def FCN_VGG19(input_shape, classes,
trainable_encoder=True, weights='imagenet'):
"""Fully Convolutional Networks for semantic segmentation with VGG16.
# Arguments
input_shape: input image shape
classes: number of classes
trainable_encoder: Bool whether the weights of encoder are trainable
weights: pre-trained weights to load (None for training from scratch)
# Returns
A Keras model instance
"""
# input
inputs = Input(shape=input_shape)
# Get the feature pyramid [drop7, pool4, pool3] from the VGG16 encoder
pyramid_layers = 3
encoder = VGG19(inputs, weights='imagenet', trainable=trainable_encoder)
feat_pyramid = encoder.outputs[:pyramid_layers]
# Append image to the end of feature pyramid
feat_pyramid.append(inputs)
# Decode feature pyramid
outputs = VGGUpsampler(feat_pyramid, scales=[1, 1e-2, 1e-4], classes=21)
# Activation TODO{jihong} work only for channels_last
outputs = Activation('softmax')(outputs)
# return model
return Model(inputs=inputs, outputs=outputs)
def test_vgg_upsampler():
if K.image_data_format() == 'channels_last':
inputs = Input(shape=(500, 500, 3))
pool3 = Input(shape=(63, 63, 256))
pool4 = Input(shape=(32, 32, 512))
drop7 = Input(shape=(16, 16, 4096))
score_shape = (None, 500, 500, 21)
else:
inputs = Input(shape=(3, 500, 500))
pool3 = Input(shape=(256, 63, 63))
pool4 = Input(shape=(512, 32, 32))
drop7 = Input(shape=(4096, 16, 16))
score_shape = (None, 21, 500, 500)
pyramid = [drop7, pool4, pool3, inputs]
scales = [1., 1e-2, 1e-4]
score = VGGUpsampler(pyramid, scales, classes=21)
assert K.int_shape(score) == score_shape