Extra Keras Metrics
Additional metrics integrated with the TensorFlow and Keras Neural Network libraries.
How do I install this package?
As usual, just download it using pip:
pip install extra_keras_metrics
How do I use this package?
In addition to importing individual metrics, sets of metrics are also available.
Multi-class metrics
To retrieve an instance of the set of multi-class metrics, use:
from extra_keras_metrics import get_minimal_multiclass_metrics
model = my_keras_model()
model.compile(
optimizer="nadam",
loss="categorical_crossentropy",
metrics=get_minimal_multiclass_metrics()
)
Sparse multi-class metrics
To retrieve an instance of the set of sparse multi-class metrics, use:
from extra_keras_metrics import get_sparse_multiclass_metrics
model = my_keras_model()
model.compile(
optimizer="nadam",
loss="sparse_categorical_crossentropy",
metrics=get_sparse_multiclass_metrics()
)
Note that currently, this only includes categorical accuracy, as it is the only one provided out-of-the-box by TensorFlow. More metrics are planned.
Binary metrics
To retrieve an instance of the set of binary metrics, use:
from extra_keras_metrics import get_standard_binary_metrics
model = my_keras_model()
model.compile(
optimizer="nadam",
loss="binary_crossentropy",
metrics=get_standard_binary_metrics()
)
All the binary metrics
We have implemented a wide range of binary metrics, including some lesser-known ones. To include all available binary metrics, use:
from extra_keras_metrics import get_complete_binary_metrics
model = my_keras_model()
model.compile(
optimizer="nadam",
loss="binary_crossentropy",
metrics=get_complete_binary_metrics()
)
Extras
You might also enjoy these related packages:
- extra_keras_utils - contains commonly used code for Keras projects.
- plot_keras_history - automatically plots Keras training history.
1 maintainer
Metadata
1 maintainer
Release files for extra-keras-metrics 2.0.14
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| extra_keras_metrics-2.0.14.tar.gz | 8.8 kB | Details |
Release files / extra_keras_metrics-2.0.14.tar.gz
| Download URL | extra_keras_metrics-2.0.14.tar.gz |
|---|---|
| Size | 8.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c1e702efe91a611c237db7257d749decd09e9e003bd5d98f20fd138ee10062f3
|
|
BLAKE2b-256 checksum How to use checksums |
18808e9188e2f93ac04a1d9179a1853bfab12554b6e695b83476ffe0dd728c07
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.9 tqdm/4.63.1 importlib-metadata/4.11.3 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.7.9
|
