Skip to main content

picodl.

A tiny deep learning library built from scratch in Python - autograd engine, layers, losses, optimizers, and a training loop, all on top of plain numpy. No PyTorch, no TensorFlow, no hidden framework underneath.

Documentation

Documentation

Installation

Install picodl with pip

  pip install picodl-nn

Demo

A sample model

from picodl.nn import NeuralNet
from picodl.layers import Linear, GELU
from picodl.loss import CrossEntropyLoss
from picodl.optim import AdamW
from picodl.train import train

net = NeuralNet([
    Linear(784, 128),
    GELU(),
    Linear(128, 10),
])

train(net, x_train, y_train,
      num_epochs=10,
      loss=CrossEntropyLoss(),
      optimizer=AdamW(lr=0.001, weight_decay=0.01))

net.save("model.picodl")

Authors

License

MIT

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

picodl_nn-0.1.0.tar.gz (9.1 kB view details)

Uploaded Source

Built Distribution

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

picodl_nn-0.1.0-py3-none-any.whl (10.2 kB view details)

Uploaded Python 3

File details

Details for the file picodl_nn-0.1.0.tar.gz.

File metadata

  • Download URL: picodl_nn-0.1.0.tar.gz
  • Upload date:
  • Size: 9.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.5

File hashes

Hashes for picodl_nn-0.1.0.tar.gz
Algorithm Hash digest
SHA256 10a041048b85901eccdd62724d225d986bc2b49afe74c4658e34479a1ec00a0e
MD5 f80a4a4bf25e9a0eed34b04941bbaf99
BLAKE2b-256 5ff003a28e4e6162ffbee5d7d55346dc1fb4727196bbbf80dea60198e3ad8341

See more details on using hashes here.

File details

Details for the file picodl_nn-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: picodl_nn-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 10.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.5

File hashes

Hashes for picodl_nn-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 336bbafb5130754350330bda50628d577d265b07f7c071d6fe17f50969c4f5de
MD5 3e9de4eb24627849093e978e2ff4dbe6
BLAKE2b-256 3c48b66d6b49e5b219e7f88a731887612f892f58e7f4ab8442a7451b96e687d2

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