def build_pspnet(inputs,
label_size,
num_classes,
preset_model='PSPNet',
frontend="ResNet101",
pooling_type="MAX",
weight_decay=1e-5,
upscaling_method="conv",
is_training=True,
pretrained_dir="network_helpers/models"):
"""
Builds the PSPNet model.
Arguments:
inputs: The input tensor
label_size: Size of the final label tensor. We need to know this for proper upscaling
preset_model: Which model you want to use. Select which ResNet model to use for feature extraction
num_classes: Number of classes
pooling_type: Max or Average pooling
Returns:
PSPNet model
"""
logits, end_points, frontend_scope, init_fn = frontend_builder.build_frontend(
inputs,
frontend,
pretrained_dir=pretrained_dir,
is_training=is_training)
feature_map_shape = [int(x / 8.0) for x in label_size]
print(feature_map_shape)
psp = PyramidPoolingModule(end_points['pool3'],
feature_map_shape=feature_map_shape,
pooling_type=pooling_type)
net = slim.conv2d(psp, 512, [3, 3], activation_fn=None)
net = slim.batch_norm(net, fused=True)
net = tf.nn.relu(net)
if upscaling_method.lower() == "conv":
net = ConvUpscaleBlock(net, 256, kernel_size=[3, 3], scale=2)
net = ConvBlock(net, 256)
net = ConvUpscaleBlock(net, 128, kernel_size=[3, 3], scale=2)
net = ConvBlock(net, 128)
net = ConvUpscaleBlock(net, 64, kernel_size=[3, 3], scale=2)
net = ConvBlock(net, 64)
elif upscaling_method.lower() == "bilinear":
net = Upsampling(net, label_size)
net = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
scope='logits')
return net, init_fn
def build_dense_aspp(inputs,
num_classes,
preset_model='DenseASPP',
frontend="ResNet101",
weight_decay=1e-5,
is_training=True,
pretrained_dir="network_helpers/models"):
logits, end_points, frontend_scope, init_fn = frontend_builder.build_frontend(
inputs,
frontend,
pretrained_dir=pretrained_dir,
is_training=is_training)
init_features = end_points['pool3']
### First block, rate = 3
d_3_features = DilatedConvBlock(init_features,
n_filters=256,
kernel_size=[1, 1])
d_3 = DilatedConvBlock(d_3_features,
n_filters=64,
rate=3,
kernel_size=[3, 3])
### Second block, rate = 6
d_4 = tf.concat([init_features, d_3], axis=-1)
d_4 = DilatedConvBlock(d_4, n_filters=256, kernel_size=[1, 1])
d_4 = DilatedConvBlock(d_4, n_filters=64, rate=6, kernel_size=[3, 3])
### Third block, rate = 12
d_5 = tf.concat([init_features, d_3, d_4], axis=-1)
d_5 = DilatedConvBlock(d_5, n_filters=256, kernel_size=[1, 1])
d_5 = DilatedConvBlock(d_5, n_filters=64, rate=12, kernel_size=[3, 3])
### Fourth block, rate = 18
d_6 = tf.concat([init_features, d_3, d_4, d_5], axis=-1)
d_6 = DilatedConvBlock(d_6, n_filters=256, kernel_size=[1, 1])
d_6 = DilatedConvBlock(d_6, n_filters=64, rate=18, kernel_size=[3, 3])
### Fifth block, rate = 24
d_7 = tf.concat([init_features, d_3, d_4, d_5, d_6], axis=-1)
d_7 = DilatedConvBlock(d_7, n_filters=256, kernel_size=[1, 1])
d_7 = DilatedConvBlock(d_7, n_filters=64, rate=24, kernel_size=[3, 3])
full_block = tf.concat([init_features, d_3, d_4, d_5, d_6, d_7], axis=-1)
net = slim.conv2d(full_block,
num_classes, [1, 1],
activation_fn=None,
scope='logits')
net = Upsampling(net, scale=8)
return net, init_fn
def build_refinenet(inputs, num_classes, preset_model='RefineNet', frontend="ResNet101", weight_decay=1e-5, upscaling_method="bilinear", pretrained_dir="models", is_training=True):
"""
Builds the RefineNet model.
Arguments:
inputs: The input tensor
preset_model: Which model you want to use. Select which ResNet model to use for feature extraction
num_classes: Number of classes
Returns:
RefineNet model
"""
logits, end_points, frontend_scope, init_fn = frontend_builder.build_frontend(inputs, frontend, pretrained_dir=pretrained_dir, is_training=is_training)
high = [end_points['pool5'], end_points['pool4'],
end_points['pool3'], end_points['pool2']]
low = [None, None, None, None]
# Get the feature maps to the proper size with bottleneck
high[0]=slim.conv2d(high[0], 512, 1)
high[1]=slim.conv2d(high[1], 256, 1)
high[2]=slim.conv2d(high[2], 256, 1)
high[3]=slim.conv2d(high[3], 256, 1)
# RefineNet
low[0]=RefineBlock(high_inputs=high[0],low_inputs=None) # Only input ResNet 1/32
low[1]=RefineBlock(high[1],low[0]) # High input = ResNet 1/16, Low input = Previous 1/16
low[2]=RefineBlock(high[2],low[1]) # High input = ResNet 1/8, Low input = Previous 1/8
low[3]=RefineBlock(high[3],low[2]) # High input = ResNet 1/4, Low input = Previous 1/4
# g[3]=Upsampling(g[3],scale=4)
net = low[3]
net = ResidualConvUnit(net)
net = ResidualConvUnit(net)
if upscaling_method.lower() == "conv":
net = ConvUpscaleBlock(net, 128, kernel_size=[3, 3], scale=2)
net = ConvBlock(net, 128)
net = ConvUpscaleBlock(net, 64, kernel_size=[3, 3], scale=2)
net = ConvBlock(net, 64)
elif upscaling_method.lower() == "bilinear":
net = Upsampling(net, scale=4)
net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, scope='logits')
return net, init_fn
def build_bisenet(inputs, num_classes, preset_model='BiSeNet', frontend="ResNet101", weight_decay=1e-5, is_training=True, pretrained_dir="network_helpers/models"):
"""
Builds the BiSeNet model.
Arguments:
inputs: The input tensor=
preset_model: Which model you want to use. Select which ResNet model to use for feature extraction
num_classes: Number of classes
Returns:
BiSeNet model
"""
### The spatial path
### The number of feature maps for each convolution is not specified in the paper
### It was chosen here to be equal to the number of feature maps of a classification
### model at each corresponding stage
spatial_net = ConvBlock(inputs, n_filters=64, kernel_size=[3, 3], strides=2)
spatial_net = ConvBlock(spatial_net, n_filters=128, kernel_size=[3, 3], strides=2)
spatial_net = ConvBlock(spatial_net, n_filters=256, kernel_size=[3, 3], strides=2)
### Context path
logits, end_points, frontend_scope, init_fn = frontend_builder.build_frontend(inputs, frontend, pretrained_dir=pretrained_dir, is_training=is_training)
net_4 = AttentionRefinementModule(end_points['pool4'], n_filters=512)
net_5 = AttentionRefinementModule(end_points['pool5'], n_filters=2048)
global_channels = tf.reduce_mean(net_5, [1, 2], keep_dims=True)
net_5_scaled = tf.multiply(global_channels, net_5)
### Combining the paths
net_4 = Upsampling(net_4, scale=2)
net_5_scaled = Upsampling(net_5_scaled, scale=4)
context_net = tf.concat([net_4, net_5_scaled], axis=-1)
net = FeatureFusionModule(input_1=spatial_net, input_2=context_net, n_filters=num_classes)
### Final upscaling and finish
net = Upsampling(net, scale=8)
net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, scope='logits')
return net, init_fn
def build_custom(inputs, num_classes, frontend="ResNet101", weight_decay=1e-5, is_training=True, pretrained_dir="network_helpers/models"): logits, end_points, frontend_scope, init_fn = frontend_builder.build_frontend(inputs, frontend, is_training=is_training) up_1 = conv_transpose_block(end_points["pool2"], strides=4, n_filters=64) up_2 = conv_transpose_block(end_points["pool3"], strides=8, n_filters=64) up_3 = conv_transpose_block(end_points["pool4"], strides=16, n_filters=64) up_4 = conv_transpose_block(end_points["pool5"], strides=32, n_filters=64) features = tf.concat([up_1, up_2, up_3, up_4], axis=-1) features = conv_block(inputs=features, n_filters=256, filter_size=[1, 1]) features = conv_block(inputs=features, n_filters=64, filter_size=[3, 3]) features = conv_block(inputs=features, n_filters=64, filter_size=[3, 3]) features = conv_block(inputs=features, n_filters=64, filter_size=[3, 3]) net = slim.conv2d(features, num_classes, [1, 1], scope='logits') return net
def build_deeplabv3(inputs,
num_classes,
preset_model='DeepLabV3',
frontend="ResNet101",
weight_decay=1e-5,
is_training=True,
pretrained_dir="models"):
"""
Builds the DeepLabV3 model.
Arguments:
inputs: The input tensor=
preset_model: Which model you want to use. Select which ResNet model to use for feature extraction
num_classes: Number of classes
Returns:
DeepLabV3 model
"""
logits, end_points, frontend_scope, init_fn = frontend_builder.build_frontend(
inputs,
frontend,
pretrained_dir=pretrained_dir,
is_training=is_training)
label_size = tf.shape(inputs)[1:3]
net = AtrousSpatialPyramidPoolingModule(end_points['pool4'])
net = Upsampling(net, label_size)
net = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
scope='logits')
return net, init_fn
def build_deeplabv3_plus(inputs, num_classes, preset_model='DeepLabV3+', frontend="ResNet101", weight_decay=1e-5, is_training=True, pretrained_dir="network_helpers/models"):
"""
Builds the DeepLabV3 model.
Arguments:
inputs: The input tensor=
preset_model: Which model you want to use. Select which ResNet model to use for feature extraction
num_classes: Number of classes
Returns:
DeepLabV3 model
"""
logits, end_points, frontend_scope, init_fn = frontend_builder.build_frontend(inputs, frontend, pretrained_dir=pretrained_dir, is_training=is_training)
label_size = tf.shape(inputs)[1:3]
encoder_features = end_points['pool2']
net = AtrousSpatialPyramidPoolingModule(end_points['pool4'])
net = slim.conv2d(net, 256, [1, 1], scope="conv_1x1_output", activation_fn=None)
decoder_features = Upsampling(net, label_size / 4)
encoder_features = slim.conv2d(encoder_features, 48, [1, 1], activation_fn=tf.nn.relu, normalizer_fn=None)
net = tf.concat((encoder_features, decoder_features), axis=3)
net = slim.conv2d(net, 256, [3, 3], activation_fn=tf.nn.relu, normalizer_fn=None)
net = slim.conv2d(net, 256, [3, 3], activation_fn=tf.nn.relu, normalizer_fn=None)
net = Upsampling(net, label_size)
net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, scope='logits')
return net, init_fn
def build_ddsc(inputs,
num_classes,
preset_model='DDSC',
frontend="ResNet101",
weight_decay=1e-5,
is_training=True,
pretrained_dir="network_helpers/models"):
"""
Builds the Dense Decoder Shortcut Connections model.
Arguments:
inputs: The input tensor=
preset_model: Which model you want to use. Select which ResNet model to use for feature extraction
num_classes: Number of classes
Returns:
Dense Decoder Shortcut Connections model
"""
logits, end_points, frontend_scope, init_fn = frontend_builder.build_frontend(
inputs,
frontend,
pretrained_dir=pretrained_dir,
is_training=is_training)
### Adapting features for all stages
decoder_4 = EncoderAdaptionBlock(end_points['pool5'], n_filters=1024)
decoder_3 = EncoderAdaptionBlock(end_points['pool4'], n_filters=512)
decoder_2 = EncoderAdaptionBlock(end_points['pool3'], n_filters=256)
decoder_1 = EncoderAdaptionBlock(end_points['pool2'], n_filters=128)
decoder_4 = SemanticFeatureGenerationBlock(decoder_4,
D_features=1024,
D_prime_features=1024 / 4,
O_features=1024)
### Fusing features from 3 and 4
decoder_4 = ConvBlock(decoder_4, n_filters=512, kernel_size=[3, 3])
decoder_4 = Upsampling(decoder_4, scale=2)
decoder_3 = ConvBlock(decoder_3, n_filters=512, kernel_size=[3, 3])
decoder_3 = tf.add_n([decoder_4, decoder_3])
decoder_3 = SemanticFeatureGenerationBlock(decoder_3,
D_features=512,
D_prime_features=512 / 4,
O_features=512)
### Fusing features from 2, 3, 4
decoder_4 = ConvBlock(decoder_4, n_filters=256, kernel_size=[3, 3])
decoder_4 = Upsampling(decoder_4, scale=4)
decoder_3 = ConvBlock(decoder_3, n_filters=256, kernel_size=[3, 3])
decoder_3 = Upsampling(decoder_3, scale=2)
decoder_2 = ConvBlock(decoder_2, n_filters=256, kernel_size=[3, 3])
decoder_2 = tf.add_n([decoder_4, decoder_3, decoder_2])
decoder_2 = SemanticFeatureGenerationBlock(decoder_2,
D_features=256,
D_prime_features=256 / 4,
O_features=256)
### Fusing features from 1, 2, 3, 4
decoder_4 = ConvBlock(decoder_4, n_filters=128, kernel_size=[3, 3])
decoder_4 = Upsampling(decoder_4, scale=8)
decoder_3 = ConvBlock(decoder_3, n_filters=128, kernel_size=[3, 3])
decoder_3 = Upsampling(decoder_3, scale=4)
decoder_2 = ConvBlock(decoder_2, n_filters=128, kernel_size=[3, 3])
decoder_2 = Upsampling(decoder_2, scale=2)
decoder_1 = ConvBlock(decoder_1, n_filters=128, kernel_size=[3, 3])
decoder_1 = tf.add_n([decoder_4, decoder_3, decoder_2, decoder_1])
decoder_1 = SemanticFeatureGenerationBlock(decoder_1,
D_features=128,
D_prime_features=128 / 4,
O_features=num_classes)
### Final upscaling and finish
net = Upsampling(decoder_1, scale=4)
net = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
scope='logits')
return net, init_fn
def build_gcn(inputs,
num_classes,
preset_model='GCN',
frontend="ResNet101",
weight_decay=1e-5,
is_training=True,
upscaling_method="bilinear",
pretrained_dir="network_helpers/models"):
"""
Builds the GCN model.
Arguments:
inputs: The input tensor
preset_model: Which model you want to use. Select which ResNet model to use for feature extraction
num_classes: Number of classes
Returns:
GCN model
"""
logits, end_points, frontend_scope, init_fn = frontend_builder.build_frontend(
inputs,
frontend,
pretrained_dir=pretrained_dir,
is_training=is_training)
res = [
end_points['pool5'], end_points['pool4'], end_points['pool3'],
end_points['pool2']
]
down_5 = GlobalConvBlock(res[0], n_filters=21, size=3)
down_5 = BoundaryRefinementBlock(down_5, n_filters=21, kernel_size=[3, 3])
down_5 = ConvUpscaleBlock(down_5,
n_filters=21,
kernel_size=[3, 3],
scale=2)
down_4 = GlobalConvBlock(res[1], n_filters=21, size=3)
down_4 = BoundaryRefinementBlock(down_4, n_filters=21, kernel_size=[3, 3])
down_4 = tf.add(down_4, down_5)
down_4 = BoundaryRefinementBlock(down_4, n_filters=21, kernel_size=[3, 3])
down_4 = ConvUpscaleBlock(down_4,
n_filters=21,
kernel_size=[3, 3],
scale=2)
down_3 = GlobalConvBlock(res[2], n_filters=21, size=3)
down_3 = BoundaryRefinementBlock(down_3, n_filters=21, kernel_size=[3, 3])
down_3 = tf.add(down_3, down_4)
down_3 = BoundaryRefinementBlock(down_3, n_filters=21, kernel_size=[3, 3])
down_3 = ConvUpscaleBlock(down_3,
n_filters=21,
kernel_size=[3, 3],
scale=2)
down_2 = GlobalConvBlock(res[3], n_filters=21, size=3)
down_2 = BoundaryRefinementBlock(down_2, n_filters=21, kernel_size=[3, 3])
down_2 = tf.add(down_2, down_3)
down_2 = BoundaryRefinementBlock(down_2, n_filters=21, kernel_size=[3, 3])
down_2 = ConvUpscaleBlock(down_2,
n_filters=21,
kernel_size=[3, 3],
scale=2)
net = BoundaryRefinementBlock(down_2, n_filters=21, kernel_size=[3, 3])
net = ConvUpscaleBlock(net, n_filters=21, kernel_size=[3, 3], scale=2)
net = BoundaryRefinementBlock(net, n_filters=21, kernel_size=[3, 3])
net = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
scope='logits')
return net, init_fn