keras-metrics

Metrics for Keras. DEPRECATED since Keras 2.3.0

Showing:

Popularity

Downloads/wk

0

GitHub Stars

165

Maintenance

Last Commit

2yrs ago

Contributors

10

Package

Dependencies

1

License

Categories

Readme

Keras Metrics

Deprecation Warning

Since Keras version 2.3.0, it provides all metrics available in this package. It's preferrable to use metrics from the original Keras package.

This package will be maintained for older version of Keras (<2.3.0).

Build Status

This package provides metrics for evaluation of Keras classification models. The metrics are safe to use for batch-based model evaluation.

Installation

To install the package from the PyPi repository you can execute the following command:

pip install keras-metrics

Usage

The usage of the package is simple:

import keras
import keras_metrics as km

model = models.Sequential()
model.add(keras.layers.Dense(1, activation="sigmoid", input_dim=2))
model.add(keras.layers.Dense(1, activation="softmax"))

model.compile(optimizer="sgd",
              loss="binary_crossentropy",
              metrics=[km.binary_precision(), km.binary_recall()])

Similar configuration for multi-label binary crossentropy:

import keras
import keras_metrics as km

model = models.Sequential()
model.add(keras.layers.Dense(1, activation="sigmoid", input_dim=2))
model.add(keras.layers.Dense(2, activation="softmax"))

# Calculate precision for the second label.
precision = km.binary_precision(label=1)

# Calculate recall for the first label.
recall = km.binary_recall(label=0)

model.compile(optimizer="sgd",
              loss="binary_crossentropy",
              metrics=[precision, recall])

Keras metrics package also supports metrics for categorical crossentropy and sparse categorical crossentropy:

import keras_metrics as km

c_precision = km.categorical_precision()
sc_precision = km.sparse_categorical_precision()

# ...

Tensorflow Keras

Tensorflow library provides the keras package as parts of its API, in order to use keras_metrics with Tensorflow Keras, you are advised to perform model training with initialized global variables:

import numpy as np
import keras_metrics as km
import tensorflow as tf
import tensorflow.keras as keras

model = keras.Sequential()
model.add(keras.layers.Dense(1, activation="softmax"))
model.compile(optimizer="sgd",
              loss="binary_crossentropy",
              metrics=[km.binary_true_positive()])

x = np.array([[0], [1], [0], [1]])
y = np.array([1, 0, 1, 0])

# Wrap model.fit into the session with global
# variables initialization.
with tf.Session() as s:
    s.run(tf.global_variables_initializer())
    model.fit(x=x, y=y)

Rate & Review

Great Documentation0
Easy to Use0
Performant0
Highly Customizable0
Bleeding Edge0
Responsive Maintainers0
Poor Documentation0
Hard to Use0
Slow0
Buggy0
Abandoned0
Unwelcoming Community0
100