Project description

The Auton Lab TA1 primitives

This repository contains additional Auton Lab TA1 primitives for the D3M program.

Iterative Labeling - Blackbox based iterative labeling for semi-supervised learning
Video featurizer - Video Feature Extraction for Action Classification With 3D ResNet

To install primitives, run:

pip install -U autonbox

Video featurizer requires a static file, for pre-trained model weights. To download it, run:

mkdir -p /tmp/cmu/pretrained_files
python3 -m d3m index download -o /tmp/cmu/pretrained_files # requires d3m core

The primitive outputs a data frame of size N x M, where N is the number of videos and M is 2024 features of type float.

It supports running on GPUs.

These details have not been verified by PyPI

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

This version

0.3.0

Feb 20, 2023

0.2.5

Jan 23, 2023

0.2.4

Jan 23, 2023

0.2.3

Jan 23, 2023

0.2.2

Jan 23, 2023

0.2.0

Mar 23, 2022

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

Uploaded Feb 20, 2023 Source

Uploaded Feb 20, 2023 Python 3

Hashes for autonbox-0.3.0.tar.gz
Algorithm	Hash digest
SHA256	`fca6bd0f4abe513b2cde1dee150a439516bec25e6b8c8dc1a6da213539bf002c`
MD5	`a2de1a85d94353ba61ae7f9fe6f59dc0`
BLAKE2b-256	`c48196a517fded2a049ae22bdcfc0ba74f2c4dde6fb0a501c6804d27609f42cf`

Hashes for autonbox-0.3.0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`0dce992e4d43cdaa678a0b1f73d2dad4ed740a559645f561685a8c4f6cae72ff`
MD5	`bf6de6ca4b3a3b4b988f6395d3abb409`
BLAKE2b-256	`e38699a53a7b8c40d2c722c63932d89310ac7412ad267ed6e457c4ac4768c37b`