Menu
I am working on a multi-label image classification problem with the evaluation being conducted in terms of F1-score between system predicted and ground truth labels.
Given that, should I use loss="binary_crossentropy" or loss=keras_metrics.f1_score() where keras_metrics.f1_score() is taken from here: https://pypi.org/project/keras-metrics/? I am a bit confused because all of the tutorials I have found on the Internet regarding multi-label classification are based on the binary_crossentropy loss function, but here I have to optimize against F1-score.
Furthermore, should I set metrics=["accuracy"] or maybe metrics=[keras_metrics.f1_score()] or I should left this completely empty?
693
MultinomialNB() is the Naive Bayes algorithm method used for classification. This is important because by converting our multi-label problem to a multi-class problem, we need an algorithm to handle this multi-class problem.
You will get training and validation F1 score after each epoch. By default, f1 score is not part of keras metrics and hence we can't just directly write f1-score in metrics while compiling model and get results. However, Keras provide some other evaluation metrics like accuracy, categorical accuracy etc.
Based on user706838 answer ...
use the f1_score in https://www.kaggle.com/rejpalcz/best-loss-function-for-f1-score-metric
import tensorflow as tf
import keras.backend as K
def f1_loss(y_true, y_pred):
tp = K.sum(K.cast(y_true*y_pred, 'float'), axis=0)
tn = K.sum(K.cast((1-y_true)*(1-y_pred), 'float'), axis=0)
fp = K.sum(K.cast((1-y_true)*y_pred, 'float'), axis=0)
fn = K.sum(K.cast(y_true*(1-y_pred), 'float'), axis=0)
p = tp / (tp + fp + K.epsilon())
r = tp / (tp + fn + K.epsilon())
f1 = 2*p*r / (p+r+K.epsilon())
f1 = tf.where(tf.is_nan(f1), tf.zeros_like(f1), f1)
return 1 - K.mean(f1)
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
