scope(scope_name, scope_name):
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1
net = resnet_utils.conv2d_same(img_batch,
64,
7,
stride=2,
scope='conv1')
net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
net = slim.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='pool1')
not_freezed = [False
] * cfgs.FIXED_BLOCKS + (4 - cfgs.FIXED_BLOCKS) * [True]
# Fixed_Blocks can be 1~3
with slim.arg_scope(
resnet_arg_scope(is_training=(is_training and not_freezed[0]))):
C2, end_points_C2 = resnet_v1.resnet_v1(net,
blocks[0:1],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C2 = tf.Print(C2, [tf.shape(C2)], summarize=10, message='C2_shape')
# add_heatmap(C2, name='Layer2/C2_heat')
with slim.arg_scope(
resnet_arg_scope(is_training=(is_training and not_freezed[1]))):
C3, end_points_C3 = resnet_v1.resnet_v1(C2,
blocks[1:2],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C3 = tf.Print(C3, [tf.shape(C3)], summarize=10, message='C3_shape')
# add_heatmap(C3, name='Layer3/C3_heat')
with slim.arg_scope(
resnet_arg_scope(is_training=(is_training and not_freezed[2]))):
C4, end_points_C4 = resnet_v1.resnet_v1(C3,
blocks[2:3],
global_pool=False,
include_root_block=False,
scope=scope_name)
# add_heatmap(C4, name='Layer4/C4_heat')
# C4 = tf.Print(C4, [tf.shape(C4)], summarize=10, message='C4_shape')
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C5, end_points_C5 = resnet_v1.resnet_v1(C4,
blocks[3:4],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C5 = tf.Print(C5, [tf.shape(C5)], summarize=10, message='C5_shape')
# add_heatmap(C5, name='Layer5/C5_heat')
feature_dict = {
'C2':
end_points_C2['{}/block1/unit_2/bottleneck_v1'.format(scope_name)],
'C3':
end_points_C3['{}/block2/unit_3/bottleneck_v1'.format(scope_name)],
'C4':
end_points_C4['{}/block3/unit_{}/bottleneck_v1'.format(
scope_name, middle_num_units - 1)],
'C5':
end_points_C5['{}/block4/unit_3/bottleneck_v1'.format(scope_name)],
# 'C5': end_points_C5['{}/block4'.format(scope_name)],
}
pyramid_dict = {}
with tf.variable_scope('build_pyramid'):
with slim.arg_scope([slim.conv2d],
weights_regularizer=slim.l2_regularizer(
cfgs.WEIGHT_DECAY),
activation_fn=None,
normalizer_fn=None):
P5 = slim.conv2d(feature_dict['C5'],
num_outputs=256,
kernel_size=[1, 1],
stride=1,
scope='build_P5')
pyramid_dict['P5'] = P5
for level in range(4, 2, -1): # build [P4, P3]
pyramid_dict['P%d' % level] = fusion_two_layer(
C_i=feature_dict["C%d" % level],
P_j=pyramid_dict["P%d" % (level + 1)],
scope='build_P%d' % level)
for level in range(5, 2, -1):
pyramid_dict['P%d' % level] = slim.conv2d(
pyramid_dict['P%d' % level],
num_outputs=256,
kernel_size=[3, 3],
padding="SAME",
stride=1,
scope="fuse_P%d" % level)
p6 = slim.conv2d(
pyramid_dict['P5'] if cfgs.USE_P5 else feature_dict['C5'],
num_outputs=256,
kernel_size=[3, 3],
padding="SAME",
stride=2,
scope='p6_conv')
pyramid_dict['P6'] = p6
p7 = tf.nn.relu(p6, name='p6_relu')
p7 = slim.conv2d(p7,
num_outputs=256,
kernel_size=[3, 3],
padding="SAME",
stride=2,
scope='p7_conv')
pyramid_dict['P7'] = p7
# for level in range(7, 1, -1):
# add_heatmap(pyramid_dict['P%d' % level], name='Layer%d/P%d_heat' % (level, level))
return pyramid_dict
def _decide_blocks(self):
# 关于不同数量层 选择不同的块
if self._num_layers == 50:
self._blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2),
resnet_v1_block('block2',
base_depth=128,
num_units=4,
stride=2),
resnet_v1_block('block3',
base_depth=256,
num_units=6,
stride=1),
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1)
]
elif self._num_layers == 101:
self._blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2),
resnet_v1_block('block2',
base_depth=128,
num_units=4,
stride=2),
resnet_v1_block('block3',
base_depth=256,
num_units=23,
stride=1),
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1)
]
elif self._num_layers == 152:
self._blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2),
resnet_v1_block('block2',
base_depth=128,
num_units=8,
stride=2),
resnet_v1_block('block3',
base_depth=256,
num_units=36,
stride=1),
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1)
]
else:
raise NotImplementedError
def _decide_blocks(self):
# choose different blocks for different number of layers
if self._num_layers == 50:
self._blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3', base_depth=256, num_units=6, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
elif self._num_layers == 101:
self._blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3', base_depth=256, num_units=23, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
elif self._num_layers == 152:
self._blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=8, stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3', base_depth=256, num_units=36, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
else:
# other numbers are not supported
raise NotImplementedError
def build_network(self, sess, is_training=True):
# select initializers
# if cfg.TRAIN.TRUNCATED:
if cfg.FLAGS.initializer == "truncated":
initializer = tf.truncated_normal_initializer(mean=0.0,
stddev=0.01)
initializer_bbox = tf.truncated_normal_initializer(mean=0.0,
stddev=0.001)
else:
initializer = tf.random_normal_initializer(mean=0.0, stddev=0.01)
initializer_bbox = tf.random_normal_initializer(mean=0.0,
stddev=0.001)
bottleneck = resnet_v1.bottleneck
# choose different blocks for different number of layers
if self._num_layers == 50:
# blocks = [
# resnet_utils.Block('block1', bottleneck,
# [(256, 64, 1)] * 2 + [(256, 64, 2)]),
# resnet_utils.Block('block2', bottleneck,
# [(512, 128, 1)] * 3 + [(512, 128, 2)]),
# # Use stride-1 for the last conv4 layer
# resnet_utils.Block('block3', bottleneck,
# [(1024, 256, 1)] * 5 + [(1024, 256, 1)]),
# resnet_utils.Block('block4', bottleneck, [(2048, 512, 1)] * 3)
# ]
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=1),
resnet_v1.resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1),
]
elif self._num_layers == 101:
# blocks = [
# resnet_utils.Block('block1', bottleneck,
# [(256, 64, 1)] * 2 + [(256, 64, 2)]),
# resnet_utils.Block('block2', bottleneck,
# [(512, 128, 1)] * 3 + [(512, 128, 2)]),
# # Use stride-1 for the last conv4 layer
# resnet_utils.Block('block3', bottleneck,
# [(1024, 256, 1)] * 22 + [(1024, 256, 1)]),
# resnet_utils.Block('block4', bottleneck, [(2048, 512, 1)] * 3)
# ]
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=23,
stride=1),
resnet_v1.resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1),
]
elif self._num_layers == 152:
# blocks = [
# resnet_utils.Block('block1', bottleneck,
# [(256, 64, 1)] * 2 + [(256, 64, 2)]),
# resnet_utils.Block('block2', bottleneck,
# [(512, 128, 1)] * 7 + [(512, 128, 2)]),
# # Use stride-1 for the last conv4 layer
# resnet_utils.Block('block3', bottleneck,
# [(1024, 256, 1)] * 35 + [(1024, 256, 1)]),
# resnet_utils.Block('block4', bottleneck, [(2048, 512, 1)] * 3)
# ]
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=8,
stride=2),
resnet_v1.resnet_v1_block('block3',
base_depth=256,
num_units=36,
stride=1),
resnet_v1.resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1),
]
else:
# other numbers are not supported
raise NotImplementedError
assert (0 <= cfg.FLAGS.fixed_blocks < 4)
if cfg.FLAGS.fixed_blocks == 3:
with slim.arg_scope(resnet_arg_scope(is_training=False)):
net = self.build_base()
net_conv4, _ = resnet_v1.resnet_v1(
net,
blocks[0:cfg.FLAGS.fixed_blocks],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
elif cfg.FLAGS.fixed_blocks > 0:
with slim.arg_scope(resnet_arg_scope(is_training=False)):
net = self.build_base()
net, _ = resnet_v1.resnet_v1(net,
blocks[0:cfg.FLAGS.fixed_blocks],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
net_conv4, _ = resnet_v1.resnet_v1(
net,
blocks[cfg.FLAGS.fixed_blocks:-1],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
else: # cfg.RESNET.FIXED_BLOCKS == 0
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
net = self.build_base()
net_conv4, _ = resnet_v1.resnet_v1(net,
blocks[0:-1],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
self._act_summaries.append(net_conv4)
self._layers['head'] = net_conv4
with tf.variable_scope(self._resnet_scope, self._resnet_scope):
# build the anchors for the image
self._anchor_component()
# rpn
rpn = slim.conv2d(net_conv4,
512, [3, 3],
trainable=is_training,
weights_initializer=initializer,
scope="rpn_conv/3x3")
self._act_summaries.append(rpn)
rpn_cls_score = slim.conv2d(rpn,
self._num_anchors * 2, [1, 1],
trainable=is_training,
weights_initializer=initializer,
padding='VALID',
activation_fn=None,
scope='rpn_cls_score')
# change it so that the score has 2 as its channel size
rpn_cls_score_reshape = self._reshape_layer(
rpn_cls_score, 2, 'rpn_cls_score_reshape')
rpn_cls_prob_reshape = self._softmax_layer(rpn_cls_score_reshape,
"rpn_cls_prob_reshape")
rpn_cls_prob = self._reshape_layer(rpn_cls_prob_reshape,
self._num_anchors * 2,
"rpn_cls_prob")
rpn_bbox_pred = slim.conv2d(rpn,
self._num_anchors * 4, [1, 1],
trainable=is_training,
weights_initializer=initializer,
padding='VALID',
activation_fn=None,
scope='rpn_bbox_pred')
if is_training:
rois, roi_scores = self._proposal_layer(
rpn_cls_prob, rpn_bbox_pred, "rois")
rpn_labels = self._anchor_target_layer(rpn_cls_score, "anchor")
# Try to have a determinestic order for the computing graph, for reproducibility
with tf.control_dependencies([rpn_labels]):
rois, _ = self._proposal_target_layer(
rois, roi_scores, "rpn_rois")
else:
if cfg.FLAGS.test_mode == 'nms':
rois, _ = self._proposal_layer(rpn_cls_prob, rpn_bbox_pred,
"rois")
elif cfg.FLAGS.test_mode == 'top':
rois, _ = self._proposal_top_layer(rpn_cls_prob,
rpn_bbox_pred, "rois")
else:
raise NotImplementedError
# rcnn
if cfg.FLAGS.pooling_mode == 'crop':
pool5 = self._crop_pool_layer(net_conv4, rois, "pool5")
else:
raise NotImplementedError
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
fc7, _ = resnet_v1.resnet_v1(pool5,
blocks[-1:],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
with tf.variable_scope(self._resnet_scope, self._resnet_scope):
# Average pooling done by reduce_mean
fc7 = tf.reduce_mean(fc7, axis=[1, 2])
cls_score = slim.fully_connected(fc7,
self._num_classes,
weights_initializer=initializer,
trainable=is_training,
activation_fn=None,
scope='cls_score')
cls_prob = self._softmax_layer(cls_score, "cls_prob")
bbox_pred = slim.fully_connected(
fc7,
self._num_classes * 4,
weights_initializer=initializer_bbox,
trainable=is_training,
activation_fn=None,
scope='bbox_pred')
self._predictions["rpn_cls_score"] = rpn_cls_score
self._predictions["rpn_cls_score_reshape"] = rpn_cls_score_reshape
self._predictions["rpn_cls_prob"] = rpn_cls_prob
self._predictions["rpn_bbox_pred"] = rpn_bbox_pred
self._predictions["cls_score"] = cls_score
self._predictions["cls_prob"] = cls_prob
self._predictions["bbox_pred"] = bbox_pred
self._predictions["rois"] = rois
self._score_summaries.update(self._predictions)
return rois, cls_prob, bbox_pred
def resnet_base(img_batch, scope_name, is_training=True):
'''
this code is derived from light-head rcnn.
https://github.com/zengarden/light_head_rcnn
It is convenient to freeze blocks. So we adapt this mode.
'''
if scope_name == 'resnet_v1_50':
middle_num_units = 6
elif scope_name == 'resnet_v1_101':
middle_num_units = 23
else:
raise NotImplementedError('We only support resnet_v1_50 or resnet_v1_101. Check your network name....yjr')
blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
# use stride 1 for the last conv4 layer.
resnet_v1_block('block3', base_depth=256, num_units=middle_num_units, stride=1)]
# when use fpn . stride list is [1, 2, 2]
with slim.arg_scope(resnet_arg_scope(is_training=False)):
with tf.variable_scope(scope_name, scope_name):
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1
net = resnet_utils.conv2d_same(
img_batch, 64, 7, stride=2, scope='conv1')
net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
net = slim.max_pool2d(
net, [3, 3], stride=2, padding='VALID', scope='pool1')
not_freezed = [False] * cfgs.FIXED_BLOCKS + (4-cfgs.FIXED_BLOCKS)*[True]
# Fixed_Blocks can be 1~3
with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[0]))):
C2, _ = resnet_v1.resnet_v1(net,
blocks[0:1],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C2 = tf.Print(C2, [tf.shape(C2)], summarize=10, message='C2_shape')
with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[1]))):
C3, _ = resnet_v1.resnet_v1(C2,
blocks[1:2],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C3 = tf.Print(C3, [tf.shape(C3)], summarize=10, message='C3_shape')
with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[2]))):
C4, _ = resnet_v1.resnet_v1(C3,
blocks[2:3],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C4 = tf.Print(C4, [tf.shape(C4)], summarize=10, message='C4_shape')
return C2, C4
def _build_network(self, sess, is_training=True):
# select initializers
if cfg.TRAIN.TRUNCATED:
initializer = tf.truncated_normal_initializer(mean=0.0, stddev=0.01)
initializer_bbox = tf.truncated_normal_initializer(mean=0.0, stddev=0.001)
else:
initializer = tf.random_normal_initializer(mean=0.0, stddev=0.01)
initializer_bbox = tf.random_normal_initializer(mean=0.0, stddev=0.001)
# choose different blocks for different number of layers
if self._num_layers == 50:
blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3', base_depth=256, num_units=6, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
elif self._num_layers == 101:
blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3', base_depth=256, num_units=23, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
elif self._num_layers == 152:
blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=8, stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3', base_depth=256, num_units=36, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)]
else:
# other numbers are not supported
raise NotImplementedError
assert (0 <= cfg.RESNET.FIXED_BLOCKS <= 3)
# Now the base is always fixed during training
with slim.arg_scope(resnet_arg_scope(is_training=False)):
net_conv = self._build_base()
if cfg.RESNET.FIXED_BLOCKS > 0:
with slim.arg_scope(resnet_arg_scope(is_training=False)):
net_conv, _ = resnet_v1.resnet_v1(net_conv,
blocks[0:cfg.RESNET.FIXED_BLOCKS],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
if cfg.RESNET.FIXED_BLOCKS < 3:
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
net_conv, _ = resnet_v1.resnet_v1(net_conv,
blocks[cfg.RESNET.FIXED_BLOCKS:-1],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
self._act_summaries.append(net_conv)
self._layers['head'] = net_conv
with tf.variable_scope(self._resnet_scope, self._resnet_scope):
# build the anchors for the image
self._anchor_component()
# region proposal network
rois = self._region_proposal(net_conv, is_training, initializer)
# region of interest pooling
if cfg.POOLING_MODE == 'crop':
pool5 = self._crop_pool_layer(net_conv, rois, "pool5")
else:
raise NotImplementedError
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
fc7, _ = resnet_v1.resnet_v1(pool5,
blocks[-1:],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
with tf.variable_scope(self._resnet_scope, self._resnet_scope):
# average pooling done by reduce_mean
fc7 = tf.reduce_mean(fc7, axis=[1, 2])
# region classification
cls_prob, bbox_pred = self._region_classification(fc7, is_training,
initializer, initializer_bbox)
self._score_summaries.update(self._predictions)
return rois, cls_prob, bbox_pred
def resnet_base(img_batch, scope_name, is_training):
'''
this code is derived from light-head rcnn.
https://github.com/zengarden/light_head_rcnn
It is convenient to freeze blocks. So we adapt this mode.
'''
if scope_name == 'resnet_v1_50':
middle_num_units = 6
elif scope_name == 'resnet_v1_101':
middle_num_units = 23 #101第3个block是23
elif scope_name == 'resnet_v1_152':
middle_num_units = 36
else:
raise NotImplementedError(
'We only support resnet_v1_50 、resnet_v1_101 、resnet152. Check your network name....yjr'
)
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3, stride=1),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3',
base_depth=256,
num_units=middle_num_units,
stride=2),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=2)
]
with slim.arg_scope(
resnet_arg_scope(is_training=is_training)): #resnet_arg_scope配置参数
with tf.variable_scope(scope_name, scope_name):
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1
net = resnet_utils.conv2d_same(
img_batch, 64, 7, stride=2,
scope='conv1') #RESNET第一个卷积层， 7*7*64， stride=2
net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]
]) #padding 0 ?? 类似与后面的samepadding?
net = slim.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='pool1') #3*3最大池化
#not_freezed = [False] * cfgs.FIXED_BLOCKS + (4-cfgs.FIXED_BLOCKS)*[True] #不冻结的Blocks层
#net = tf.Print(net, [tf.shape(net)], summarize=10, message='net')
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C2, end_points_C2 = resnet_v1.resnet_v1(
net,
blocks[0:1], #传入的是一个resnet_utils.Block类 一整个Resnet block
global_pool=False,
include_root_block=False,
scope=scope_name
) #返回当前构建resnet block层：C2 end_points_C2： collection中已有的特征图 越到后面越多
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C3, end_points_C3 = resnet_v1.resnet_v1(
C2,
blocks[1:2],
global_pool=False,
include_root_block=False,
scope=scope_name) #构建第二个block模块
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C4, end_points_C4 = resnet_v1.resnet_v1(C3,
blocks[2:3],
global_pool=False,
include_root_block=False,
scope=scope_name)
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C5, end_points_C5 = resnet_v1.resnet_v1(C4,
blocks[3:4],
num_classes=cfgs.num_classes,
global_pool=True,
include_root_block=False,
scope=scope_name)
C5 = tf.reshape(C5, [-1, cfgs.num_classes])
return C5
def __init__(self,
in_channels=3,
num_classes=0,
num_nodes=17 + 2,
edge_importance_weighting=True,
is_training=True,
num_fc=1024,
posetype=1,
bi_posegraph=False,
bodypart=False,
binary=False,
posemap=False,
posegraph=False,
semantic=False,
data_bn=True):
self.predictions = {}
self.train_summaries = []
self.losses = {}
self.lr = tf.placeholder(tf.float32)
self.num_binary = 1 # existence of HOI (0 or 1)
self.num_classes = 600
self.gt_binary_label = tf.placeholder(tf.float32,
shape=[None, 1],
name='gt_binary_label')
self.gt_class_HO = tf.placeholder(tf.float32,
shape=[None, 600],
name='gt_class_HO')
self.is_training = is_training
if self.is_training:
self.keep_prob = cfg.TRAIN_DROP_OUT_BINARY
self.keep_prob_tail = .5
else:
self.keep_prob = 1
self.keep_prob_tail = 1
self.image = tf.placeholder(tf.float32,
shape=[1, None, None, 3],
name='image')
self.head = tf.placeholder(tf.float32,
shape=[1, None, None, 1024],
name='head')
self.H_boxes = tf.placeholder(tf.float32,
shape=[None, 5],
name='H_boxes')
self.O_boxes = tf.placeholder(tf.float32,
shape=[None, 5],
name='O_boxes')
self.partboxes = tf.placeholder(tf.float32,
shape=[None, 17, 5],
name='part_boxes')
self.semantic = tf.placeholder(tf.float32,
shape=[None, 1024],
name='semantic_feat')
self.H_num = tf.placeholder(tf.int32)
# Control the network architecture
self.bodypart = bodypart
self.binary = binary
self.posemap = posemap
self.posegraph = posegraph
self.bi_posegraph = bi_posegraph
self.posetype = posetype
self.semantic_flag = semantic
if self.posetype == 1:
self.spatial = tf.placeholder(tf.float32,
shape=[None, 64, 64, 2],
name='sp')
else:
self.spatial = tf.placeholder(tf.float32,
shape=[None, 64, 64, 3],
name='sp')
# ResNet 50 Network
self.scope = 'resnet_v1_50'
self.num_fc = 1024
self.num_fc2 = num_fc
self.stride = [
16,
]
if tf.__version__ == '1.1.0':
self.blocks = [
resnet_utils.Block('block1', resnet_v1.bottleneck,
[(256, 64, 1)] * 2 + [(256, 64, 2)]),
resnet_utils.Block('block2', resnet_v1.bottleneck,
[(512, 128, 1)] * 3 + [(512, 128, 2)]),
resnet_utils.Block('block3', resnet_v1.bottleneck,
[(1024, 256, 1)] * 5 + [(1024, 256, 1)]),
resnet_utils.Block('block4', resnet_v1.bottleneck,
[(2048, 512, 1)] * 3),
resnet_utils.Block('block5', resnet_v1.bottleneck,
[(2048, 512, 1)] * 3)
]
else:
from tensorflow.contrib.slim.python.slim.nets.resnet_v1 import resnet_v1_block
self.blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2),
resnet_v1_block('block2',
base_depth=128,
num_units=4,
stride=2),
resnet_v1_block('block3',
base_depth=256,
num_units=6,
stride=1),
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1),
resnet_v1_block('block5',
base_depth=512,
num_units=3,
stride=1)
]
# GCN setting
self.num_nodes = num_nodes
self.c = in_channels
self.data_bn = data_bn
self.strategy = 'spatial'
self.graph = Graph(strategy=self.strategy)
self.A = tf.convert_to_tensor(self.graph.A.astype(
np.float32)) # [None, num_nodes, num_nodes]
self.spatial_kernel_size = self.A.shape[0]
# [N, C, T, V, M] = [N, 3, 1, 19, 1]
self.Gnodes = tf.placeholder(
tf.float32,
shape=[None, self.c, 1, self.num_nodes, 1],
name='Gnodes')
# ST_GCN
self.depth_st_gcn_networks = 10
def __init__(self, model_name):
self.model_name = model_name
self.visualize = {}
self.test_visualize = {}
self.intermediate = {}
self.predictions = {}
self.score_summaries = {}
self.event_summaries = {}
self.train_summaries = []
self.losses = {}
self.image = tf.placeholder(tf.float32,
shape=[1, None, None, 3],
name='image')
self.spatial = tf.placeholder(tf.float32,
shape=[None, 64, 64, 3],
name='sp')
self.H_boxes = tf.placeholder(tf.float32,
shape=[None, 5],
name='H_boxes')
self.O_boxes = tf.placeholder(tf.float32,
shape=[None, 5],
name='O_boxes')
self.gt_class_HO = tf.placeholder(tf.float32,
shape=[None, 600],
name='gt_class_HO')
self.H_num = tf.placeholder(tf.int32) # positive nums
self.image_id = tf.placeholder(tf.int32)
self.num_classes = 600
self.compose_num_classes = 600
self.num_fc = 1024
self.verb_num_classes = 117
self.obj_num_classes = 80
self.scope = 'resnet_v1_101'
self.stride = [
16,
]
self.lr = tf.placeholder(tf.float32)
if tf.__version__ == '1.1.0':
raise Exception('wrong tensorflow version 1.1.0')
else:
from tensorflow.contrib.slim.python.slim.nets.resnet_v1 import resnet_v1_block
self.blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2),
resnet_v1_block('block2',
base_depth=128,
num_units=4,
stride=2),
resnet_v1_block('block3',
base_depth=256,
num_units=23,
stride=1),
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1),
resnet_v1_block('block5',
base_depth=512,
num_units=3,
stride=1)
]
if self.model_name.__contains__('unique_weights') or self.model_name.__contains__('_pa3')\
or self.model_name.__contains__('_pa4'):
print("add block6 unique_weights2")
self.blocks.append(
resnet_v1_block('block6',
base_depth=512,
num_units=3,
stride=1))
"""We copy from TIN. calculated by log(1/(n_c/sum(n_c)) c is the category and n_c is
the number of positive samples"""
self.HO_weight = np.array([
9.192927, 9.778443, 10.338059, 9.164914, 9.075144, 10.045923,
8.714437, 8.59822, 12.977117, 6.2745423, 11.227917, 6.765012,
9.436157, 9.56762, 11.0675745, 11.530198, 9.609821, 9.897503,
6.664475, 6.811699, 6.644726, 9.170454, 13.670264, 3.903943,
10.556748, 8.814335, 9.519224, 12.753973, 11.590822, 8.278912,
5.5245695, 9.7286825, 8.997436, 10.699849, 9.601237, 11.965516,
9.192927, 10.220277, 6.056692, 7.734048, 8.42324, 6.586457,
6.969533, 10.579222, 13.670264, 4.4531965, 9.326459, 9.288238,
8.071842, 10.431585, 12.417501, 11.530198, 11.227917, 4.0678477,
8.854023, 12.571651, 8.225684, 10.996116, 11.0675745, 10.100731,
7.0376034, 7.463688, 12.571651, 14.363411, 5.4902234, 11.0675745,
14.363411, 8.45805, 10.269067, 9.820116, 14.363411, 11.272368,
11.105314, 7.981595, 9.198626, 3.3284247, 14.363411, 12.977117,
9.300817, 10.032678, 12.571651, 10.114916, 10.471591, 13.264799,
14.363411, 8.01953, 10.412168, 9.644913, 9.981384, 7.2197933,
14.363411, 3.1178555, 11.031207, 8.934066, 7.546675, 6.386472,
12.060826, 8.862153, 9.799063, 12.753973, 12.753973, 10.412168,
10.8976755, 10.471591, 12.571651, 9.519224, 6.207762, 12.753973,
6.60636, 6.2896967, 4.5198326, 9.7887, 13.670264, 11.878505,
11.965516, 8.576513, 11.105314, 9.192927, 11.47304, 11.367679,
9.275815, 11.367679, 9.944571, 11.590822, 10.451388, 9.511381,
11.144535, 13.264799, 5.888291, 11.227917, 10.779892, 7.643191,
11.105314, 9.414651, 11.965516, 14.363411, 12.28397, 9.909063,
8.94731, 7.0330057, 8.129001, 7.2817025, 9.874775, 9.758241,
11.105314, 5.0690055, 7.4768796, 10.129305, 9.54313, 13.264799,
9.699972, 11.878505, 8.260853, 7.1437693, 6.9321113, 6.990665,
8.8104515, 11.655361, 13.264799, 4.515912, 9.897503, 11.418972,
8.113436, 8.795067, 10.236277, 12.753973, 14.363411, 9.352776,
12.417501, 0.6271591, 12.060826, 12.060826, 12.166186, 5.2946343,
11.318889, 9.8308115, 8.016022, 9.198626, 10.8976755, 13.670264,
11.105314, 14.363411, 9.653881, 9.503599, 12.753973, 5.80546,
9.653881, 9.592727, 12.977117, 13.670264, 7.995224, 8.639826,
12.28397, 6.586876, 10.929424, 13.264799, 8.94731, 6.1026597,
12.417501, 11.47304, 10.451388, 8.95624, 10.996116, 11.144535,
11.031207, 13.670264, 13.670264, 6.397866, 7.513285, 9.981384,
11.367679, 11.590822, 7.4348736, 4.415428, 12.166186, 8.573451,
12.977117, 9.609821, 8.601359, 9.055143, 11.965516, 11.105314,
13.264799, 5.8201604, 10.451388, 9.944571, 7.7855496, 14.363411,
8.5463, 13.670264, 7.9288645, 5.7561946, 9.075144, 9.0701065,
5.6871653, 11.318889, 10.252538, 9.758241, 9.407584, 13.670264,
8.570397, 9.326459, 7.488179, 11.798462, 9.897503, 6.7530537,
4.7828183, 9.519224, 7.6492405, 8.031909, 7.8180614, 4.451856,
10.045923, 10.83705, 13.264799, 13.670264, 4.5245686, 14.363411,
10.556748, 10.556748, 14.363411, 13.670264, 14.363411, 8.037262,
8.59197, 9.738439, 8.652985, 10.045923, 9.400566, 10.9622135,
11.965516, 10.032678, 5.9017305, 9.738439, 12.977117, 11.105314,
10.725825, 9.080208, 11.272368, 14.363411, 14.363411, 13.264799,
6.9279733, 9.153925, 8.075553, 9.126969, 14.363411, 8.903826,
9.488214, 5.4571533, 10.129305, 10.579222, 12.571651, 11.965516,
6.237189, 9.428937, 9.618479, 8.620408, 11.590822, 11.655361,
9.968962, 10.8080635, 10.431585, 14.363411, 3.796231, 12.060826,
10.302968, 9.551227, 8.75394, 10.579222, 9.944571, 14.363411,
6.272396, 10.625742, 9.690582, 13.670264, 11.798462, 13.670264,
11.724354, 9.993963, 8.230013, 9.100721, 10.374427, 7.865129,
6.514087, 14.363411, 11.031207, 11.655361, 12.166186, 7.419324,
9.421769, 9.653881, 10.996116, 12.571651, 13.670264, 5.912144,
9.7887, 8.585759, 8.272101, 11.530198, 8.886948, 5.9870906,
9.269661, 11.878505, 11.227917, 13.670264, 8.339964, 7.6763024,
10.471591, 10.451388, 13.670264, 11.185357, 10.032678, 9.313555,
12.571651, 3.993144, 9.379805, 9.609821, 14.363411, 9.709451,
8.965248, 10.451388, 7.0609145, 10.579222, 13.264799, 10.49221,
8.978916, 7.124196, 10.602211, 8.9743395, 7.77862, 8.073695,
9.644913, 9.339531, 8.272101, 4.794418, 9.016304, 8.012526,
10.674532, 14.363411, 7.995224, 12.753973, 5.5157638, 8.934066,
10.779892, 7.930471, 11.724354, 8.85808, 5.9025764, 14.363411,
12.753973, 12.417501, 8.59197, 10.513264, 10.338059, 14.363411,
7.7079706, 14.363411, 13.264799, 13.264799, 10.752493, 14.363411,
14.363411, 13.264799, 12.417501, 13.670264, 6.5661197, 12.977117,
11.798462, 9.968962, 12.753973, 11.47304, 11.227917, 7.6763024,
10.779892, 11.185357, 14.363411, 7.369478, 14.363411, 9.944571,
10.779892, 10.471591, 9.54313, 9.148476, 10.285873, 10.412168,
12.753973, 14.363411, 6.0308623, 13.670264, 10.725825, 12.977117,
11.272368, 7.663911, 9.137665, 10.236277, 13.264799, 6.715625,
10.9622135, 14.363411, 13.264799, 9.575919, 9.080208, 11.878505,
7.1863923, 9.366199, 8.854023, 9.874775, 8.2857685, 13.670264,
11.878505, 12.166186, 7.616999, 9.44343, 8.288065, 8.8104515,
8.347254, 7.4738197, 10.302968, 6.936267, 11.272368, 7.058223,
5.0138307, 12.753973, 10.173757, 9.863602, 11.318889, 9.54313,
10.996116, 12.753973, 7.8339925, 7.569945, 7.4427395, 5.560738,
12.753973, 10.725825, 10.252538, 9.307165, 8.491293, 7.9161053,
7.8849015, 7.782772, 6.3088884, 8.866243, 9.8308115, 14.363411,
10.8976755, 5.908519, 10.269067, 9.176025, 9.852551, 9.488214,
8.90809, 8.537411, 9.653881, 8.662968, 11.965516, 10.143904,
14.363411, 14.363411, 9.407584, 5.281472, 11.272368, 12.060826,
14.363411, 7.4135547, 8.920994, 9.618479, 8.891141, 14.363411,
12.060826, 11.965516, 10.9622135, 10.9622135, 14.363411, 5.658909,
8.934066, 12.571651, 8.614018, 11.655361, 13.264799, 10.996116,
13.670264, 8.965248, 9.326459, 11.144535, 14.363411, 6.0517673,
10.513264, 8.7430105, 10.338059, 13.264799, 6.878481, 9.065094,
8.87035, 14.363411, 9.92076, 6.5872955, 10.32036, 14.363411,
9.944571, 11.798462, 10.9622135, 11.031207, 7.652888, 4.334878,
13.670264, 13.670264, 14.363411, 10.725825, 12.417501, 14.363411,
13.264799, 11.655361, 10.338059, 13.264799, 12.753973, 8.206432,
8.916674, 8.59509, 14.363411, 7.376845, 11.798462, 11.530198,
11.318889, 11.185357, 5.0664344, 11.185357, 9.372978, 10.471591,
9.6629305, 11.367679, 8.73579, 9.080208, 11.724354, 5.04781,
7.3777695, 7.065643, 12.571651, 11.724354, 12.166186, 12.166186,
7.215852, 4.374113, 11.655361, 11.530198, 14.363411, 6.4993753,
11.031207, 8.344818, 10.513264, 10.032678, 14.363411, 14.363411,
4.5873594, 12.28397, 13.670264, 12.977117, 10.032678, 9.609821
],
dtype='float32').reshape(1, 600)
num_inst_path = cfg.ROOT_DIR + '/Data/num_inst.npy'
num_inst = np.load(num_inst_path)
self.num_inst = num_inst
verb_to_HO_matrix, obj_to_HO_matrix = get_convert_matrix(
self.verb_num_classes, self.obj_num_classes)
self.obj_to_HO_matrix = tf.constant(obj_to_HO_matrix, tf.float32)
self.verb_to_HO_matrix = tf.constant(verb_to_HO_matrix, tf.float32)
self.gt_obj_class = tf.cast(
tf.matmul(
self.gt_class_HO, self.obj_to_HO_matrix, transpose_b=True) > 0,
tf.float32)
self.gt_verb_class = tf.cast(
tf.matmul(self.gt_class_HO,
self.verb_to_HO_matrix,
transpose_b=True) > 0, tf.float32)
def resnet_base(img_batch, scope_name, is_training=False):
'''
this code is derived from light-head rcnn.
https://github.com/zengarden/light_head_rcnn
It is convenient to freeze blocks. So we adapt this mode.
'''
if scope_name == 'resnet_v1_50':
middle_num_units = 6
elif scope_name == 'resnet_v1_101':
middle_num_units = 23
else:
raise NotImplementedError(
'We only support resnet_v1_50 or resnet_v1_101. Check your network name....yjr'
)
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=9, stride=2),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)
]
# when use fpn . stride list is [1, 2, 2]
with slim.arg_scope(resnet_arg_scope(is_training=False)):
with tf.variable_scope(scope_name, scope_name):
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1
net = resnet_utils.conv2d_same(img_batch,
64,
7,
stride=2,
scope='conv1')
net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
net = slim.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='pool1')
not_freezed = [False] * 0 + (4 - 0) * [True]
# Fixed_Blocks can be 1~3
with slim.arg_scope(
resnet_arg_scope(is_training=(is_training and not_freezed[0]))):
C2, end_points_C2 = resnet_v1.resnet_v1(net,
blocks[0:1],
global_pool=False,
include_root_block=False,
scope=scope_name)
#C2=tf.layers.average_pooling2d(inputs=C2, pool_size=3, strides=2,padding="valid")
#C2=tf.reduce_mean(C2, axis=[1, 2], keep_dims=False, name='global_average_pooling')
with slim.arg_scope(
resnet_arg_scope(is_training=(is_training and not_freezed[1]))):
C3, end_points_C3 = resnet_v1.resnet_v1(C2,
blocks[1:2],
global_pool=False,
include_root_block=False,
scope=scope_name)
C3 = slim.avg_pool2d(C3, 2)
#C3 = tf.reduce_mean(C3, axis=[1, 2], keep_dims=False, name='global_average_pooling')
#return C3
'''with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[2]))):
C4, end_points_C4 = resnet_v1.resnet_v1(C3,
blocks[2:3],
global_pool=False,
include_root_block=False,
scope=scope_name)'''
return C3
def resnet_base(img_batch, scope_name, is_training=True):
'''
this code is derived from light-head rcnn.
https://github.com/zengarden/light_head_rcnn
It is convenient to freeze blocks. So we adapt this mode.
'''
if scope_name == 'resnet_v1_50':
middle_num_units = 6
elif scope_name == 'resnet_v1_101':
middle_num_units = 23
else:
raise NotImplementedError(
'We only support resnet_v1_50 or resnet_v1_101. Check your network name....'
)
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3',
base_depth=256,
num_units=middle_num_units,
stride=2),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1)
]
# when use fpn . stride list is [1, 2, 2]
with slim.arg_scope(resnet_arg_scope(is_training=False)):
with tf.variable_scope(scope_name, scope_name):
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1
net = resnet_utils.conv2d_same(img_batch,
64,
7,
stride=2,
scope='conv1')
net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
net = slim.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='pool1')
not_freezed = [False
] * cfgs.FIXED_BLOCKS + (4 - cfgs.FIXED_BLOCKS) * [True]
# Fixed_Blocks can be 1~3
with slim.arg_scope(
resnet_arg_scope(is_training=(is_training and not_freezed[0]))):
C2, end_points_C2 = resnet_v1.resnet_v1(net,
blocks[0:1],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C2 = tf.Print(C2, [tf.shape(C2)], summarize=10, message='C2_shape')
# add_heatmap(C2, name='Layer2/C2_heat')
with slim.arg_scope(
resnet_arg_scope(is_training=(is_training and not_freezed[1]))):
C3, end_points_C3 = resnet_v1.resnet_v1(C2,
blocks[1:2],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C3 = tf.Print(C3, [tf.shape(C3)], summarize=10, message='C3_shape')
# add_heatmap(C3, name='Layer3/C3_heat')
with slim.arg_scope(
resnet_arg_scope(is_training=(is_training and not_freezed[2]))):
C4, end_points_C4 = resnet_v1.resnet_v1(C3,
blocks[2:3],
global_pool=False,
include_root_block=False,
scope=scope_name)
# add_heatmap(C4, name='Layer4/C4_heat')
# C4 = tf.Print(C4, [tf.shape(C4)], summarize=10, message='C4_shape')
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C5, end_points_C5 = resnet_v1.resnet_v1(C4,
blocks[3:4],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C5 = tf.Print(C5, [tf.shape(C5)], summarize=10, message='C5_shape')
# add_heatmap(C5, name='Layer5/C5_heat')
feature_dict = {
'C2':
end_points_C2['{}/block1/unit_2/bottleneck_v1'.format(scope_name)],
'C3':
end_points_C3['{}/block2/unit_3/bottleneck_v1'.format(scope_name)],
'C4':
end_points_C4['{}/block3/unit_{}/bottleneck_v1'.format(
scope_name, middle_num_units - 1)],
'C5':
end_points_C5['{}/block4/unit_3/bottleneck_v1'.format(scope_name)],
# 'C5': end_points_C5['{}/block4'.format(scope_name)],
}
pyramid_dict = {}
with tf.variable_scope('build_pyramid'):
with slim.arg_scope([slim.conv2d],
weights_regularizer=slim.l2_regularizer(
cfgs.WEIGHT_DECAY),
activation_fn=None,
normalizer_fn=None):
P5 = slim.conv2d(feature_dict['C5'],
num_outputs=256,
kernel_size=[1, 1],
stride=1,
scope='build_P5')
pyramid_dict['P5'] = P5
for level in range(4, 1, -1): # build [P4, P3, P2]
pyramid_dict['P%d' % level] = fusion_two_layer(
C_i=feature_dict["C%d" % level],
P_j=pyramid_dict["P%d" % (level + 1)],
scope='build_P%d' % level)
for level in range(5, 1, -1):
pyramid_dict['P%d' % level] = slim.conv2d(
pyramid_dict['P%d' % level],
num_outputs=256,
kernel_size=[3, 3],
padding="SAME",
stride=1,
scope="fuse_P%d" % level)
if "P6" in cfgs.LEVLES:
P6 = slim.avg_pool2d(pyramid_dict['P5'],
kernel_size=[1, 1],
stride=2,
scope='build_P6')
pyramid_dict['P6'] = P6
# for level in range(5, 1, -1):
# add_heatmap(feature_dict['C%d' % level], name='Layer%d/C%d_heat' % (level, level))
# add_heatmap(pyramid_dict['P%d' % level], name='Layer%d/P%d_heat' % (level, level))
# return [P2, P3, P4, P5, P6]
print("we are in Pyramid::-======>>>>")
print(cfgs.LEVLES)
print("base_anchor_size are: ", cfgs.BASE_ANCHOR_SIZE_LIST)
print(20 * "__")
return [pyramid_dict[level_name] for level_name in cfgs.LEVLES]
def __init__(self):
self.visualize = {}
self.intermediate = {}
self.predictions = {}
self.score_summaries = {}
self.event_summaries = {}
self.train_summaries = []
self.losses = {}
self.image = tf.placeholder(tf.float32, shape=[1, None, None, 3], name = 'image')
self.spatial = tf.placeholder(tf.float32, shape=[None, 64, 64, 3], name = 'sp')
self.H_boxes = tf.placeholder(tf.float32, shape=[None, 5], name = 'H_boxes')
self.O_boxes = tf.placeholder(tf.float32, shape=[None, 5], name = 'O_boxes')
self.gt_class_HO = tf.placeholder(tf.float32, shape=[None, 600], name = 'gt_class_HO')
self.gt_binary_label = tf.placeholder(tf.float32, shape=[None, 2], name = 'gt_binary_label')
self.H_num = tf.placeholder(tf.int32)
self.HO_weight = np.array([
9.192927, 9.778443, 10.338059, 9.164914, 9.075144, 10.045923, 8.714437, 8.59822, 12.977117, 6.2745423,
11.227917, 6.765012, 9.436157, 9.56762, 11.0675745, 11.530198, 9.609821, 9.897503, 6.664475, 6.811699,
6.644726, 9.170454, 13.670264, 3.903943, 10.556748, 8.814335, 9.519224, 12.753973, 11.590822, 8.278912,
5.5245695, 9.7286825, 8.997436, 10.699849, 9.601237, 11.965516, 9.192927, 10.220277, 6.056692, 7.734048,
8.42324, 6.586457, 6.969533, 10.579222, 13.670264, 4.4531965, 9.326459, 9.288238, 8.071842, 10.431585,
12.417501, 11.530198, 11.227917, 4.0678477, 8.854023, 12.571651, 8.225684, 10.996116, 11.0675745, 10.100731,
7.0376034, 7.463688, 12.571651, 14.363411, 5.4902234, 11.0675745, 14.363411, 8.45805, 10.269067, 9.820116,
14.363411, 11.272368, 11.105314, 7.981595, 9.198626, 3.3284247, 14.363411, 12.977117, 9.300817, 10.032678,
12.571651, 10.114916, 10.471591, 13.264799, 14.363411, 8.01953, 10.412168, 9.644913, 9.981384, 7.2197933,
14.363411, 3.1178555, 11.031207, 8.934066, 7.546675, 6.386472, 12.060826, 8.862153, 9.799063, 12.753973,
12.753973, 10.412168, 10.8976755, 10.471591, 12.571651, 9.519224, 6.207762, 12.753973, 6.60636, 6.2896967,
4.5198326, 9.7887, 13.670264, 11.878505, 11.965516, 8.576513, 11.105314, 9.192927, 11.47304, 11.367679,
9.275815, 11.367679, 9.944571, 11.590822, 10.451388, 9.511381, 11.144535, 13.264799, 5.888291, 11.227917,
10.779892, 7.643191, 11.105314, 9.414651, 11.965516, 14.363411, 12.28397, 9.909063, 8.94731, 7.0330057,
8.129001, 7.2817025, 9.874775, 9.758241, 11.105314, 5.0690055, 7.4768796, 10.129305, 9.54313, 13.264799,
9.699972, 11.878505, 8.260853, 7.1437693, 6.9321113, 6.990665, 8.8104515, 11.655361, 13.264799, 4.515912,
9.897503, 11.418972, 8.113436, 8.795067, 10.236277, 12.753973, 14.363411, 9.352776, 12.417501, 0.6271591,
12.060826, 12.060826, 12.166186, 5.2946343, 11.318889, 9.8308115, 8.016022, 9.198626, 10.8976755, 13.670264,
11.105314, 14.363411, 9.653881, 9.503599, 12.753973, 5.80546, 9.653881, 9.592727, 12.977117, 13.670264,
7.995224, 8.639826, 12.28397, 6.586876, 10.929424, 13.264799, 8.94731, 6.1026597, 12.417501, 11.47304,
10.451388, 8.95624, 10.996116, 11.144535, 11.031207, 13.670264, 13.670264, 6.397866, 7.513285, 9.981384,
11.367679, 11.590822, 7.4348736, 4.415428, 12.166186, 8.573451, 12.977117, 9.609821, 8.601359, 9.055143,
11.965516, 11.105314, 13.264799, 5.8201604, 10.451388, 9.944571, 7.7855496, 14.363411, 8.5463, 13.670264,
7.9288645, 5.7561946, 9.075144, 9.0701065, 5.6871653, 11.318889, 10.252538, 9.758241, 9.407584, 13.670264,
8.570397, 9.326459, 7.488179, 11.798462, 9.897503, 6.7530537, 4.7828183, 9.519224, 7.6492405, 8.031909,
7.8180614, 4.451856, 10.045923, 10.83705, 13.264799, 13.670264, 4.5245686, 14.363411, 10.556748, 10.556748,
14.363411, 13.670264, 14.363411, 8.037262, 8.59197, 9.738439, 8.652985, 10.045923, 9.400566, 10.9622135,
11.965516, 10.032678, 5.9017305, 9.738439, 12.977117, 11.105314, 10.725825, 9.080208, 11.272368, 14.363411,
14.363411, 13.264799, 6.9279733, 9.153925, 8.075553, 9.126969, 14.363411, 8.903826, 9.488214, 5.4571533,
10.129305, 10.579222, 12.571651, 11.965516, 6.237189, 9.428937, 9.618479, 8.620408, 11.590822, 11.655361,
9.968962, 10.8080635, 10.431585, 14.363411, 3.796231, 12.060826, 10.302968, 9.551227, 8.75394, 10.579222,
9.944571, 14.363411, 6.272396, 10.625742, 9.690582, 13.670264, 11.798462, 13.670264, 11.724354, 9.993963,
8.230013, 9.100721, 10.374427, 7.865129, 6.514087, 14.363411, 11.031207, 11.655361, 12.166186, 7.419324,
9.421769, 9.653881, 10.996116, 12.571651, 13.670264, 5.912144, 9.7887, 8.585759, 8.272101, 11.530198, 8.886948,
5.9870906, 9.269661, 11.878505, 11.227917, 13.670264, 8.339964, 7.6763024, 10.471591, 10.451388, 13.670264,
11.185357, 10.032678, 9.313555, 12.571651, 3.993144, 9.379805, 9.609821, 14.363411, 9.709451, 8.965248,
10.451388, 7.0609145, 10.579222, 13.264799, 10.49221, 8.978916, 7.124196, 10.602211, 8.9743395, 7.77862,
8.073695, 9.644913, 9.339531, 8.272101, 4.794418, 9.016304, 8.012526, 10.674532, 14.363411, 7.995224,
12.753973, 5.5157638, 8.934066, 10.779892, 7.930471, 11.724354, 8.85808, 5.9025764, 14.363411, 12.753973,
12.417501, 8.59197, 10.513264, 10.338059, 14.363411, 7.7079706, 14.363411, 13.264799, 13.264799, 10.752493,
14.363411, 14.363411, 13.264799, 12.417501, 13.670264, 6.5661197, 12.977117, 11.798462, 9.968962, 12.753973,
11.47304, 11.227917, 7.6763024, 10.779892, 11.185357, 14.363411, 7.369478, 14.363411, 9.944571, 10.779892,
10.471591, 9.54313, 9.148476, 10.285873, 10.412168, 12.753973, 14.363411, 6.0308623, 13.670264, 10.725825,
12.977117, 11.272368, 7.663911, 9.137665, 10.236277, 13.264799, 6.715625, 10.9622135, 14.363411, 13.264799,
9.575919, 9.080208, 11.878505, 7.1863923, 9.366199, 8.854023, 9.874775, 8.2857685, 13.670264, 11.878505,
12.166186, 7.616999, 9.44343, 8.288065, 8.8104515, 8.347254, 7.4738197, 10.302968, 6.936267, 11.272368,
7.058223, 5.0138307, 12.753973, 10.173757, 9.863602, 11.318889, 9.54313, 10.996116, 12.753973, 7.8339925,
7.569945, 7.4427395, 5.560738, 12.753973, 10.725825, 10.252538, 9.307165, 8.491293, 7.9161053, 7.8849015,
7.782772, 6.3088884, 8.866243, 9.8308115, 14.363411, 10.8976755, 5.908519, 10.269067, 9.176025, 9.852551,
9.488214, 8.90809, 8.537411, 9.653881, 8.662968, 11.965516, 10.143904, 14.363411, 14.363411, 9.407584,
5.281472, 11.272368, 12.060826, 14.363411, 7.4135547, 8.920994, 9.618479, 8.891141, 14.363411, 12.060826,
11.965516, 10.9622135, 10.9622135, 14.363411, 5.658909, 8.934066, 12.571651, 8.614018, 11.655361, 13.264799,
10.996116, 13.670264, 8.965248, 9.326459, 11.144535, 14.363411, 6.0517673, 10.513264, 8.7430105, 10.338059,
13.264799, 6.878481, 9.065094, 8.87035, 14.363411, 9.92076, 6.5872955, 10.32036, 14.363411, 9.944571,
11.798462, 10.9622135, 11.031207, 7.652888, 4.334878, 13.670264, 13.670264, 14.363411, 10.725825, 12.417501,
14.363411, 13.264799, 11.655361, 10.338059, 13.264799, 12.753973, 8.206432, 8.916674, 8.59509, 14.363411,
7.376845, 11.798462, 11.530198, 11.318889, 11.185357, 5.0664344, 11.185357, 9.372978, 10.471591, 9.6629305,
11.367679, 8.73579, 9.080208, 11.724354, 5.04781, 7.3777695, 7.065643, 12.571651, 11.724354, 12.166186,
12.166186, 7.215852, 4.374113, 11.655361, 11.530198, 14.363411, 6.4993753, 11.031207, 8.344818, 10.513264,
10.032678, 14.363411, 14.363411, 4.5873594, 12.28397, 13.670264, 12.977117, 10.032678, 9.609821
], dtype = 'float32').reshape(1,600)
self.binary_weight = np.array([1.6094379124341003, 0.22314355131420976], dtype = 'float32').reshape(1,2)
self.num_classes = 600 # HOI
self.num_binary = 2 # existence (0 or 1) of HOI
self.num_fc = 1024
self.scope = 'resnet_v1_50'
self.stride = [16, ]
self.lr = tf.placeholder(tf.float32)
if tf.__version__ == '1.1.0':
self.blocks = [resnet_utils.Block('block1', resnet_v1.bottleneck,[(256, 64, 1)] * 2 + [(256, 64, 2)]),
resnet_utils.Block('block2', resnet_v1.bottleneck,[(512, 128, 1)] * 3 + [(512, 128, 2)]),
resnet_utils.Block('block3', resnet_v1.bottleneck,[(1024, 256, 1)] * 5 + [(1024, 256, 1)]),
resnet_utils.Block('block4', resnet_v1.bottleneck,[(2048, 512, 1)] * 3),
resnet_utils.Block('block5', resnet_v1.bottleneck,[(2048, 512, 1)] * 3)]
else: # we use tf 1.2.0 here, Resnet-50
from tensorflow.contrib.slim.python.slim.nets.resnet_v1 import resnet_v1_block
self.blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2), # a resnet_v1 bottleneck block
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=6, stride=1), # feature former
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1),
resnet_v1_block('block5', base_depth=512, num_units=3, stride=1)]
def __init__(self, model_name):
self.model_name = model_name
self.visualize = {}
self.test_visualize = {}
self.intermediate = {}
self.predictions = {}
self.score_summaries = {}
self.event_summaries = {}
self.train_summaries = []
self.losses = {}
self.image = tf.placeholder(tf.float32, shape=[1, None, None, 3], name = 'image')
self.spatial = tf.placeholder(tf.float32, shape=[None, 64, 64, 3], name = 'sp')
# self.Hsp_boxes = tf.placeholder(tf.float32, shape=[None, 5], name = 'Hsp_boxes')
self.H_boxes = tf.placeholder(tf.float32, shape=[None, 5], name='H_boxes')
self.O_boxes = tf.placeholder(tf.float32, shape=[None, 5], name = 'O_boxes')
self.gt_class_H = tf.placeholder(tf.float32, shape=[None, 24], name = 'gt_class_H')
self.gt_class_HO = tf.placeholder(tf.float32, shape=[None, 24], name = 'gt_class_HO')
self.gt_class_sp = tf.placeholder(tf.float32, shape=[None, 24], name = 'gt_class_sp')
self.Mask_HO = tf.placeholder(tf.float32, shape=[None, 24], name = 'HO_mask')
self.Mask_H = tf.placeholder(tf.float32, shape=[None, 24], name = 'H_mask')
self.Mask_sp = tf.placeholder(tf.float32, shape=[None, 24], name = 'sp_mask')
self.gt_compose = tf.placeholder(tf.float32, shape=[None, 222], name='gt_compose')
self.gt_obj = tf.placeholder(tf.float32, shape=[None, 80], name='gt_obj')
self.H_num = tf.placeholder(tf.int32)
self.image_id = tf.placeholder(tf.int32)
self.num_classes = 24
if self.model_name.__contains__('_t4_'):
self.num_classes = 222
if self.model_name.__contains__('_t5_'):
self.verb_num_classes = 21
self.num_classes = 222
self.num_fc = 1024
self.verb_num_classes = 24
self.obj_num_classes = 80
self.scope = 'resnet_v1_50'
self.stride = [16, ]
# self.lr = tf.placeholder(tf.float32)
if tf.__version__ == '1.1.0':
self.blocks = [resnet_utils.Block('block1', resnet_v1.bottleneck,[(256, 64, 1)] * 2 + [(256, 64, 2)]),
resnet_utils.Block('block2', resnet_v1.bottleneck,[(512, 128, 1)] * 3 + [(512, 128, 2)]),
resnet_utils.Block('block3', resnet_v1.bottleneck,[(1024, 256, 1)] * 5 + [(1024, 256, 1)]),
resnet_utils.Block('block4', resnet_v1.bottleneck,[(2048, 512, 1)] * 3),
resnet_utils.Block('block5', resnet_v1.bottleneck,[(2048, 512, 1)] * 3)]
else:
from tensorflow.contrib.slim.python.slim.nets.resnet_v1 import resnet_v1_block
self.blocks = [resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=6, stride=1),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1),
resnet_v1_block('block5', base_depth=512, num_units=3, stride=1)]
if self.model_name.__contains__('unique_weights'):
print("unique_weights2")
self.blocks.append(resnet_v1_block('block6', base_depth=512, num_units=3, stride=1))
# remove 3, 17 22, 23 27
self.HO_weight = np.array([3.3510249, 3.4552405, 4.0257854, 4.088436,
3.4370995, 3.85842, 4.637334, 3.5487218, 3.536237,
2.5578923, 3.342811, 3.8897269, 4.70686, 3.3952892,
3.9706533, 4.504736, 1.4873443, 3.700363,
4.1058283, 3.6298118, 5.0808263,
1.520838, 3.3888445, 3.9899964], dtype='float32').reshape(1, 24)
self.H_weight = np.array([4.0984106, 4.102459, 4.0414762, 4.0414762,
3.9768186, 4.23686, 5.3542085, 3.723717, 3.4699364,
2.4587274, 3.7167964, 4.08836, 5.050695, 3.9077065,
4.534647, 3.4699364, 1.8585607, 3.9433942,
3.9433942, 4.3523254, 5.138182,
1.7807873, 4.080392, 4.5761204], dtype='float32').reshape(1, 24)
self.reset_classes()
def __init__(self):
self.visualize = {}
self.intermediate = {}
self.predictions = {}
self.score_summaries = {}
self.event_summaries = {}
self.train_summaries = []
self.losses = {}
self.image = tf.placeholder(tf.float32,
shape=[1, None, None, 3],
name='image') #scene stream
self.H_boxes = tf.placeholder(tf.float32,
shape=[None, 5],
name='H_boxes') # Human stream
self.P_boxes = tf.placeholder(tf.float32,
shape=[None, 10, 5],
name='P_boxes') # PaSta stream
self.gt_verb = tf.placeholder(tf.float32,
shape=[None, 80],
name='gt_class_verb') # target verb
self.H_num = tf.placeholder(tf.int32)
self.verb_weight = np.array(verb80, dtype='float32').reshape(1, -1)
self.num_classes = 80 # HOI
self.num_pasta0 = 12 # pasta0 ankle
self.num_pasta1 = 10 # pasta1 knee
self.num_pasta2 = 5 # pasta2 hip
self.num_pasta3 = 31 # pasta3 hand
self.num_pasta4 = 5 # pasta4 shoulder
self.num_pasta5 = 13 # pasta5 head
self.num_fc = 1024
self.scope = 'resnet_v1_50'
self.stride = [
16,
]
self.lr = tf.placeholder(tf.float32)
if tf.__version__ == '1.1.0':
self.blocks = [
resnet_utils.Block('block1', resnet_v1.bottleneck,
[(256, 64, 1)] * 2 + [(256, 64, 2)]),
resnet_utils.Block('block2', resnet_v1.bottleneck,
[(512, 128, 1)] * 3 + [(512, 128, 2)]),
resnet_utils.Block('block3', resnet_v1.bottleneck,
[(1024, 256, 1)] * 5 + [(1024, 256, 1)]),
resnet_utils.Block('block4', resnet_v1.bottleneck,
[(2048, 512, 1)] * 3),
resnet_utils.Block('block5', resnet_v1.bottleneck,
[(2048, 512, 1)] * 3)
]
else: # we use tf 1.2.0 here, Resnet-50
from tensorflow.contrib.slim.python.slim.nets.resnet_v1 import resnet_v1_block
self.blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2), # a resnet_v1 bottleneck block
resnet_v1_block('block2',
base_depth=128,
num_units=4,
stride=2),
resnet_v1_block('block3',
base_depth=256,
num_units=6,
stride=1), # feature former
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1),
resnet_v1_block('block5',
base_depth=512,
num_units=3,
stride=1)
]
def _build_network(self, sess, is_training=True):
# select initializers
if cfg.TRAIN.TRUNCATED:
initializer = tf.truncated_normal_initializer(mean=0.0,
stddev=0.01)
initializer_bbox = tf.truncated_normal_initializer(mean=0.0,
stddev=0.001)
else:
initializer = tf.random_normal_initializer(mean=0.0, stddev=0.01)
initializer_bbox = tf.random_normal_initializer(mean=0.0,
stddev=0.001)
# choose different blocks for different number of layers
if self._num_layers == 50:
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2),
resnet_v1_block('block2',
base_depth=128,
num_units=4,
stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3',
base_depth=256,
num_units=6,
stride=1),
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1)
]
elif self._num_layers == 101:
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2),
resnet_v1_block('block2',
base_depth=128,
num_units=4,
stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3',
base_depth=256,
num_units=23,
stride=1),
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1)
]
elif self._num_layers == 152:
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3,
stride=2),
resnet_v1_block('block2',
base_depth=128,
num_units=8,
stride=2),
# use stride 1 for the last conv4 layer
resnet_v1_block('block3',
base_depth=256,
num_units=36,
stride=1),
resnet_v1_block('block4',
base_depth=512,
num_units=3,
stride=1)
]
else:
# other numbers are not supported
raise NotImplementedError
assert (0 <= cfg.RESNET.FIXED_BLOCKS <= 3)
# Now the base is always fixed during training
with slim.arg_scope(resnet_arg_scope(is_training=False)):
net_conv = self._build_base()
base_output = net_conv
if cfg.RESNET.FIXED_BLOCKS > 0:
with slim.arg_scope(resnet_arg_scope(is_training=False)):
net_conv, end_points_initial = resnet_v1.resnet_v1(
net_conv,
blocks[0:cfg.RESNET.FIXED_BLOCKS],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
if cfg.RESNET.FIXED_BLOCKS < 3:
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
net_conv, end_points_initial = resnet_v1.resnet_v1(
net_conv,
blocks[cfg.RESNET.FIXED_BLOCKS:-1],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
self._act_summaries.append(net_conv)
self._layers['head'] = net_conv
with tf.variable_scope(self._resnet_scope, self._resnet_scope):
# build the anchors for the image
self._anchor_component()
# region proposal network
rois = self._region_proposal(net_conv, is_training, initializer)
# region of interest pooling
if cfg.POOLING_MODE == 'crop':
pool5 = self._crop_pool_layer(net_conv, rois, "pool5")
else:
raise NotImplementedError
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
fc7, end_points_last = resnet_v1.resnet_v1(
pool5,
blocks[-1:],
global_pool=False,
include_root_block=False,
scope=self._resnet_scope)
print("Layer dimensions")
print(base_output.get_shape())
print(end_points_initial['resnet_v1_152/block2'].get_shape())
print(end_points_initial['resnet_v1_152/block3'].get_shape())
concatenated_features_lower = tf.concat(values=[tf.reduce_mean(base_output, axis=[1, 2]), \
tf.reduce_mean(end_points_initial['resnet_v1_152/block2'], axis=[1, 2]), \
tf.reduce_mean(end_points_initial['resnet_v1_152/block3'], axis=[1, 2])], axis=1)
print("Concatenated lower features dimensions")
feature_size = concatenated_features_lower.get_shape(
).dims[1].value
print(feature_size)
# concatenated_features = tf.reshape(tf.tile(concatenated_features_lower, [1, 256]), [-1, tf.shape(concatenated_features_lower)[1]])
concatenated_features = tf.reshape(
tf.tile(concatenated_features_lower, [1, 256]),
[256, feature_size])
print(concatenated_features.get_shape())
concatenated_features = tf.concat(values=[
concatenated_features,
tf.reduce_mean(end_points_last['resnet_v1_152/block4'],
axis=[1, 2])
],
axis=1)
print(concatenated_features.get_shape())
with tf.variable_scope(self._resnet_scope, self._resnet_scope):
# average pooling done by reduce_mean
fc7 = tf.reduce_mean(fc7, axis=[1, 2])
print(fc7.get_shape())
final_feature_vec = tf.concat(values=[concatenated_features, fc7],
axis=1)
print("Final feature vector dimensions")
print(final_feature_vec.get_shape())
# region classification
cls_prob, bbox_pred = self._region_classification(
fc7, is_training, initializer, initializer_bbox)
self._score_summaries.update(self._predictions)
return rois, cls_prob, bbox_pred
def resnet_base(rgb_img_batch, ir_img_batch, scope_name, is_training=True):
if scope_name == 'resnet_v1_50':
middle_num_units = 6
elif scope_name == 'resnet_v1_101':
middle_num_units = 23
else:
raise NotImplementedError('We only support resnet_v1_50 or resnet_v1_101. ')
org_scope_name = scope_name
blocks = [resnet_v1_block('RGB/resnet_v1_50/block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('RGB/resnet_v1_50/block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('RGB/resnet_v1_50/block3', base_depth=256, num_units=middle_num_units, stride=2),
resnet_v1_block('RGB/resnet_v1_50/block4', base_depth=512, num_units=3, stride=1)]
# when use fpn . stride list is [1, 2, 2]
scope_name = "RGB/"+org_scope_name
with slim.arg_scope(resnet_arg_scope(is_training=False)):
with tf.variable_scope(scope_name, scope_name):
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1
net_rgb = resnet_utils.conv2d_same(
rgb_img_batch, 64, 7, stride=2, scope='conv1')
net_rgb = tf.pad(net_rgb, [[0, 0], [1, 1], [1, 1], [0, 0]])
net_rgb = slim.max_pool2d(
net_rgb, [3, 3], stride=2, padding='VALID', scope='pool1')
not_freezed = [False] * cfgs.RGB_FIXED_BLOCKS + (4-cfgs.RGB_FIXED_BLOCKS)*[True]
# Fixed_Blocks can be 1~3
with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[0]))):
C2_rgb, end_points_C2_rgb = resnet_v1.resnet_v1(net_rgb,
blocks[0:1],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C2 = tf.Print(C2, [tf.shape(C2)], summarize=10, message='C2_shape')
# add_heatmap(C2, name='Layer2/C2_heat')
with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[1]))):
C3_rgb, end_points_C3_rgb = resnet_v1.resnet_v1(C2_rgb,
blocks[1:2],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C3 = tf.Print(C3, [tf.shape(C3)], summarize=10, message='C3_shape')
# add_heatmap(C3, name='Layer3/C3_heat')
with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[2]))):
C4_rgb, end_points_C4_rgb = resnet_v1.resnet_v1(C3_rgb,
blocks[2:3],
global_pool=False,
include_root_block=False,
scope=scope_name)
# add_heatmap(C4, name='Layer4/C4_heat')
# C4 = tf.Print(C4, [tf.shape(C4)], summarize=10, message='C4_shape')
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C5_rgb, end_points_C5_rgb = resnet_v1.resnet_v1(C4_rgb,
blocks[3:4],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C5 = tf.Print(C5, [tf.shape(C5)], summarize=10, message='C5_shape')
# add_heatmap(C5, name='Layer5/C5_heat')
blocks = [resnet_v1_block('IR/resnet_v1_50/block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('IR/resnet_v1_50/block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('IR/resnet_v1_50/block3', base_depth=256, num_units=middle_num_units, stride=2),
resnet_v1_block('IR/resnet_v1_50/block4', base_depth=512, num_units=3, stride=1)]
scope_name = "IR/"+org_scope_name
with slim.arg_scope(resnet_arg_scope(is_training=False)):
with tf.variable_scope(scope_name, scope_name):
# Do the first few layers manually, because 'SAME' padding can behave inconsistently
# for images of different sizes: sometimes 0, sometimes 1
net_ir = resnet_utils.conv2d_same(
ir_img_batch, 64, 7, stride=2, scope='conv1')
net_ir = tf.pad(net_ir, [[0, 0], [1, 1], [1, 1], [0, 0]])
net_ir = slim.max_pool2d(
net_ir, [3, 3], stride=2, padding='VALID', scope='pool1')
not_freezed = [False] * cfgs.IR_FIXED_BLOCKS + (4-cfgs.IR_FIXED_BLOCKS)*[True]
# Fixed_Blocks can be 1~3
with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[0]))):
C2_ir, end_points_C2_ir = resnet_v1.resnet_v1(net_ir,
blocks[0:1],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C2 = tf.Print(C2, [tf.shape(C2)], summarize=10, message='C2_shape')
# add_heatmap(C2, name='Layer2/C2_heat')
with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[1]))):
C3_ir, end_points_C3_ir = resnet_v1.resnet_v1(C2_ir,
blocks[1:2],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C3 = tf.Print(C3, [tf.shape(C3)], summarize=10, message='C3_shape')
# add_heatmap(C3, name='Layer3/C3_heat')
with slim.arg_scope(resnet_arg_scope(is_training=(is_training and not_freezed[2]))):
C4_ir, end_points_C4_ir = resnet_v1.resnet_v1(C3_ir,
blocks[2:3],
global_pool=False,
include_root_block=False,
scope=scope_name)
# add_heatmap(C4, name='Layer4/C4_heat')
# C4 = tf.Print(C4, [tf.shape(C4)], summarize=10, message='C4_shape')
with slim.arg_scope(resnet_arg_scope(is_training=is_training)):
C5_ir, end_points_C5_ir = resnet_v1.resnet_v1(C4_ir,
blocks[3:4],
global_pool=False,
include_root_block=False,
scope=scope_name)
# C5 = tf.Print(C5, [tf.shape(C5)], summarize=10, message='C5_shape')
# add_heatmap(C5, name='Layer5/C5_heat')
multi_end_points_C2 = tf.concat(axis=3, values = [end_points_C2_rgb['{}/block1/unit_2/bottleneck_v1'.format("RGB/resnet_v1_50/RGB/"+org_scope_name)], end_points_C2_ir['{}/block1/unit_2/bottleneck_v1'.format("IR/resnet_v1_50/IR/"+org_scope_name)]])
multi_end_points_C3 = tf.concat(axis=3, values = [end_points_C3_rgb['{}/block2/unit_3/bottleneck_v1'.format("RGB/resnet_v1_50/RGB/"+org_scope_name)], end_points_C3_ir['{}/block2/unit_3/bottleneck_v1'.format("IR/resnet_v1_50/IR/"+org_scope_name)]])
multi_end_points_C4 = tf.concat(axis=3, values = [end_points_C4_rgb['{}/block3/unit_{}/bottleneck_v1'.format("RGB/resnet_v1_50/RGB/"+org_scope_name, middle_num_units - 1)], end_points_C4_ir['{}/block3/unit_{}/bottleneck_v1'.format("IR/resnet_v1_50/IR/"+org_scope_name, middle_num_units - 1)]])
multi_end_points_C5 = tf.concat(axis=3, values = [end_points_C5_rgb['{}/block4/unit_3/bottleneck_v1'.format("RGB/resnet_v1_50/RGB/"+org_scope_name)], end_points_C5_ir['{}/block4/unit_3/bottleneck_v1'.format("IR/resnet_v1_50/IR/"+org_scope_name)]])
feature_dict = {'C2': multi_end_points_C2,
'C3': multi_end_points_C3,
'C4': multi_end_points_C4,
'C5': multi_end_points_C5,
# 'C5': end_points_C5['{}/block4'.format(scope_name)],
}
scope_name = org_scope_name
pyramid_dict = {}
with tf.variable_scope('build_pyramid'):
with slim.arg_scope([slim.conv2d], weights_regularizer=slim.l2_regularizer(cfgs.WEIGHT_DECAY),
activation_fn=None, normalizer_fn=None):
conv_channels = 256
last_fm = None
for i in range(3):
fm = feature_dict['C{}'.format(5-i)]
fm_1x1_conv = slim.conv2d(fm, num_outputs=conv_channels, kernel_size=[1, 1],
stride=1, scope='p{}_1x1_conv'.format(5-i))
if last_fm is not None:
h, w = tf.shape(fm_1x1_conv)[1], tf.shape(fm_1x1_conv)[2]
last_resize = tf.image.resize_bilinear(last_fm,
size=[h, w],
name='p{}_up2x'.format(5-i))
fm_1x1_conv = fm_1x1_conv + last_resize
last_fm = fm_1x1_conv
fm_3x3_conv = slim.conv2d(fm_1x1_conv,
num_outputs=conv_channels, kernel_size=[3, 3], padding="SAME",
stride=1, scope='p{}_3x3_conv'.format(5 - i))
pyramid_dict['P{}'.format(5-i)] = fm_3x3_conv
p6 = slim.conv2d(pyramid_dict['P5'],
num_outputs=conv_channels, kernel_size=[3, 3], padding="SAME",
stride=2, scope='p6_conv')
pyramid_dict['P6'] = p6
p7 = tf.nn.relu(p6)
p7 = slim.conv2d(p7,
num_outputs=conv_channels, kernel_size=[3, 3], padding="SAME",
stride=2, scope='p7_conv')
pyramid_dict['P7'] = p7
# for level in range(7, 1, -1):
# add_heatmap(pyramid_dict['P%d' % level], name='Layer%d/P%d_heat' % (level, level))
return pyramid_dict