Vision Mamba - Pytorch

Project description

Vision Mamba

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images

Installation

You can install the package using pip

pip install -e .

Usage

Code Quality 🧹

make style to format the code
make check_code_quality to check code quality (PEP8 basically)
black .
ruff . --fix

Tests 🧪

pytests is used to run our tests.

License

MIT

Project details

Release history Release notifications | RSS feed

This version

0.0.1

Jan 21, 2024

Download files

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

Source Distribution

vision_mamba-0.0.1.tar.gz (3.7 kB view hashes)

Uploaded Jan 21, 2024 Source

Built Distribution

vision_mamba-0.0.1-py3-none-any.whl (3.7 kB view hashes)

Uploaded Jan 21, 2024 Python 3

Hashes for vision_mamba-0.0.1.tar.gz

Hashes for vision_mamba-0.0.1.tar.gz
Algorithm	Hash digest
SHA256	`295024e264f1f356613c913ba1e9ae9111a22e2f781754af80a0a489b5980af2`
MD5	`0a43c4ffbcc708e23f11cbd7907b4e01`
BLAKE2b-256	`595f9a0d56768932e511a7619221adef65cbe29db376200ce03f0be0d506a959`

Hashes for vision_mamba-0.0.1-py3-none-any.whl

Hashes for vision_mamba-0.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`16d3a1f00c6c499c7a1d3e4b63e544e42021add1ea0b09d62a0ff16bf8c1b819`
MD5	`6022bfa1d5bbbef65b8fa2f7cf4a7a33`
BLAKE2b-256	`69c77289a8cad26099271e7fb5e102df0153a863d7f51ca9c0d21432814ad13b`