Skip to main content

Boost pretrained models with test time augmentation selection

Project description

TTABoost - Boost Your pre-trained Model With Test Time Augmentation Selection

Test time augmentation selection for image detection and classification.

Install

pip install ttabooster

Usage example

from ttabooster.TTABoost import TTABooster

model = load_model('pretrained-model.h5')  # Load any keras model
x_test, y_test = ...  # Load your validation set

AUGMENTATIONS_TEST = Compose([
    RandomSizedCrop((28, 28), 32, 32, w2h_ratio=1.0, interpolation=1, always_apply=False, p=1.0), 
    # Add your augmentations...
])

booster = TTABooster(model, batch_size=100, augmentations=AUGMENTATIONS_TEST)
booster.benchmark_results(x_test, y_test)

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

ttabooster-0.14.tar.gz (7.9 kB view details)

Uploaded Source

File details

Details for the file ttabooster-0.14.tar.gz.

File metadata

  • Download URL: ttabooster-0.14.tar.gz
  • Upload date:
  • Size: 7.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/42.0.2 requests-toolbelt/0.9.1 tqdm/4.41.0 CPython/3.6.8

File hashes

Hashes for ttabooster-0.14.tar.gz
Algorithm Hash digest
SHA256 9c9adba3abee1f97ff61aed92572734724e01c27cd73bd3e779d6d467d7992c6
MD5 c151e97b0f72b03790dcef59a9fc9dac
BLAKE2b-256 5847d572938702343445d3726daadb71916d64c66201aa52e067445e1755e5c5

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