simurgailab/mask-rcnn-implementation-with-custom-dataset

Implementation of Mask R-CNN architecture, one of the object recognition architectures, on a custom dataset.

29
/ 100
Experimental

This project helps machine learning engineers and researchers implement a Mask R-CNN model for object detection and instance segmentation on their unique datasets. It takes a custom dataset with JSON annotations defining objects and their pixel-level masks, and outputs a trained model capable of identifying objects and outlining their exact shapes in new images. This tool is for those who need to detect and segment specific objects not covered by standard, pre-trained models.

No commits in the last 6 months.

Use this if you need to train a Mask R-CNN model from scratch or fine-tune it to precisely identify and segment objects in images from your own specialized dataset.

Not ideal if you are looking for a plug-and-play solution for common object detection tasks or if you don't have a labeled dataset for training.

computer-vision image-analysis object-detection instance-segmentation custom-dataset-training
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

10

Forks

7

Language

Jupyter Notebook

License

Last pushed

Nov 01, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/simurgailab/mask-rcnn-implementation-with-custom-dataset"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.