def test_vgg_deconv():
if K.image_data_format() == 'channels_first':
x1 = K.variable(np.random.random((1, 512, 8, 8)))
y1_shape = (1, 21, 18, 18)
x2 = K.variable(np.random.random((1, 512, 27, 27)))
y2_shape = (1, 21, 38, 38)
x3 = K.variable(np.random.random((1, 256, 53, 53)))
y3_shape = (1, 21, 312, 312)
else:
x1 = K.variable(np.random.random((1, 8, 8, 512)))
y1_shape = (1, 18, 18, 21)
x2 = K.variable(np.random.random((1, 27, 27, 512)))
y2_shape = (1, 38, 38, 21)
x3 = K.variable(np.random.random((1, 53, 53, 256)))
y3_shape = (1, 312, 312, 21)
upscore1 = vgg_deconv(classes=21)(x1, None)
assert K.int_shape(upscore1) == y1_shape
assert not np.any(np.isnan(K.eval(upscore1)))
upscore2 = vgg_deconv(classes=21)(x2, upscore1)
assert K.int_shape(upscore2) == y2_shape
assert not np.any(np.isnan(K.eval(upscore2)))
upscore3 = vgg_deconv(classes=21, kernel_size=(16, 16),
strides=(8, 8))(x3, upscore2)
assert K.int_shape(upscore3) == y3_shape
assert not np.any(np.isnan(K.eval(upscore3)))
def test_vgg_deconv():
if K.image_data_format() == 'channels_first':
x1 = K.variable(np.random.random((1, 512, 8, 8)))
y1_shape = (1, 21, 18, 18)
x2 = K.variable(np.random.random((1, 512, 27, 27)))
y2_shape = (1, 21, 38, 38)
x3 = K.variable(np.random.random((1, 256, 53, 53)))
y3_shape = (1, 21, 312, 312)
else:
x1 = K.variable(np.random.random((1, 8, 8, 512)))
y1_shape = (1, 18, 18, 21)
x2 = K.variable(np.random.random((1, 27, 27, 512)))
y2_shape = (1, 38, 38, 21)
x3 = K.variable(np.random.random((1, 53, 53, 256)))
y3_shape = (1, 312, 312, 21)
upscore1 = vgg_deconv(classes=21)(x1, None)
assert K.int_shape(upscore1) == y1_shape
assert not np.any(np.isnan(K.eval(upscore1)))
upscore2 = vgg_deconv(classes=21)(x2, upscore1)
assert K.int_shape(upscore2) == y2_shape
assert not np.any(np.isnan(K.eval(upscore2)))
upscore3 = vgg_deconv(classes=21, kernel_size=(16, 16),
strides=(8, 8))(x3, upscore2)
assert K.int_shape(upscore3) == y3_shape
assert not np.any(np.isnan(K.eval(upscore3)))
def VGGDecoder(pyramid, scales, classes):
"""(Deprecated) A Functional decoder for the VGG Nets.
:param: pyramid: A list of features in pyramid, scaling from large
receptive field to small receptive field.
The bottom of the pyramid is the input image.
:param: scales: A list of weights for each of the feature map in the
pyramid, sorted in the same order as the pyramid.
:param: classes: Integer, number of classes.
"""
if len(scales) != len(pyramid) - 1:
raise ValueError('`scales` needs to match the length of'
'`pyramid` - 1.')
blocks = []
features = pyramid[:-1]
for i in range(len(features)):
block_name = 'feat{}'.format(i + 1)
if i < len(features) - 1:
block = vgg_deconv(classes=classes,
scale=scales[i],
kernel_size=(4, 4),
strides=(2, 2),
crop_offset='centered',
weight_decay=1e-3,
block_name=block_name)
else:
block = vgg_deconv(classes=classes,
scale=scales[i],
kernel_size=(16, 16),
strides=(8, 8),
crop_offset='centered',
weight_decay=1e-3,
block_name=block_name)
blocks.append(block)
# Crop the decoded feature to match the image
blocks.append(vgg_score(crop_offset='centered'))
return Decoder(pyramid=pyramid, blocks=blocks)
def VGGDecoder(pyramid, scales, classes):
"""(Deprecated) A Functional decoder for the VGG Nets.
:param: pyramid: A list of features in pyramid, scaling from large
receptive field to small receptive field.
The bottom of the pyramid is the input image.
:param: scales: A list of weights for each of the feature map in the
pyramid, sorted in the same order as the pyramid.
:param: classes: Integer, number of classes.
"""
if len(scales) != len(pyramid) - 1:
raise ValueError('`scales` needs to match the length of'
'`pyramid` - 1.')
blocks = []
features = pyramid[:-1]
for i in range(len(features)):
block_name = 'feat{}'.format(i + 1)
if i < len(features) - 1:
block = vgg_deconv(classes=classes, scale=scales[i],
kernel_size=(4, 4), strides=(2, 2),
crop_offset='centered',
weight_decay=1e-3,
block_name=block_name)
else:
block = vgg_deconv(classes=classes, scale=scales[i],
kernel_size=(16, 16), strides=(8, 8),
crop_offset='centered',
weight_decay=1e-3,
block_name=block_name)
blocks.append(block)
# Crop the decoded feature to match the image
blocks.append(vgg_score(crop_offset='centered'))
return Decoder(pyramid=pyramid, blocks=blocks)