DeepSeaAI is a Python package to simplify processing deep sea video in AWS from a command line.
Project description
DeepSea-AI is a Python package to simplify processing deep sea video in AWS from a command line.
It includes reasonable defaults that have been optimized for deep sea video. The goal is to simplify running these algorithms in AWS.
DeepSea-AI currently supports:
- Training YOLOv5 object detection models
- Running YOLOv5 detection and tracking pipelines on video using either:
Authors: Danelle Cline, dcline@mbari.org, Duane Edgington, duane@mbari.org
For details on AWS installation, see docs.mbari.org/deepsea-ai/install
Assuming you have completed the AWS installation, install and update using pip:
$ pip install -U deepsea-ai
Commands
deepsea-ai train --help
- Train a YOLOv5 model and save the model to a bucketdeepsea-ai process --help
- Process one or more videos and save the results to a bucketdeepsea-ai ecsprocess --help
- Process one or more videos using the Elastic Container Service and save the results to a bucketdeepsea-ai split --help
- Split your training data; required before the train command.deepsea-ai -h
- Print help message and exit.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
deepsea-ai-1.0.1.tar.gz
(30.7 kB
view hashes)
Built Distribution
deepsea_ai-1.0.1-py3-none-any.whl
(39.5 kB
view hashes)
Close
Hashes for deepsea_ai-1.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 354cc5d25146f7abef0c473eb18ac73a7343ff49c323d2eb532b2e5dcaea3d4b |
|
MD5 | a2b3dfd35efdf9880b6d9116f470e4ef |
|
BLAKE2b-256 | 3c671e157e373b3e96b120b68ac7995cff8aff41d48918ac2dd68044b4b90ba9 |