Skip to main content

Delightful and useful neural networks models, including OrdinalRegressionLoss, etc.

Project description

handy-nn

Delightful and useful neural networks models, including OrdinalRegressionLoss, etc.

Install

$ pip install handy-nn

Usage

from handy_nn import OrdinalRegressionLoss

# Initialize the loss function
num_classes = 5
criterion = OrdinalRegressionLoss(num_classes)

# For training
logits = model(inputs)  # Shape: (batch_size, 1)
loss = criterion(logits, targets)
loss.backward()

# To get class probabilities
probas = criterion.predict_probas(logits)  # Shape: (batch_size, num_classes)

License

MIT

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

handy_nn-0.0.1.tar.gz (4.3 kB view details)

Uploaded Source

Built Distribution

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

handy_nn-0.0.1-py3-none-any.whl (4.8 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: handy_nn-0.0.1.tar.gz
  • Upload date:
  • Size: 4.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for handy_nn-0.0.1.tar.gz
Algorithm Hash digest
SHA256 498f986e2aa41b2ea39d350d2383fc470daf48f2599cca702ed338e36c7a173f
MD5 575d62531c09e891e0bd9aeee9b50fe2
BLAKE2b-256 6a344ab80d31c7574fb6f081591525e9154df43f70f2f07dfcabd5d9c8c93a0c

See more details on using hashes here.

File details

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

File metadata

  • Download URL: handy_nn-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 4.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for handy_nn-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 4bbc56fc12ab6bed6ea7b0c36981118c016db12d21aa802d75da7a711bf1ada8
MD5 0ace1f9547c01d7416213f86b5419491
BLAKE2b-256 06e13822bf77566c9fd5fe8e6be2ec0967d031f8742373bca06b123c585a97a1

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