AnswerBun.com

How to interpret a regression model performances (Loss, accuracy) under keras

Data Science Asked by asendjasni on November 28, 2020

I built a regression model using Keras. The following parms were used:

model.compile(loss=custom_mse, optimizer=RMSprop(0.0001), metrics=mae)
history = model.fit(x=x_train, y=y_train, validation_data=(x_valid, y_valid), epochs=100, batch_size=16, verbose=2)

And here the funcs for the loss and accuracy:

import tensorflow.keras.backend as K

def custom_mse(y_true, y_pred):
    loss = K.square(y_pred - y_true)  
    return K.sum(loss, axis=1)        

def mae(y_true, y_pred):
    eval = K.abs(y_pred - y_true)
    return K.mean(eval, axis=-1)

I’m quite new with CNN and regression models. I couldn’t interpret the loss and accuracy.

The performances’ history is depicted in the following figures.

enter image description here

From the above plot, is the model overfitting or its doing alright? And what is all those spades mean?

Add your own answers!

Related Questions

Optimization problem: Given Beta Bounds Maximize sharpe

1  Asked on September 27, 2021 by trapadulli

 

DBSCAN Clustering

1  Asked on September 27, 2021 by tushar-pandey

       

Question on bootstrap sampling

1  Asked on September 27, 2021 by horcle_buzz

   

Changing word inflections

1  Asked on September 25, 2021 by alan-hogue

 

Which type of model to use and what’s my target variable

4  Asked on September 25, 2021 by elena-stamatelou

     

Bib number recognition using Keras

2  Asked on September 25, 2021

 

Ask a Question

Get help from others!

© 2022 AnswerBun.com. All rights reserved. Sites we Love: PCI Database, MenuIva, UKBizDB, Menu Kuliner, Sharing RPP, SolveDir