This video walks you through the process of training a custom YOLO v8 model using your own data.
Code generated in this video is available here: https://github.com/bnsreenu/python_for_microscopists/blob/master/334_training_YOLO_V8_EM_platelets_converted_labels.ipynb
In this exercise, I use a public dataset that shows multiple classes for segmentation. This is the same dataset from tutorial 330 (Detectron2) - https://youtu.be/cEgF0YknpZw
Dataset from: https://leapmanlab.github.io/dense-cell/
Direct link to the dataset: https://www.dropbox.com/s/68yclbraqq1diza/platelet_data_1219.zip
Data courtesy of: Guay, M.D., Emam, Z.A.S., Anderson, A.B. et al. Dense cellular segmentation for EM using 2D–3D neural network ensembles. Sci Rep 11, 2561 (2021).
To prepare this dataset for YOLO, the binary masks were converted to the YOLO format. Please follow this tutorial to learn about this process.
(https://youtu.be/NYeJvxe5nYw)
If you already have annotations in COCO format JSON file, for example by annotating using makesense (https://www.makesense.ai/) then the annotations can be imported to Roboflow for conversion to YOLO format. Otherwise, if you are starting from scratch, just annotate datasets on Roboflow. (https://roboflow.com/). You just need to upload your images along with the JSON file and Roboflow will convert them to any other format, in our case YOLO v8.
For information about YOLO models:
https://docs.ultralytics.com/models/yolov8/#key-features
