TensorFlow implementation of focal loss.
Project description
TensorFlow implementation of focal loss [1]: a loss function generalizing binary cross-entropy loss that penalizes hard-to-classify examples.
The focal_loss package provides a function binary_focal_loss and a class BinaryFocalLoss that can be used as stand-in replacements for tf.keras.losses functions and classes, respectively.
# Typical tf.keras API usage
import tensorflow as tf
from focal_loss import BinaryFocalLoss
model = tf.keras.Model(...)
model.compile(
optimizer=...,
loss=BinaryFocalLoss(gamma=2)
metrics=...,
)
history = model.fit(...)
Installation
Make sure that a CPU or GPU version of TensorFlow 2.0 or later is installed (see this link for installation instructions).
The focal_loss package can be installed using the pip utility. For the latest version, install directly from the package’s GitHub page:
pip install git+https://github.com/artemmavrin/focal-loss.git
Alternatively, install the a recent release from the Python Package Index (PyPI):
pip install focal-loss
References
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for focal_loss-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d36749b514290c06cc9b373a2a1835da91fa60dc20943676044f4303ffdda359 |
|
MD5 | 7ec31ba04089d5f03f9f3605c39ab7b6 |
|
BLAKE2b-256 | aa52001d60921313c26ffcc75662d776b4b6c3bcd2965066705e9cdd21f69bc8 |