def Deeplabv3pResNet50(input_shape=(512, 512, 3),
weights=None,
input_tensor=None,
classes=21,
OS=8,
**kwargs):
""" Instantiates the Deeplabv3+ MobileNetV3Large architecture
# Arguments
input_shape: shape of input image. format HxWxC
PASCAL VOC model was trained on (512,512,3) images
weights: one of 'pascal_voc' (pre-trained on pascal voc)
or None (random initialization)
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
classes: number of desired classes. If classes != 21,
last layer is initialized randomly
OS: determines input_shape/feature_extractor_output ratio. One of {8,16}.
# Returns
A Keras model instance.
"""
if not (weights in {'pascal_voc', None}):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `pascal_voc` '
'(pre-trained on PASCAL VOC)')
if input_tensor is None:
img_input = Input(shape=input_shape, name='image_input')
else:
img_input = input_tensor
# normalize input image
img_norm = Lambda(normalize, name='input_normalize')(img_input)
# backbone body for feature extract
x, skip_feature, backbone_len = ResNet50(include_top=False, input_tensor=img_norm, weights='imagenet', OS=OS)
# ASPP block
x = ASPP_block(x, OS)
# Deeplabv3+ decoder for feature projection
x = Decoder_block(x, skip_feature)
# Final prediction conv block
x = DeeplabConv2D(classes, (1, 1), padding='same', name='logits_semantic')(x)
x = Lambda(img_resize, arguments={'size': (input_shape[0],input_shape[1]), 'mode': 'bilinear'}, name='pred_resize')(x)
x = Reshape((input_shape[0]*input_shape[1], classes)) (x)
x = Softmax(name='Predictions/Softmax')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
#if input_tensor is not None:
#inputs = get_source_inputs(input_tensor)
#else:
#inputs = img_input
model = Model(img_input, x, name='deeplabv3p_resnet50')
return model, backbone_len
def Deeplabv3pMobileNetV2(input_shape=(512, 512, 3),
alpha=1.0,
weights=None,
input_tensor=None,
classes=21,
OS=8,
**kwargs):
""" Instantiates the Deeplabv3+ MobileNetV2 architecture
# Arguments
input_shape: shape of input image. format HxWxC
PASCAL VOC model was trained on (512,512,3) images
alpha: controls the width of the MobileNetV2 network. This is known as the
width multiplier in the MobileNetV2 paper.
- If `alpha` < 1.0, proportionally decreases the number
of filters in each layer.
- If `alpha` > 1.0, proportionally increases the number
of filters in each layer.
- If `alpha` = 1, default number of filters from the paper
are used at each layer.
Used only for mobilenetv2 backbone
weights: one of 'pascal_voc' (pre-trained on pascal voc)
or None (random initialization)
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
classes: number of desired classes. If classes != 21,
last layer is initialized randomly
OS: determines input_shape/feature_extractor_output ratio. One of {8,16}.
Used only for xception backbone.
# Returns
A Keras model instance.
"""
if not (weights in {'pascal_voc', None}):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `pascal_voc` '
'(pre-trained on PASCAL VOC)')
if input_tensor is None:
img_input = Input(shape=input_shape, name='image_input')
else:
img_input = input_tensor
# normalize input image
img_norm = Lambda(normalize, name='input_normalize')(img_input)
# backbone body for feature extract
x, skip_feature, backbone_len = MobileNetV2_body(img_norm, OS, alpha)
# ASPP block
x = ASPP_block(x, OS)
# Deeplabv3+ decoder for feature projection
x = Decoder_block(x, skip_feature)
# Final prediction conv block
x = DeeplabConv2D(classes, (1, 1), padding='same',
name='logits_semantic')(x)
x = Lambda(img_resize,
arguments={
'size': (input_shape[0], input_shape[1]),
'mode': 'bilinear'
},
name='pred_resize')(x)
x = Reshape((input_shape[0] * input_shape[1], classes))(x)
x = Softmax(name='Predictions/Softmax')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
#if input_tensor is not None:
#inputs = get_source_inputs(input_tensor)
#else:
#inputs = img_input
model = Model(img_input, x, name='deeplabv3p_mobilenetv2')
# load weights
#if weights == 'pascal_voc':
#weights_path = get_file('deeplabv3_mobilenetv2_tf_dim_ordering_tf_kernels.h5',
#WEIGHTS_PATH_MOBILE,
#cache_subdir='models')
#model.load_weights(weights_path, by_name=True)
return model, backbone_len
def Deeplabv3pXception(input_shape=(512, 512, 3),
weights='pascal_voc',
input_tensor=None,
classes=21,
OS=16,
**kwargs):
""" Instantiates the Deeplabv3+ architecture
Optionally loads weights pre-trained
on PASCAL VOC. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
# Arguments
input_shape: shape of input image. format HxWxC
PASCAL VOC model was trained on (512,512,3) images
weights: one of 'pascal_voc' (pre-trained on pascal voc)
or None (random initialization)
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
classes: number of desired classes. If classes != 21,
last layer is initialized randomly
OS: determines input_shape/feature_extractor_output ratio. One of {8,16}.
Used only for xception backbone.
# Returns
A Keras model instance.
# Raises
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
ValueError: in case of invalid argument for `weights` or `backbone`
"""
if not (weights in {'pascal_voc', None}):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `pascal_voc` '
'(pre-trained on PASCAL VOC)')
if input_tensor is None:
img_input = Input(shape=input_shape, name='image_input')
else:
img_input = input_tensor
# normalize input image
img_norm = Lambda(normalize, name='input_normalize')(img_input)
# backbone body for feature extract
x, skip_feature, backbone_len = Xception_body(img_norm, OS)
# ASPP block
x = ASPP_block(x, OS)
# Deeplabv3+ decoder for feature projection
x = Decoder_block(x, skip_feature)
# Final prediction conv block
x = DeeplabConv2D(classes, (1, 1), padding='same',
name='logits_semantic')(x)
x = Lambda(img_resize,
arguments={
'size': (input_shape[0], input_shape[1]),
'mode': 'bilinear'
},
name='pred_resize')(x)
x = Reshape((input_shape[0] * input_shape[1], classes))(x)
x = Softmax(name='Predictions/Softmax')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
#if input_tensor is not None:
#inputs = get_source_inputs(input_tensor)
#else:
#inputs = img_input
model = Model(img_input, x, name='deeplabv3p_xception')
# load weights
if weights == 'pascal_voc':
weights_path = get_file(
'deeplabv3_xception_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH_X,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
return model, backbone_len