CODEWITHSUNDEEP
pythonkeras
winterstar
winterstar

Reputation: 11

what values does the keras' metrics return? a scalar or a tensor ？

I am writing code about the custom loss function and custom metrics function in Keras. Now it is wrong with the code.

I don't know what values should these custom functions return, a scalar or a tensor which size is 'batch_size'? I tried all of them, surprisingly they all work while the results are different.

So I want to know which of them is right. What is the computing mechanism of 'loss' and 'metrics' when it completes a epoch in training?

The shapes of y_true and y_predict are (batch_size,1)

def loss_scalar(y_true,y_pred):

main_loss=K.sum(K.reshape((1+0.2*(K.abs((5-y_true)-5/2)))*K.square(y_true-y_pred),shape=(-1,)))

def loss_tensor(y_true,y_pred):

main_loss=(K.reshape((1+0.2*(K.abs((5-y_true)-5/2)))*K.square(y_true-y_pred),shape=(-1,))

def mae_tensor(y_true,y_pred):

return  (K.mean(K.abs(y_true-y_pred),axis=-1))

def mae_scalar(y_true,y_pred):

return  K.sum(K.mean(K.abs(y_true-y_pred),axis=-1))

Upvotes: 1

Views: 386

Answers (1)

Benjamin Breton
Benjamin Breton

Reputation: 1577

Keras Metrics return: Single tensor value representing the mean of the output array across all datapoints. according to the doc

Upvotes: 0

Related Questions