def augmentate(image, for_classify=False):
if not for_classify:
return tf.image.random_flip_left_right(image)
threshold = tf.constant(0.1)
r = tf.random.uniform([], 0.0, 1.0)
image = tf.cond(greater(threshold,
r), lambda: tf.image.flip_left_right(image),
lambda: tf.identity(image))
r = tf.random.uniform([], 0.0, 1.0)
image = tf.cond(
greater(threshold, r),
lambda: tf.contrib.image.rotate(image, (r - 0.05) * 3.14 * 900 / 180),
lambda: tf.identity(image))
def crop_with_resize(image):
image = tf.image.random_crop(image, [128, 128, 3])
return tf.image.resize_images(image, [160, 160],
tf.image.ResizeMethod.NEAREST_NEIGHBOR)
def crop_with_pad(image):
image = tf.image.random_crop(image, [128, 128, 3])
return tf.image.resize_image_with_crop_or_pad(image, 160, 160)
r = tf.random.uniform([], 0.0, 1.0)
image = tf.cond(
tf.logical_and(greater(threshold, r), greater(r, threshold / 2)),
lambda: crop_with_resize(image), lambda: tf.identity(image))
image = tf.cond(greater(threshold / 2, r), lambda: crop_with_pad(image),
lambda: tf.identity(image))
r = tf.random.uniform([], 0.0, 1.0)
image = tf.cond(greater(threshold / 4,
r), lambda: tf.image.random_brightness(image, 0.4),
lambda: tf.identity(image))
r = tf.random.uniform([], 0.0, 1.0)
image = tf.cond(greater(threshold / 4, r),
lambda: tf.image.random_contrast(image, 0.5, 1.8),
lambda: tf.identity(image))
r = tf.random.uniform([], 0.0, 1.0)
image = tf.cond(greater(threshold / 4,
r), lambda: tf.image.random_hue(image, 0.1),
lambda: tf.identity(image))
r = tf.random.uniform([], 0.0, 1.0)
image = tf.cond(greater(threshold / 4, r),
lambda: tf.image.random_saturation(image, 0.8, 1.1),
lambda: tf.identity(image))
return image
def adaptive_wing_loss(labels, output):
alpha = 2.1
omega = 14
epsilon = 1
theta = 0.5
with tf.name_scope('adaptive_wing_loss'):
x = output - labels
theta_over_epsilon_tensor = tf.fill(tf.shape(labels), theta/epsilon)
A = omega*(1/(1+pow(theta_over_epsilon_tensor, alpha-labels)))*(alpha-labels)*pow(theta_over_epsilon_tensor, alpha-labels-1)*(1/epsilon)
C = theta*A-omega*log(1+pow(theta_over_epsilon_tensor, alpha-labels))
absolute_x = abs(x)
losses = tf.where(greater(theta, absolute_x), omega*log(1+pow(absolute_x/epsilon, alpha-labels)), A*absolute_x-C)
loss = reduce_mean(reduce_sum(losses, axis=[1, 2]), axis=0)
return loss
def body(i, extras, n_set, current_val, seg):
def case1(i, extras, n_set, current_val: tf.Tensor, seg):
# current_val += 0
extras -= 1
n_set += 1
seg = tf.sparse.add(
seg,
tf.SparseTensor(indices=[[0, i]],
values=[current_val],
dense_shape=[1, n]))
return extras, n_set, current_val, seg
def case2(i, extras, n_set, current_val, seg):
current_val += 1
n_set -= n_set
n_set += 1
seg = tf.sparse.add(
seg,
tf.SparseTensor(indices=[[0, i]],
values=[current_val],
dense_shape=[1, n]))
return extras, n_set, current_val, seg
def case3(i, extras, n_set, current_val, seg):
# current_val += 0
n_set += 1
seg = tf.sparse.add(
seg,
tf.SparseTensor(indices=[[0, i]],
values=[current_val],
dense_shape=[1, n]))
return extras, n_set, current_val, seg
extras, n_set, current_val, seg = tf.cond(
logical_and(greater(extras, 0), equal(n_set, y)),
lambda: case1(i, extras, n_set, current_val, seg),
lambda: tf.cond(
greater_equal(n_set, y), lambda: case2(
i, extras, n_set, current_val, seg), lambda: case3(
i, extras, n_set, current_val, seg)))
return b(i), extras, n_set, current_val, seg
def decode_and_preprocess_func(file, label=None):
image = tf.image.decode_and_crop_jpeg(file, [29, 9, 160, 160])
#image = tf.image.resize_images(image, [128, 128], tf.image.ResizeMethod.BICUBIC)
if augmentation:
image = augmentate(image, for_classify)
image.set_shape((160, 160, 3))
image = tf.cast(image, tf.float32)
if augmentation and for_classify:
r = tf.random.uniform([], 0.0, 1.0)
image = tf.cond(greater(tf.constant(0.1), r),
lambda: tf.image.per_image_standardization(image),
lambda: image / 127.5 - 1)
else:
image = image / 127.5 - 1
if for_classify:
return image, label
else:
return image, image
def basis2(self, x):
# b_2_k = K.variable(np.zeros(x.shape[0], ))
k_1 = tf.constant(self.breakpoints[self.k - 1], dtype=tf.float32)
# print(k_1.shape)
k = tf.constant(self.breakpoints[self.k], dtype=tf.float32)
def f1():
return tfm.add(
tfm.subtract(tfm.divide(tfm.multiply(x, x), 2),
tfm.multiply(k_1, x)),
tfm.divide(tfm.multiply(k_1, k_1), 2))
def f2():
val1 = tfm.divide(
tfm.multiply(tfm.subtract(k, k_1), tfm.subtract(k, k_1)), 2)
val2 = tfm.multiply(tfm.subtract(k, k_1), tfm.subtract(x, k))
val = tfm.add(val1, val2)
return val
b2ks = [0] * x.shape[0]
for i in range(x.shape[0]):
b2ks[i] = tf.cond(
tfm.logical_and(tfm.greater(x[i, 0], k_1),
tfm.less(x[i, 0], k)), lambda: f1(),
lambda: f2())
# print(b2ks[i].shape)
b_2_k = K.concatenate(b2ks)
# if tfm.greater(x, k_1) and tfm.less(x, k):
# elif tfm.less(k, x):
return tfm.multiply(self.w[self.i][self.k - 1], b_2_k)
def decode_and_preprocess_func(file, label=None):
image = tf.image.decode_and_crop_jpeg(file, [29, 9, 160, 160])
#image = tf.image.resize_images(image, [128, 128], tf.image.ResizeMethod.BICUBIC)
if aug_level:
image = augmentate(image, level=aug_level)
image.set_shape((160, 160, 3))
image = tf.cast(image, tf.float32)
if aug_level == 'enhanced':
r = tf.random.uniform([], 0.0, 1.0)
image = tf.cond(greater(tf.constant(0.1), r),
lambda: tf.image.per_image_standardization(image),
lambda: image / 127.5 - 1)
else:
image = image / 127.5 - 1
if consumer == 'classifier':
return image, label
elif consumer == 'vae':
return image, image
elif consumer == 'translator':
return image, label
'''
def dice_whole_tumor(y_true, y_pred):
mask_true, mask_pred = get_one_hot_from_output(y_true, y_pred)
mask_true = tfmth.greater(mask_true, 0)
mask_pred = tfmth.greater(mask_pred, 0)
return dice_coefficient(mask_true, mask_pred)
def tf_ssim(x, y, is_normalized=False):
"""
k1 = 0.01
k2 = 0.03
L = 1.0 if is_normalized else 255.0
c1 = np.power(k1 * L, 2)
c2 = np.power(k2 * L, 2)
c3 = c2 / 2
"""
k1 = 0.01
k2 = 0.03
L = 1.0 if is_normalized else 255.0
c1 = tf_pow(multiply(k1, L), 2.0)
c2 = tf_pow(multiply(k2, L), 2.0)
c3 = divide(c2, 2.0)
# if type(x) is np.ndarray:
# x = tf.convert_to_tensor(x, dtype=tf.float32)
# if type(y) is np.ndarray:
# y = tf.convert_to_tensor(y, dtype=tf.float32)
"""
ux = x.mean()
uy = y.mean()
"""
ux = tf_mean(x)
uy = tf_mean(y)
"""
std_x = x.std()
std_y = y.std()
"""
std_x = tf_std(x)
std_y = tf_std(y)
"""
xy = (x - ux) * (y - uy)
std_xy = xy.mean()
"""
xy = multiply(subtract(x, ux), subtract(y, uy))
std_xy = tf_mean(xy)
"""
l_xy = (2 * ux * uy + c1) / (np.power(ux, 2) + np.power(uy, 2) + c1)
"""
l_son = add(multiOperation(multiply, 2.0, ux, uy), c1)
l_mom = multiOperation(add, tf_pow(ux, 2.0), tf_pow(uy, 2.0), c1)
l_xy = divide(l_son, l_mom)
"""
c_xy = (2 * std_x * std_y + c2) / (np.power(std_x, 2) + np.power(std_y, 2) + c2)
"""
c_son = add(multiOperation(multiply, 2.0, std_x, std_y), c2)
c_mom = multiOperation(add, tf_pow(std_x, 2.0), tf_pow(std_y, 2.0), c2)
c_xy = divide(c_son, c_mom)
"""
s_xy = (std_xy + c3) / (std_x * std_y + c3)
"""
s_son = add(std_xy, c3)
s_mom = add(multiply(std_x, std_y), c3)
s_xy = divide(s_son, s_mom)
one = tf.constant(1.0)
_ssim = multiOperation(multiply, l_xy, c_xy, s_xy)
_result = tf.cond(greater(_ssim, one), lambda: one, lambda: _ssim)
return _result