Uploaded December 2022 | Updated November 2026, 3 days ago
Traditionally, YOLO models were designed exclusively for object detection. However, it has proven to be very influential in creating high-speed image segmentation architectures such as YOLACT. The recently released YOLOv7 natively supports not only object detection, but also pose estimation and image segmentation.
Chapters:
0:00 Introduction
0:57 Roboflow Notebooks
1:47 Installing YOLOv7
2:48 YOLOv7 repository structure
4:28 Inference using model pre-trained on COCO dataset
5:41 Speed vs accuracy trade-off
7:30 YOLOv7 dataset structure
9:32 Download dataset from Roboflow Universe
11:21 Training YOLOv7 segmentation model on custom dataset
11:40 Model evaluation and prediction
13:34 Outro
Resources:
π Roboflow: roboflow.com
π Roboflow Universe: universe.roboflow.com
π "Train YOLOv7 Instance Segmentation on a Custom Dataset" notebook: github.com/roboflow/notebooks/blob/main/notebooks/train-yolov7-instance-segmentation-on-custom-data.ipynb
π "Train YOLOv7 Instance Segmentation on a Custom Dataset" blog post: blog.roboflow.com/train-yolov7-instance-segmentation-on-custom-data
π» YOLOv7 repository: github.com/WongKinYiu/yolov7
πΌοΈ Concrete Cracks dataset: universe.roboflow.com/university-bswxt/crack-bphdr
π Learn more about YOLOv7 and other Computer Vision models with Roboflow Notebooks: github.com/roboflow-ai/notebooks
β½ Football Players Tracking YouTube video: youtu.be/QCG8QMhga9k
Stay up to date with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! β
Traditionally, YOLO models were designed exclusively for object detection. However, it has proven to be very influential in creating high-speed image segmentation architectures such as YOLACT. The recently released YOLOv7 natively supports not only object detection, but also pose estimation and image segmentation.
Chapters:
0:00 Introduction
0:57 Roboflow Notebooks
1:47 Installing YOLOv7
2:48 YOLOv7 repository structure
4:28 Inference using model pre-trained on COCO dataset
5:41 Speed vs accuracy trade-off
7:30 YOLOv7 dataset structure
9:32 Download dataset from Roboflow Universe
11:21 Training YOLOv7 segmentation model on custom dataset
11:40 Model evaluation and prediction
13:34 Outro
Resources:
π Roboflow: roboflow.com
π Roboflow Universe: universe.roboflow.com
π "Train YOLOv7 Instance Segmentation on a Custom Dataset" notebook: github.com/roboflow/notebooks/blob/main/notebooks/train-yolov7-instance-segmentation-on-custom-data.ipynb
π "Train YOLOv7 Instance Segmentation on a Custom Dataset" blog post: blog.roboflow.com/train-yolov7-instance-segmentation-on-custom-data
π» YOLOv7 repository: github.com/WongKinYiu/yolov7
πΌοΈ Concrete Cracks dataset: universe.roboflow.com/university-bswxt/crack-bphdr
π Learn more about YOLOv7 and other Computer Vision models with Roboflow Notebooks: github.com/roboflow-ai/notebooks
β½ Football Players Tracking YouTube video: youtu.be/QCG8QMhga9k
Stay up to date with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! β










