Skip to main content

NumPy Neural Network

Project description

NPNN

NumPy Neural Network

What's npnn?

npnn is a a torch-like Python module for gradient descent based machine learning implemented with NumPy.

Work with npnn!

construct a image classification neural network with npnn

BTW, this is a course assignment of DATA620004, School of Data Science, Fudan University.

Task

Construct and Train a neural network on Fashion-MNIST to do image classification.

  • Implement gradient backpropagation algorithm by hand,you can use numpy but DO NOT use pytorch or tensorflow to do autograd.

  • Submit source code including at least four parts: model definition, training, parameters searching and testing.

Implementation

  • dataset.py: provide Fashion MNIST dataset
  • model.py: model definition
  • train.py: model training
  • search.py: parameters searching
  • test.py: model testing
  • utils.py: some misc function, such as save_mode

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

npnn-0.0.1.tar.gz (10.6 kB view details)

Uploaded Source

Built Distribution

npnn-0.0.1-py3-none-any.whl (11.4 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: npnn-0.0.1.tar.gz
  • Upload date:
  • Size: 10.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.10.5

File hashes

Hashes for npnn-0.0.1.tar.gz
Algorithm Hash digest
SHA256 9505e726aba655575d3135db960c08ce55d3804088c20b1ac2f3811008bb5c41
MD5 cf340bf067386ab519d218ecc74a7ac2
BLAKE2b-256 c175ca1e69823f1bfd730989a2074b64e898c12297d8c4db0fe14590381dcc39

See more details on using hashes here.

File details

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

File metadata

  • Download URL: npnn-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 11.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.10.5

File hashes

Hashes for npnn-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 8a936c7dc91b6bf6e477039a363c7dac11850319c32db199ea9577f1487c4642
MD5 99d25e163bf197ee0259fe52c7d66bb1
BLAKE2b-256 b110c4e6621ad246878555079413aa2a76ca0c3c8b5f764206dd29f56bd2325f

See more details on using hashes here.

Supported by

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