TensorFlow implementation of focal loss [1]: a loss function generalizing binary and multiclass cross-entropy loss that penalizes hard-to-classify examples.
The focal_loss package provides functions and classes that can be used as off-the-shelf 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), # Used here like a tf.keras loss
metrics=...,
)
history = model.fit(...)The focal_loss package includes the functions
binary_focal_loss
sparse_categorical_focal_loss
and wrapper classes
BinaryFocalLoss (use like tf.keras.losses.BinaryCrossentropy)
SparseCategoricalFocalLoss (use like tf.keras.losses.SparseCategoricalCrossentropy)
Documentation is available at Read the Docs.
Installation
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.gitAlternatively, install a recent release from the Python Package Index (PyPI):
pip install focal-lossNote. To install the project for development (e.g., to make changes to
the source code), clone the project repository from GitHub and run
make dev:
git clone https://github.com/artemmavrin/focal-loss.git
cd focal-loss
# Optional but recommended: create and activate a new environment first
make devThis will additionally install the requirements needed to run tests, check code coverage, and produce documentation.
References
1 maintainer
Metadata
1 maintainer
Release files for focal-loss 0.0.7
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| focal-loss-0.0.7.tar.gz | 14.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| focal_loss-0.0.7-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 33.5 kB
Release files / focal-loss-0.0.7.tar.gz
| Download URL | focal-loss-0.0.7.tar.gz |
|---|---|
| Size | 14.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
52de3311fdd6e6ee8f746638fb949b8fc55e167acdfffc74a33ac852750c893c
|
|
BLAKE2b-256 checksum How to use checksums |
57b06e7497f3526cd4dd27826308d6822c25ce1405f683b17c2f515dbffb4752
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/4.3.0 pkginfo/1.5.0.1 requests/2.23.0 requests-toolbelt/0.9.1 tqdm/4.46.1 CPython/3.8.3
|
Release files / focal_loss-0.0.7-py3-none-any.whl
| Download URL | focal_loss-0.0.7-py3-none-any.whl |
|---|---|
| Size | 19.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2dad215281050019eb0ffdb4903335de6ef614f5576b08d2961bf1f2493eba42
|
|
BLAKE2b-256 checksum How to use checksums |
3aa1e362a8b955a417a6b37ae31088ecc3ad0fc31b50265c0924a969487eacf6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/4.3.0 pkginfo/1.5.0.1 requests/2.23.0 requests-toolbelt/0.9.1 tqdm/4.46.1 CPython/3.8.3
|
