def loss_fun(y_true, y_pred):
'''
y_true is teacher's prediction vector
'''
return logloss(y_true, y_pred)
def categorical_crossentropy(y_true, y_pred):
y_true = y_true[:, :nb_classes]
y_pred = y_pred[:, :nb_classes]
return logloss(y_true, y_pred)
def soft_logloss(y_true, y_pred):
logits = y_true[:, 256:]
y_soft = K.softmax(logits / temperature)
y_pred_soft = y_pred[:, 256:]
return logloss(y_soft, y_pred_soft)
def categorical_crossentropy(y_true, y_pred):
y_true = y_true[:, :256]
y_pred = y_pred[:, :256]
return logloss(y_true, y_pred)
def knowledge_distillation_loss(input_distillation):
y_pred, y_true, y_soft, y_pred_soft = input_distillation
return (1 - args.lambda_const) * logloss(y_true, y_pred) + \
args.lambda_const * args.temperature * args.temperature * logloss(y_soft, y_pred_soft)
def custom_loss(y_true, y_pred):
lambda_param = 0
soft_label = logloss(y_true[:, 1:], y_pred[:,])
hard_label = logloss(y_true[:, :1], y_pred[:,])
loss = lambda_param*soft_label + (1-lambda_param)*hard_label
return loss
def loss(y_true, y_pred):
entropy = -K.mean(K.sum(y_pred * K.log(y_pred), 1))
beta = 0.1
return logloss(y_true, y_pred) - beta * entropy
