Skip to main content

A collection of functions to help you easily train and run Tensorflow Keras

Project description

Keras Toolkit

A collection of functions to help you easily train and run Tensorflow Keras

Quickstart

Install the library:

pip install keras-toolkit

You can now use it:

import keras_toolkit as kt

# kt reduces the number of lines from ~100 to ~3
strategy = kt.accelerator.auto_select(verbose=True)
decoder = kt.image.build_decoder(with_labels=True, target_size=(300, 300))
dtrain = kt.image.build_dataset(paths, labels, bsize=BATCH_SIZE, decode_fn=decoder)

with strategy.scope():
    model = tf.keras.Sequential([...])
    model.compile(...)

model.fit(...)

API References

Get the complete API reference here.

Acknowledgement

The auto_select_accelerator was inspired by Martin Gorner's Kaggle notebook.

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

keras-toolkit-0.1.0rc4.tar.gz (4.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

keras_toolkit-0.1.0rc4-py3-none-any.whl (4.5 kB view details)

Uploaded Python 3

File details

Details for the file keras-toolkit-0.1.0rc4.tar.gz.

File metadata

  • Download URL: keras-toolkit-0.1.0rc4.tar.gz
  • Upload date:
  • Size: 4.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.10.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.2

File hashes

Hashes for keras-toolkit-0.1.0rc4.tar.gz
Algorithm Hash digest
SHA256 4f666ff2f4c1b61764c50a074ec5221d3caa95b19e7e4bb6e268e38052208a92
MD5 4d04e7440bd68f3dc59ad63871ec65e7
BLAKE2b-256 dad15d97b226fc6bf25e0bf3d64f03defc2587340f8fffb22167c84d5d4a114a

See more details on using hashes here.

File details

Details for the file keras_toolkit-0.1.0rc4-py3-none-any.whl.

File metadata

  • Download URL: keras_toolkit-0.1.0rc4-py3-none-any.whl
  • Upload date:
  • Size: 4.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.10.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.2

File hashes

Hashes for keras_toolkit-0.1.0rc4-py3-none-any.whl
Algorithm Hash digest
SHA256 b2388c2926df59bbe541643f12c684894e7346ad66c16aa5a39c75c874591eb7
MD5 f8e4e084a04f218f90f377a51f832ef4
BLAKE2b-256 02dc1caedeebf4224aa3e56538348b8d862facf98f46d7c4a7b736959c579d65

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page