Skip to main content

FRODO for free rejection of out-of-distribution samples in deep learning

Project description

FRODO: Free rejection of Out-of-distribution samples

use FRODO simply by

import model
from tf_frodo import FRODO

model_with_frodo = FRODO(model).fit(x_validation) 

results = model_with_frodo.predict(x_test)

assert results["model_outputs"] == model(x_test)
results["FRODO"] # Rejection scores for each sample in x_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

tf_frodo-0.0.1.tar.gz (3.8 kB view details)

Uploaded Source

Built Distribution

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

tf_frodo-0.0.1-py3-none-any.whl (4.7 kB view details)

Uploaded Python 3

File details

Details for the file tf_frodo-0.0.1.tar.gz.

File metadata

  • Download URL: tf_frodo-0.0.1.tar.gz
  • Upload date:
  • Size: 3.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.26.0 requests-toolbelt/0.9.1 urllib3/1.26.7 tqdm/4.63.1 importlib-metadata/4.8.1 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.7.11

File hashes

Hashes for tf_frodo-0.0.1.tar.gz
Algorithm Hash digest
SHA256 7216476161cbedaf17612b1c45f8ed8d6e38e7ff8a454984f8284873b3f903cf
MD5 d5f2b08fd8ee553716d1e9a98789e080
BLAKE2b-256 3ec170f2e3d387275c45aa6a65a4e656d5a9aaff69c9facaea68c382e5088315

See more details on using hashes here.

File details

Details for the file tf_frodo-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: tf_frodo-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 4.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.26.0 requests-toolbelt/0.9.1 urllib3/1.26.7 tqdm/4.63.1 importlib-metadata/4.8.1 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.7.11

File hashes

Hashes for tf_frodo-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 b5b4306a09cde8a13a8294c5074b1baf78bca4b6ecbb5d2d5d0aa23be943ecf3
MD5 5e19165861832fd6a6b0169c699821b9
BLAKE2b-256 b8b964a83d1a525527666168dbee2e3df5d344790fc2b16c1236af3e317aa000

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