from keras import backend as K
from keras.losses import binary_crossentropy
def dice_coef(y_true, y_pred):
y_true_f = K.flatten(y_true)
y_pred_f = K.flatten(y_pred)
intersection = K.sum(y_true_f * y_pred_f)
return (2. * intersection + 1) / (K.sum(y_true_f) + K.sum(y_pred_f) + 1)
def dice_coef_rounded(y_true, y_pred):
y_true_f = K.flatten(K.round(y_true))
y_pred_f = K.flatten(K.round(y_pred))
intersection = K.sum(y_true_f * y_pred_f)
return (2. * intersection + 1) / (K.sum(y_true_f) + K.sum(y_pred_f) + 1)
def dice_coef_loss(y_true, y_pred):
return 1 - (dice_coef(y_true, y_pred))
def dice_logloss(y_true, y_pred):
return binary_crossentropy(y_true, y_pred) * 0.5 + dice_coef_loss(y_true, y_pred) * 0.5
def dice_logloss2(y_true, y_pred):
return binary_crossentropy(y_true, y_pred) * 0.75 + dice_coef_loss(y_true, y_pred) * 0.25
def dice_logloss3(y_true, y_pred):
return binary_crossentropy(y_true, y_pred) * 0.15 + dice_coef_loss(y_true, y_pred) * 0.85
#from https://www.kaggle.com/lyakaap/weighing-boundary-pixels-loss-script-by-keras2
# weight: weighted tensor(same shape with mask image)
def weighted_bce_loss(y_true, y_pred, weight):
# avoiding overflow
epsilon = 1e-7
y_pred = K.clip(y_pred, epsilon, 1. - epsilon)
logit_y_pred = K.log(y_pred / (1. - y_pred))
# https://www.tensorflow.org/api_docs/python/tf/nn/weighted_cross_entropy_with_logits
loss = (1. - y_true) * logit_y_pred + (1. + (weight - 1.) * y_true) * \
(K.log(1. + K.exp(-K.abs(logit_y_pred))) + K.maximum(-logit_y_pred, 0.))
return K.sum(loss) / K.sum(weight)
def weighted_dice_loss(y_true, y_pred, weight):
smooth = 1.
w, m1, m2 = weight * weight, y_true, y_pred
intersection = (m1 * m2)
score = (2. * K.sum(w * intersection) + smooth) / (K.sum(w * m1) + K.sum(w * m2) + smooth)
loss = 1. - K.sum(score)
return loss
def weighted_bce_dice_loss(y_true, y_pred):
y_true = K.cast(y_true, 'float32')
y_pred = K.cast(y_pred, 'float32')
# if we want to get same size of output, kernel size must be odd number
averaged_mask = K.pool2d(
y_true, pool_size=(11, 11), strides=(1, 1), padding='same', pool_mode='avg')
border = K.cast(K.greater(averaged_mask, 0.005), 'float32') * K.cast(K.less(averaged_mask, 0.995), 'float32')
weight = K.ones_like(averaged_mask)
w0 = K.sum(weight)
weight += border * 2
w1 = K.sum(weight)
weight *= (w0 / w1)
loss = weighted_bce_loss(y_true, y_pred, weight) + \
weighted_dice_loss(y_true, y_pred, weight)
return loss
