pedropro/taco

How pedropro/taco works

TACO provides a labeled litter-image dataset and a Mask R-CNN detector workflow: users obtain images from annotation URLs, prepare train/validation/test splits, configure class mappings, then train or evaluate detection and segmentation models. The graph also shows the dataset adapter, model utilities, and visualization layer. The README documents dataset metadata, unofficial annotations, unlabeled-image URL lists, and class-map options; source excerpts support the downloader, splitting, dataset, and detector relationships. Some detector internals and notebook behavior were not sampled, so those links are omitted.

Main entry points: detector.py Train and inference CLI · download.py Image downloader · split_dataset.py Dataset splitter · dataset.py TACO dataset adapter

Components 16

Dataset assets

COCO annotations data/annotations.json
Unofficial annotations data/annotations_unofficial.json
Image URL list data/all_image_urls.csv
Image files data

Data preparation

Image downloader download.py
Dataset splitter detector/split_dataset.py
Train val test splits data

Detection workflow

TACO dataset adapter detector/dataset.py
Class maps detector/taco_config
Train and inference CLI detector/detector.py
Detector configuration detector/config.py

Model internals

Mask R-CNN model detector/model.py
Detection utilities detector/utils.py
Detection visualization detector/visualize.py

Other components

Dataset user
Image host

Connections 15

Dataset user → Image downloader: runs download README.md
Image downloader → COCO annotations: reads annotations download.py
Image downloader → Image host: fetches images download.py
Image downloader → Image files: saves images download.py
Dataset user → Dataset splitter: generates splits README.md
Dataset splitter → COCO annotations: reads source detector/split_dataset.py
Dataset splitter → Train val test splits: writes splits detector/split_dataset.py
Dataset user → Train and inference CLI: trains or evaluates README.md
Train and inference CLI → TACO dataset adapter: loads dataset detector/detector.py
Train and inference CLI → Detector configuration: configures model detector/detector.py
Train and inference CLI → Mask R-CNN model: trains or detects detector/detector.py
Train and inference CLI → Detection visualization: uses visualizers detector/detector.py
TACO dataset adapter → Detection utilities: converts masks detector/dataset.py
Mask R-CNN model → Detection utilities: uses utilities detector/model.py
Train and inference CLI → Class maps: selects class map README.md

Drawn by GitDiagram on November 10, 2026 from the repository's file tree, README and source files. Read as Markdown ·