我试图为Keras中的U-net编写一个自定义损失函数,其目标不仅是计算预测图像和真实图像的均方误差(MSE),而且还计算其梯度的均方误差(MSE)
我不确定这是否正常,但在我的自定义损失函数中y_true
的形状是(None,None,None,None),即使从下面的link,我希望y_true的大小与y_pred相同,在我的情况下,它的大小应该是:(batch_size,128,256,3)
我已经列出了我为自定义损失函数编写的代码,如果有人能提供任何建议,我将不胜感激
import tensorflow.keras.backend as K
# Encouraging the predicted image to match the label not only in image domain, but also in gradient domain
def keras_customized_loss(batch_size, lambda1 = 1.0, lambda2 = 0.05):
def grad_x(image):
out = K.zeros((batch_size,)+image.shape[1:4])
out = K.abs(image[0:batch_size, 1:, :, :] - image[0:batch_size, :-1, :, :])
return out
def grad_y(image):
out = K.zeros((batch_size,)+image.shape[1:4])
out = K.abs(image[0:batch_size, :, 1:, :] - image[0:batch_size, :, :-1, :])
return out
#OBS: Now y_true has size: (None, None, None, None), figure out how to solve it
def compute_loss(y_true, y_pred):
pred_grad_x = grad_x(y_pred)
pred_grad_y = grad_y(y_pred)
true_grad_x = grad_x(y_true)
true_grad_y = grad_y(y_true)
loss1 = K.mean(K.square(y_pred-y_true))
loss2 = K.mean(K.square(pred_grad_x-true_grad_x))
loss3 = K.mean(K.square(pred_grad_y-true_grad_y))
return (lambda1*loss1+lambda2*loss2+lambda2*loss3)
return compute_loss
model.compile(optimizer='adam', loss = keras_customized_loss(BATCH_SIZE), metrics=['MeanAbsoluteError'])
None
表示它接受可变大小。因此,您的自定义损失可以非常灵活
实际大小自然是传递给
fit
的一批数据的大小。如果您的数据具有形状
(samples, 128,256,3)
,则您无需担心但是您的代码中有很多不必要的东西,您可以:
相关问题 更多 >
编程相关推荐