Skip to main content

A Python package for computer vision experiments and research.

Project description

Multi-Models for Images in pyTorch (MMIT)

mmit is a python library with pretrained building blocks for Computer Vision models.

License badge PyTorch - Version Python - Version

Why mmit?

mmit is a library that provides building blocks for Computer Vision models. Heavily inspired by SMP, we aim at providing a unified interface for all encoder and decoders, so that any composition is plug and play. It is designed to be flexible in order to support rapid implementation and evaluation of novel research. It is also designed to be fast, modular, and extensible. mmit is built on top of PyTorch.

To Do List

In the future, we plan to add support for:

  • timm encoders
  • some of timm transformers encoders
  • torchvision / torchub models
  • UNet and UNet++ decoders
  • other decoders
  • multiple heads
  • popular loss function
  • popular datasets
  • popular metrics

Awesome Sources

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

mmit-0.0.4.tar.gz (13.3 kB view details)

Uploaded Source

Built Distribution

mmit-0.0.4-py3-none-any.whl (12.0 kB view details)

Uploaded Python 3

File details

Details for the file mmit-0.0.4.tar.gz.

File metadata

  • Download URL: mmit-0.0.4.tar.gz
  • Upload date:
  • Size: 13.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.16

File hashes

Hashes for mmit-0.0.4.tar.gz
Algorithm Hash digest
SHA256 7d53511893de719ebab85a79d414d298e54f6887376602e5d9ae436d7506d5ce
MD5 d62abce3de5a12c2066049ef0078d670
BLAKE2b-256 135cbb2d38b4444e68cc3fd828eb36221b90e96737275c35863519c1997fdc82

See more details on using hashes here.

File details

Details for the file mmit-0.0.4-py3-none-any.whl.

File metadata

  • Download URL: mmit-0.0.4-py3-none-any.whl
  • Upload date:
  • Size: 12.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.16

File hashes

Hashes for mmit-0.0.4-py3-none-any.whl
Algorithm Hash digest
SHA256 6bfbcceea85df4b061de64bb6e3edb0fb730a32e26ef6c4ccc712276f8b71d71
MD5 20009e254efafcd50d330cac2d0e4764
BLAKE2b-256 959e0188e44f088065ea78b41c7e61d04afa41440adbde625f6b30770deab362

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