/Python/Keras auc without tf.metrics.auc

Keras auc without tf.metrics.auc

import tensorflow as tf
from sklearn.metrics import roc_auc_score

def auroc(y_true, y_pred):
    return tf.py_func(roc_auc_score, (y_true, y_pred), tf.double)

# Build Model...

model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=['accuracy', auroc])

Source: stackoverflow.com

Similar codes

0 vote144 views1 answer
Array with zeros python
Python
2 votes131 views1 answer
Random date python
Python
2 votes151 views2 answers
Likeliness python
Python
0 vote143 views1 answer
AttributeError: 'tuple' object has no attribute 'reshape'
Python
16 votes133 views6 answers
Python print function
Python
3 votes139 views1 answer
Python RuntimeError: tf.placeholder() is not compatible with eager execution.
Python
2 votes135 views2 answers
Get the name of a file using os
Python
0 vote136 views4 answers
Python code auto fix online
Python
0 vote138 views2 answers
How to terminate a program cv2 python
Python
38 votes137 views4 answers
Pandas insert row
Python