Roboflow | How to Train YOLOv6 on a Custom Dataset @Roboflow | Uploaded 1 year ago | Updated 6 minutes ago
Meituan Technical Team recently released MT-YOLOv6 (shortened to YOLOv6) showcasing initial evaluation superior to incumbent open source object detection frameworks.

Chapters:
0:00 Introduction
1:01 Setting up python environment
1:53 Inference using pre-trained model
2:42 Getting open source data from Roboflow Universe
4:36 Training object detection model
5:30 YOLOv6 vs YOLOv7
6:48 Evaluation and inference
8:19 Outro

Roboflow: roboflow.com
Roboflow Universe: universe.roboflow.com
"What's New in YOLOv6?" Blog Post: blog.roboflow.com/yolov6
"How to Train YOLOv6 on a Custom Dataset" Blog Post: blog.roboflow.com/how-to-train-yolov6-on-a-custom-dataset
"Training YOLOv6 on Custom Data" Notebook : colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolov6-object-detection-on-custom-data.ipynb
"What are Anchor Boxes in Object Detection?" Blog Post: blog.roboflow.com/what-is-an-anchor-box
"What is Object Detection - ML1M" YouTube Video: youtu.be/FM4-Pvrvo14
YOLOv6 Repository: github.com/meituan/YOLOv6

📓 Learn more about YOLOv6 and other Computer Vision models with Roboflow Notebooks: github.com/roboflow-ai/notebooks

Stay up to date with the projects I'm working on at github.com/roboflow-ai and github.com/SkalskiP! ⭐