View source Download .ipynb

Create Table from YOLO Object Detection

Create a 3LC Table from YOLO-format dataset with normalized bounding box annotations for efficient object detection workflows.

YOLO format is popular for its simplicity and efficiency in modern object detection pipelines. The normalized coordinate system and straightforward text-based annotation format make it easy to work with and integrate into training workflows.

This notebook loads a YOLO-format detection dataset and converts it to a 3LC Table. We process both image files and corresponding text annotation files containing normalized bounding box coordinates and class indices for each detected object.

Project setup

PROJECT_NAME = "3LC Tutorials - YOLO Detection"
DATASET_NAME = "YOLO-Detection-Dataset"
TABLE_NAME = "initial-detection"
DATA_PATH = "../../../data"

Install dependencies

%pip install 3lc

Imports

from pathlib import Path

import tlc

Create Detection Table

dataset_yaml_file = (Path(DATA_PATH) / "yolo" / "simple.yaml").absolute()

assert dataset_yaml_file.exists()

train_table = tlc.Table.from_yolo(
    dataset_yaml_file=str(dataset_yaml_file),
    split="train",
    project_name=PROJECT_NAME,
    dataset_name=DATASET_NAME,
    table_name=TABLE_NAME,
    task="detect",
)