stephanecharette/DarkMark
Marking up images for use with Darknet.
This tool helps machine learning practitioners prepare image datasets for training object detection models. You input raw images and an optional existing neural network, and it outputs meticulously annotated images with bounding boxes and labels, along with all the necessary configuration files for the Darknet framework. It's designed for anyone building custom object detection models, particularly those using YOLO.
231 stars.
Use this if you need to accurately label objects in a large collection of images to train a custom object detection neural network.
Not ideal if you are not working with image data, or if you are using a neural network framework other than Darknet/YOLO and its specific configuration requirements.
Stars
231
Forks
28
Language
C++
License
—
Category
Last pushed
Jan 31, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/stephanecharette/DarkMark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
IBM/MAX-Object-Detector
Localize and identify multiple objects in a single image.
LSH9832/edgeyolo
an edge-real-time anchor-free object detector with decent performance
amdegroot/ssd.pytorch
A PyTorch Implementation of Single Shot MultiBox Detector
aditya-vora/FCHD-Fully-Convolutional-Head-Detector
Code for FCHD - A fast and accurate head detector
dog-qiuqiu/FastestDet
:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only...