class FCN8sMobileNet(BasicModel):
"""
FCN8s with MobileNet as an encoder Model Architecture
"""
def __init__(self, args):
super().__init__(args)
# init encoder
self.encoder = None
# init network layers
def build(self):
print("\nBuilding the MODEL...")
self.init_input()
self.init_network()
self.init_output()
self.init_train()
self.init_summaries()
print("The Model is built successfully\n")
def init_network(self):
"""
Building the Network here
:return:
"""
# Init MobileNet as an encoder
self.encoder = MobileNet(x_input=self.x_pl,
num_classes=self.params.num_classes,
pretrained_path=self.args.pretrained_path,
train_flag=self.is_training,
width_multipler=1.0,
weight_decay=self.args.weight_decay)
# Build Encoding part
self.encoder.build()
# Build Decoding part
with tf.name_scope('upscore_2s'):
self.upscore2 = conv2d_transpose(
'upscore2',
x=self.encoder.score_fr,
output_shape=self.encoder.feed1.shape.as_list()[0:3] +
[self.params.num_classes],
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.encoder.wd)
self.score_feed1 = conv2d('score_feed1',
x=self.encoder.feed1,
num_filters=self.params.num_classes,
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self.fuse_feed1 = tf.add(self.score_feed1, self.upscore2)
with tf.name_scope('upscore_4s'):
self.upscore4 = conv2d_transpose(
'upscore4',
x=self.fuse_feed1,
output_shape=self.encoder.feed2.shape.as_list()[0:3] +
[self.params.num_classes],
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.encoder.wd)
self.score_feed2 = conv2d('score_feed2',
x=self.encoder.feed2,
num_filters=self.params.num_classes,
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self.fuse_feed2 = tf.add(self.score_feed2, self.upscore4)
with tf.name_scope('upscore_8s'):
self.upscore8 = conv2d_transpose(
'upscore8',
x=self.fuse_feed2,
output_shape=self.x_pl.shape.as_list()[0:3] +
[self.params.num_classes],
kernel_size=(16, 16),
stride=(8, 8),
l2_strength=self.encoder.wd)
self.logits = self.upscore8
class FCN8sMobileNetUpsample(BasicModel):
"""
FCN8s with MobileNet Upsampling 2x2 as an encoder Model Architecture
"""
def __init__(self, args, phase=0):
super().__init__(args, phase=phase)
# init encoder
self.encoder = None
# init network layers
def build(self):
print("\nBuilding the MODEL...")
self.init_input()
self.init_network()
self.init_output()
self.init_train()
self.init_summaries()
print("The Model is built successfully\n")
def init_network(self):
"""
Building the Network here
:return:
"""
# Init MobileNet as an encoder
self.encoder = MobileNet(x_input=self.x_pl,
num_classes=self.params.num_classes,
pretrained_path=self.args.pretrained_path,
train_flag=self.is_training,
width_multipler=1.0,
weight_decay=self.args.weight_decay)
# Build Encoding part
self.encoder.build()
# Build Decoding part
with tf.name_scope('upscore_2s'):
shape = self.encoder.score_fr.shape.as_list()[1:3]
upscore2_upsample = tf.image.resize_images(
self.encoder.score_fr, (2 * shape[0], 2 * shape[1]))
self.upscore2 = conv2d('upscore2',
x=upscore2_upsample,
num_filters=self.params.num_classes,
l2_strength=self.encoder.wd)
self.score_feed1 = conv2d('score_feed1',
x=self.encoder.feed1,
num_filters=self.params.num_classes,
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self.fuse_feed1 = tf.add(self.score_feed1, self.upscore2)
with tf.name_scope('upscore_4s'):
shape = self.fuse_feed1.shape.as_list()[1:3]
upscore4_upsample = tf.image.resize_images(
self.fuse_feed1, (2 * shape[0], 2 * shape[1]))
self.upscore4 = conv2d('upscore4',
x=upscore4_upsample,
num_filters=self.params.num_classes,
l2_strength=self.encoder.wd)
self.score_feed2 = conv2d('score_feed2',
x=self.encoder.feed2,
num_filters=self.params.num_classes,
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self.fuse_feed2 = tf.add(self.score_feed2, self.upscore4)
with tf.name_scope('upscore_8s'):
shape = self.fuse_feed2.shape.as_list()[1:3]
upscore8_upsample = tf.image.resize_images(
self.fuse_feed2, (8 * shape[0], 8 * shape[1]))
self.upscore8 = conv2d('upscore8',
x=upscore8_upsample,
num_filters=self.params.num_classes,
l2_strength=self.encoder.wd)
self.logits = self.upscore8
class DilationV2MobileNet(BasicModel):
"""
FCN8s with MobileNet as an encoder Model Architecture
"""
def __init__(self, args):
super().__init__(args)
# init encoder
self.encoder = None
self.wd = self.args.weight_decay
# init network layers
self.upscore2 = None
self.score_feed1 = None
self.fuse_feed1 = None
self.upscore4 = None
self.score_feed2 = None
self.fuse_feed2 = None
self.upscore8 = None
self.targets_resize = self.args.targets_resize
def build(self):
print("\nBuilding the MODEL...")
self.init_input()
self.init_network()
self.init_output()
self.init_train()
self.init_summaries()
print("The Model is built successfully\n")
def init_input(self):
with tf.name_scope('input'):
self.x_pl = tf.placeholder(tf.float32, [
self.args.batch_size, self.params.img_height,
self.params.img_width, 3
])
self.y_pl = tf.placeholder(tf.int32, [
self.args.batch_size,
self.params.img_height // self.targets_resize,
self.params.img_width // self.targets_resize
])
print('X_batch shape ',
self.x_pl.get_shape().as_list(), ' ',
self.y_pl.get_shape().as_list())
print('Afterwards: X_batch shape ',
self.x_pl.get_shape().as_list(), ' ',
self.y_pl.get_shape().as_list())
self.curr_learning_rate = tf.placeholder(tf.float32)
if self.params.weighted_loss:
self.wghts = np.zeros(
(self.args.batch_size, self.params.img_height,
self.params.img_width),
dtype=np.float32)
self.is_training = tf.placeholder(tf.bool)
def init_network(self):
"""
Building the Network here
:return:
"""
# Init MobileNet as an encoder
self.encoder = MobileNet(x_input=self.x_pl,
num_classes=self.params.num_classes,
pretrained_path=self.args.pretrained_path,
train_flag=self.is_training,
width_multipler=1.0,
weight_decay=self.args.weight_decay)
# Build Encoding part
self.encoder.build()
# Build Decoding part
with tf.name_scope('dilation_2'):
self.conv4_2 = atrous_conv2d('conv_ds_7_dil',
self.encoder.conv4_1,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
activation=tf.nn.relu,
dilation_rate=2,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv4_2)
self.conv5_1 = depthwise_separable_conv2d(
'conv_ds_8_dil',
self.conv4_2,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_1)
self.conv5_2 = depthwise_separable_conv2d(
'conv_ds_9_dil',
self.conv5_1,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_2)
self.conv5_3 = depthwise_separable_conv2d(
'conv_ds_10_dil',
self.conv5_2,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_3)
self.conv5_4 = depthwise_separable_conv2d(
'conv_ds_11_dil',
self.conv5_3,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_4)
self.conv5_5 = depthwise_separable_conv2d(
'conv_ds_12_dil',
self.conv5_4,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_5)
self.conv5_6 = atrous_conv2d('conv_ds_13_dil',
self.conv5_5,
num_filters=1024,
kernel_size=(3, 3),
padding='SAME',
activation=tf.nn.relu,
dilation_rate=4,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_6)
self.conv6_1 = depthwise_separable_conv2d(
'conv_ds_14_dil',
self.conv5_6,
width_multiplier=self.encoder.width_multiplier,
num_filters=1024,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv6_1)
# Pooling is removed.
self.score_fr = conv2d('conv_1c_1x1_dil',
self.conv6_1,
num_filters=self.params.num_classes,
l2_strength=self.wd,
kernel_size=(1, 1))
_debug(self.score_fr)
if self.targets_resize < 8:
self.targets_resize = 8 // self.targets_resize
self.upscore8 = conv2d_transpose(
'upscore8',
x=self.score_fr,
output_shape=self.y_pl.shape.as_list()[0:3] +
[self.params.num_classes],
kernel_size=(self.targets_resize * 2,
self.targets_resize * 2),
stride=(self.targets_resize, self.targets_resize),
l2_strength=self.encoder.wd,
is_training=self.is_training)
_debug(self.upscore8)
self.logits = self.upscore8
else:
self.logits = self.score_fr
class UNetMobileNet(BasicModel):
def __init__(self, args, phase=0):
super().__init__(args, phase=phase)
# init encoder
self.encoder = None
def build(self):
print("\nBuilding the MODEL...")
self.init_input()
self.init_network()
self.init_output()
self.init_train()
self.init_summaries()
print("The Model is built successfully\n")
@staticmethod
def _debug(operation):
print("Layer_name: " + operation.op.name + " -Output_Shape: " +
str(operation.shape.as_list()))
def init_network(self):
"""
Building the Network here
:return:
"""
# Init MobileNet as an encoder
self.encoder = MobileNet(x_input=self.x_pl,
num_classes=self.params.num_classes,
pretrained_path=self.args.pretrained_path,
train_flag=self.is_training,
width_multipler=1.0,
weight_decay=self.args.weight_decay)
# Build Encoding part
self.encoder.build()
# Build Decoding part
with tf.name_scope('upscale_1'):
self.expand11 = conv2d(
'expand1_1',
x=self.encoder.conv5_6,
batchnorm_enabled=True,
is_training=self.is_training,
num_filters=self.encoder.conv5_5.shape.as_list()[3],
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self._debug(self.expand11)
self.upscale1 = conv2d_transpose(
'upscale1',
x=self.expand11,
is_training=self.is_training,
output_shape=self.encoder.conv5_5.shape.as_list(),
batchnorm_enabled=True,
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.encoder.wd)
self._debug(self.upscale1)
self.add1 = tf.add(self.upscale1, self.encoder.conv5_5)
self._debug(self.add1)
self.expand12 = conv2d(
'expand1_2',
x=self.add1,
batchnorm_enabled=True,
is_training=self.is_training,
num_filters=self.encoder.conv5_5.shape.as_list()[3],
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self._debug(self.expand12)
with tf.name_scope('upscale_2'):
self.expand21 = conv2d(
'expand2_1',
x=self.expand12,
batchnorm_enabled=True,
is_training=self.is_training,
num_filters=self.encoder.conv4_1.shape.as_list()[3],
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self._debug(self.expand21)
self.upscale2 = conv2d_transpose(
'upscale2',
x=self.expand21,
is_training=self.is_training,
output_shape=self.encoder.conv4_1.shape.as_list(),
batchnorm_enabled=True,
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.encoder.wd)
self._debug(self.upscale2)
self.add2 = tf.add(self.upscale2, self.encoder.conv4_1)
self._debug(self.add2)
self.expand22 = conv2d(
'expand2_2',
x=self.add2,
batchnorm_enabled=True,
is_training=self.is_training,
num_filters=self.encoder.conv4_1.shape.as_list()[3],
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self._debug(self.expand22)
with tf.name_scope('upscale_3'):
self.expand31 = conv2d(
'expand3_1',
x=self.expand22,
batchnorm_enabled=True,
is_training=self.is_training,
num_filters=self.encoder.conv3_1.shape.as_list()[3],
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self._debug(self.expand31)
self.upscale3 = conv2d_transpose(
'upscale3',
x=self.expand31,
batchnorm_enabled=True,
is_training=self.is_training,
output_shape=self.encoder.conv3_1.shape.as_list(),
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.encoder.wd)
self._debug(self.upscale3)
self.add3 = tf.add(self.upscale3, self.encoder.conv3_1)
self._debug(self.add3)
self.expand32 = conv2d(
'expand3_2',
x=self.add3,
batchnorm_enabled=True,
is_training=self.is_training,
num_filters=self.encoder.conv3_1.shape.as_list()[3],
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self._debug(self.expand32)
with tf.name_scope('upscale_4'):
self.expand41 = conv2d(
'expand4_1',
x=self.expand32,
batchnorm_enabled=True,
is_training=self.is_training,
num_filters=self.encoder.conv2_1.shape.as_list()[3],
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self._debug(self.expand41)
self.upscale4 = conv2d_transpose(
'upscale4',
x=self.expand41,
batchnorm_enabled=True,
is_training=self.is_training,
output_shape=self.encoder.conv2_1.shape.as_list(),
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.encoder.wd)
self._debug(self.upscale4)
self.add4 = tf.add(self.upscale4, self.encoder.conv2_1)
self._debug(self.add4)
self.expand42 = conv2d(
'expand4_2',
x=self.add4,
batchnorm_enabled=True,
is_training=self.is_training,
num_filters=self.encoder.conv2_1.shape.as_list()[3],
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self._debug(self.expand42)
with tf.name_scope('upscale_5'):
self.upscale5 = conv2d_transpose(
'upscale5',
x=self.expand42,
batchnorm_enabled=True,
is_training=self.is_training,
output_shape=self.x_pl.shape.as_list()[0:3] +
[self.encoder.conv2_1.shape.as_list()[3]],
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.encoder.wd)
self._debug(self.upscale5)
self.expand5 = conv2d(
'expand5',
x=self.upscale5,
batchnorm_enabled=True,
is_training=self.is_training,
num_filters=self.encoder.conv1_1.shape.as_list()[3],
kernel_size=(1, 1),
dropout_keep_prob=0.5,
l2_strength=self.encoder.wd)
self._debug(self.expand5)
with tf.name_scope('final_score'):
self.fscore = conv2d('fscore',
x=self.expand5,
num_filters=self.params.num_classes,
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self._debug(self.fscore)
self.logits = self.fscore
class FCN8s2StreamMobileNet(BasicModel):
"""
FCN8s with MobileNet as an encoder Model Architecture
"""
def __init__(self, args):
super().__init__(args)
# init encoder
self.encoder = None
# init network layers
def build(self):
print("\nBuilding the MODEL...")
self.init_input()
self.init_network()
self.init_output()
self.init_train()
self.init_summaries()
print("The Model is built successfully\n")
def init_input(self):
with tf.name_scope('input'):
self.x_pl = tf.placeholder(tf.float32, [
self.args.batch_size, self.params.img_height,
self.params.img_width, 3
])
self.flo_pl = tf.placeholder(tf.float32, [
self.args.batch_size, self.params.img_height,
self.params.img_width, 3
])
self.y_pl = tf.placeholder(tf.int32, [
self.args.batch_size, self.params.img_height,
self.params.img_width
])
if self.params.weighted_loss:
self.wghts = np.zeros(
(self.args.batch_size, self.params.img_height,
self.params.img_width),
dtype=np.float32)
self.is_training = tf.placeholder(tf.bool)
def init_summaries(self):
with tf.name_scope('pixel_wise_accuracy'):
self.accuracy = tf.reduce_mean(
tf.cast(tf.equal(self.y_pl, self.out_argmax), tf.float32))
with tf.name_scope('segmented_output'):
input_summary = tf.cast(self.x_pl, tf.uint8)
flow_summary = tf.cast(self.flo_pl, tf.uint8)
# labels_summary = tf.py_func(decode_labels, [self.y_pl, self.params.num_classes], tf.uint8)
preds_summary = tf.py_func(
decode_labels, [self.out_argmax, self.params.num_classes],
tf.uint8)
self.segmented_summary = tf.concat(
axis=2, values=[input_summary, flow_summary,
preds_summary]) # Concatenate row-wise
# Every step evaluate these summaries
if self.loss is not None:
with tf.name_scope('train-summary'):
tf.summary.scalar('loss', self.loss)
tf.summary.scalar('pixel_wise_accuracy', self.accuracy)
self.merged_summaries = tf.summary.merge_all()
# Save the best iou on validation
self.best_iou_tensor = tf.Variable(0.0,
trainable=False,
name='best_iou')
self.best_iou_input = tf.placeholder('float32',
None,
name='best_iou_input')
self.best_iou_assign_op = self.best_iou_tensor.assign(
self.best_iou_input)
def init_network(self):
"""
Building the Network here
:return:
"""
# Init MobileNet as an encoder
self.app_encoder = MobileNet(x_input=self.x_pl,
num_classes=self.params.num_classes,
prefix='app_',
pretrained_path=self.args.pretrained_path,
mean_path=self.args.data_dir + 'mean.npy',
train_flag=self.is_training,
width_multipler=1.0,
weight_decay=self.args.weight_decay)
self.motion_encoder = MobileNet(
x_input=self.flo_pl,
num_classes=self.params.num_classes,
prefix='mot_',
pretrained_path=self.args.pretrained_path,
mean_path=self.args.data_dir + 'flo_mean.npy',
train_flag=self.is_training,
width_multipler=1.0,
weight_decay=self.args.weight_decay)
# Build Encoding part
self.app_encoder.build()
self.motion_encoder.build()
self.feed2 = tf.multiply(self.app_encoder.conv3_2,
self.motion_encoder.conv3_2)
self.width_multiplier = 1.0
self.conv4_1 = depthwise_separable_conv2d(
'conv_ds_6_1',
self.feed2,
width_multiplier=self.width_multiplier,
num_filters=256,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu6,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.args.weight_decay)
_debug(self.conv4_1)
self.conv4_2 = depthwise_separable_conv2d(
'conv_ds_7_1',
self.conv4_1,
width_multiplier=self.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(2, 2),
activation=tf.nn.relu6,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.args.weight_decay)
_debug(self.conv4_2)
self.conv5_1 = depthwise_separable_conv2d(
'conv_ds_8_1',
self.conv4_2,
width_multiplier=self.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu6,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.args.weight_decay)
_debug(self.conv5_1)
self.conv5_2 = depthwise_separable_conv2d(
'conv_ds_9_1',
self.conv5_1,
width_multiplier=self.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu6,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.args.weight_decay)
_debug(self.conv5_2)
self.conv5_3 = depthwise_separable_conv2d(
'conv_ds_10_1',
self.conv5_2,
width_multiplier=self.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu6,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.args.weight_decay)
_debug(self.conv5_3)
self.conv5_4 = depthwise_separable_conv2d(
'conv_ds_11_1',
self.conv5_3,
width_multiplier=self.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu6,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.args.weight_decay)
_debug(self.conv5_4)
self.conv5_5 = depthwise_separable_conv2d(
'conv_ds_12_1',
self.conv5_4,
width_multiplier=self.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu6,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.args.weight_decay)
_debug(self.conv5_5)
self.conv5_6 = depthwise_separable_conv2d(
'conv_ds_13_1',
self.conv5_5,
width_multiplier=self.width_multiplier,
num_filters=1024,
kernel_size=(3, 3),
padding='SAME',
stride=(2, 2),
activation=tf.nn.relu6,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.args.weight_decay)
_debug(self.conv5_6)
self.conv6_1 = depthwise_separable_conv2d(
'conv_ds_14_1',
self.conv5_6,
width_multiplier=self.width_multiplier,
num_filters=1024,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu6,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.args.weight_decay)
_debug(self.conv6_1)
# Pooling is removed.
self.score_fr = conv2d('conv_1c_1x1_1',
self.conv6_1,
num_filters=self.params.num_classes,
l2_strength=self.args.weight_decay,
kernel_size=(1, 1))
self.feed1 = self.conv4_2
# Build Decoding part
with tf.name_scope('upscore_2s'):
self.upscore2 = conv2d_transpose(
'upscore2',
x=self.score_fr,
output_shape=self.feed1.shape.as_list()[0:3] +
[self.params.num_classes],
batchnorm_enabled=self.args.batchnorm_enabled,
is_training=self.is_training,
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.args.weight_decay,
bias=self.args.bias)
_debug(self.upscore2)
self.score_feed1 = conv2d(
'score_feed1',
x=self.feed1,
batchnorm_enabled=self.args.batchnorm_enabled,
is_training=self.is_training,
num_filters=self.params.num_classes,
kernel_size=(1, 1),
bias=self.args.bias,
l2_strength=self.args.weight_decay)
_debug(self.score_feed1)
self.fuse_feed1 = tf.add(self.score_feed1, self.upscore2)
with tf.name_scope('upscore_4s'):
self.upscore4 = conv2d_transpose(
'upscore4',
x=self.fuse_feed1,
output_shape=self.feed2.shape.as_list()[0:3] +
[self.params.num_classes],
batchnorm_enabled=self.args.batchnorm_enabled,
is_training=self.is_training,
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.args.weight_decay,
bias=self.args.bias)
_debug(self.upscore4)
self.score_feed2 = conv2d(
'score_feed2',
x=self.feed2,
batchnorm_enabled=self.args.batchnorm_enabled,
is_training=self.is_training,
num_filters=self.params.num_classes,
kernel_size=(1, 1),
bias=self.args.bias,
l2_strength=self.args.weight_decay)
_debug(self.score_feed2)
self.fuse_feed2 = tf.add(self.score_feed2, self.upscore4)
with tf.name_scope('upscore_8s'):
self.upscore8 = conv2d_transpose(
'upscore8',
x=self.fuse_feed2,
output_shape=self.x_pl.shape.as_list()[0:3] +
[self.params.num_classes],
is_training=self.is_training,
kernel_size=(16, 16),
stride=(8, 8),
l2_strength=self.args.weight_decay,
bias=self.args.bias)
_debug(self.upscore8)
self.logits = self.upscore8
class DilationMobileNet(BasicModel):
"""
FCN8s with MobileNet as an encoder Model Architecture
"""
def __init__(self, args):
super().__init__(args)
# init encoder
self.encoder = None
self.wd = self.args.weight_decay
# init network layers
self.upscore2 = None
self.score_feed1 = None
self.fuse_feed1 = None
self.upscore4 = None
self.score_feed2 = None
self.fuse_feed2 = None
self.upscore8 = None
def build(self):
print("\nBuilding the MODEL...")
self.init_input()
self.init_network()
self.init_output()
self.init_train()
self.init_summaries()
print("The Model is built successfully\n")
def init_network(self):
"""
Building the Network here
:return:
"""
# Init MobileNet as an encoder
self.encoder = MobileNet(x_input=self.x_pl,
num_classes=self.params.num_classes,
pretrained_path=self.args.pretrained_path,
train_flag=self.is_training,
width_multipler=1.0,
weight_decay=self.args.weight_decay)
# Build Encoding part
self.encoder.build()
# Build Decoding part
with tf.name_scope('dilation_2'):
self.conv4_2 = atrous_conv2d('conv_ds_7_dil',
self.encoder.conv4_1,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
activation=tf.nn.relu,
dilation_rate=2,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv4_2)
self.conv5_1 = depthwise_separable_conv2d(
'conv_ds_8_dil',
self.conv4_2,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_1)
self.conv5_2 = depthwise_separable_conv2d(
'conv_ds_9_dil',
self.conv5_1,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_2)
self.conv5_3 = depthwise_separable_conv2d(
'conv_ds_10_dil',
self.conv5_2,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_3)
self.conv5_4 = depthwise_separable_conv2d(
'conv_ds_11_dil',
self.conv5_3,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_4)
self.conv5_5 = depthwise_separable_conv2d(
'conv_ds_12_dil',
self.conv5_4,
width_multiplier=self.encoder.width_multiplier,
num_filters=512,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_5)
self.conv5_6 = atrous_conv2d('conv_ds_13_dil',
self.conv5_5,
num_filters=1024,
kernel_size=(3, 3),
padding='SAME',
activation=tf.nn.relu,
dilation_rate=4,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv5_6)
self.conv6_1 = depthwise_separable_conv2d(
'conv_ds_14_dil',
self.conv5_6,
width_multiplier=self.encoder.width_multiplier,
num_filters=1024,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
activation=tf.nn.relu,
batchnorm_enabled=True,
is_training=self.is_training,
l2_strength=self.wd)
_debug(self.conv6_1)
# Pooling is removed.
self.score_fr = conv2d('conv_1c_1x1_dil',
self.conv6_1,
num_filters=self.params.num_classes,
l2_strength=self.wd,
batchnorm_enabled=True,
is_training=self.is_training,
kernel_size=(1, 1))
_debug(self.score_fr)
self.upscore8 = conv2d_transpose(
'upscore8',
x=self.score_fr,
output_shape=self.x_pl.shape.as_list()[0:3] +
[self.params.num_classes],
kernel_size=(16, 16),
stride=(8, 8),
l2_strength=self.encoder.wd,
is_training=self.is_training)
_debug(self.upscore8)
self.logits = self.upscore8
class FCN8sMobileNetTFRecords(BasicModel):
"""
FCN8s with MobileNet as an encoder Model Architecture
"""
def __init__(self, args):
super().__init__(args)
# init encoder
self.encoder = None
# init network layers
self.upscore2 = None
self.score_feed1 = None
self.fuse_feed1 = None
self.upscore4 = None
self.score_feed2 = None
self.fuse_feed2 = None
self.upscore8 = None
# init tfrecords needs
self.handle = None
self.training_iterator = None
self.validation_iterator = None
self.next_img = None
self.training_handle = None
self.validation_handle = None
# get the default session
self.sess = tf.get_default_session()
def build(self):
print("\nBuilding the MODEL...")
self.init_input()
self.init_tfrecord_input()
self.init_network()
self.init_output()
self.init_train()
self.init_summaries()
print("The Model is built successfully\n")
def init_tfrecord_input(self):
if self.args.mode == 'train':
print("USING TF RECORDS")
# Use `tf.parse_single_example()` to extract data from a `tf.Example`
# protocol buffer, and perform any additional per-record preprocessing.
def parser(record):
keys_to_features = {
'height': tf.FixedLenFeature([], tf.int64),
'width': tf.FixedLenFeature([], tf.int64),
'image_raw': tf.FixedLenFeature([], tf.string),
'mask_raw': tf.FixedLenFeature([], tf.string)
}
parsed = tf.parse_single_example(record, keys_to_features)
image = tf.cast(tf.decode_raw(parsed['image_raw'], tf.uint8),
tf.float32)
annotation = tf.cast(
tf.decode_raw(parsed['mask_raw'], tf.uint8), tf.int32)
height = tf.cast(parsed['height'], tf.int32)
width = tf.cast(parsed['width'], tf.int32)
image_shape = tf.stack([height, width, 3])
annotation_shape = tf.stack([height, width])
image = tf.reshape(image, image_shape)
annotation = tf.reshape(annotation, annotation_shape)
return image, annotation
# Use `Dataset.map()` to build a pair of a feature dictionary and a label
# tensor for each example.
train_filename = "./data/" + self.args.tfrecord_train_file
train_dataset = tf.contrib.data.TFRecordDataset(['./data/cscapes_train_1.tfrecords', \
'./data/cscapes_train_2.tfrecords',\
'./data/cscapes_train_3.tfrecord', \
'./data/cscapes_train_4.tfrecords' ])#train_filename)
train_dataset = train_dataset.map(parser)
train_dataset = train_dataset.shuffle(
buffer_size=self.args.tfrecord_train_len)
train_dataset = train_dataset.batch(self.args.batch_size)
train_dataset = train_dataset.repeat()
val_filename = "./data/" + self.args.tfrecord_val_file
val_dataset = tf.contrib.data.TFRecordDataset(val_filename)
val_dataset = val_dataset.map(parser)
val_dataset = val_dataset.batch(self.args.batch_size)
self.training_iterator = train_dataset.make_one_shot_iterator()
self.validation_iterator = val_dataset.make_initializable_iterator(
)
self.training_handle = self.sess.run(
self.training_iterator.string_handle())
self.validation_handle = self.sess.run(
self.validation_iterator.string_handle())
self.handle = tf.placeholder(tf.string, shape=[])
iterator = tf.contrib.data.Iterator.from_string_handle(
self.handle, train_dataset.output_types,
train_dataset.output_shapes)
self.next_img = iterator.get_next()
self.x_pl, self.y_pl = self.next_img
self.x_pl.set_shape(
[None, self.args.img_height, self.args.img_width, 3])
self.y_pl.set_shape(
[None, self.args.img_height, self.args.img_width])
def init_network(self):
"""
Building the Network here
:return:
"""
# Init MobileNet as an encoder
self.encoder = MobileNet(x_input=self.x_pl,
num_classes=self.params.num_classes,
pretrained_path=self.args.pretrained_path,
train_flag=self.is_training,
width_multipler=1.0,
weight_decay=self.args.weight_decay)
# Build Encoding part
self.encoder.build()
# Build Decoding part
with tf.name_scope('upscore_2s'):
self.upscore2 = conv2d_transpose(
'upscore2',
x=self.encoder.score_fr,
output_shape=[self.args.batch_size] +
self.encoder.feed1.shape.as_list()[1:3] +
[self.params.num_classes],
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.encoder.wd)
self.score_feed1 = conv2d('score_feed1',
x=self.encoder.feed1,
num_filters=self.params.num_classes,
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self.fuse_feed1 = tf.add(self.score_feed1, self.upscore2)
with tf.name_scope('upscore_4s'):
self.upscore4 = conv2d_transpose(
'upscore4',
x=self.fuse_feed1,
output_shape=[self.args.batch_size] +
self.encoder.feed2.shape.as_list()[1:3] +
[self.params.num_classes],
kernel_size=(4, 4),
stride=(2, 2),
l2_strength=self.encoder.wd)
self.score_feed2 = conv2d('score_feed2',
x=self.encoder.feed2,
num_filters=self.params.num_classes,
kernel_size=(1, 1),
l2_strength=self.encoder.wd)
self.fuse_feed2 = tf.add(self.score_feed2, self.upscore4)
with tf.name_scope('upscore_8s'):
self.upscore8 = conv2d_transpose(
'upscore8',
x=self.fuse_feed2,
output_shape=[self.args.batch_size] +
self.x_pl.shape.as_list()[1:3] + [self.params.num_classes],
kernel_size=(16, 16),
stride=(8, 8),
l2_strength=self.encoder.wd)
self.logits = self.upscore8