Uploaded November 2022 | Updated November 2026, 4 days ago
Roboflow 100 (RF100) is a crowdsourced object detection benchmark. It consists of 100 datasets, 224,714 images, 804 label classes divided into 7 domains. RF100 should be used in tandem with COCO to measure models performance.
This video is a step-by-step tutorial showing how to use RF100 and benchmark models in Google Colab and Docker. We use YOLOv5 and YOLOv7 as examples.
Chapters:
0:00 WTF COCO
2:02 Roboflow 100
3:13 Plan of Attack
4:02 Google Colab YOLOv7 benchmark example
9:22 Docker YOLOv5 benchmark example
11:33 YOLOv5 vs YOLOv7 comparison
12:29 Outro
Website: rf100.org
Blog post: blog.roboflow.com/roboflow-100
Github: github.com/roboflow-ai/roboflow-100-benchmark
Paper: arxiv.org/abs/2211.13523
Papers with Code: paperswithcode.com/dataset/rf100
Google Colab Tutorial: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-use-rf100.ipynb
Roboflow Notebooks: github.com/roboflow-ai/notebooks
Explore the datasets: universe.roboflow.com/roboflow-100
Stay up to date with the projects I'm working on at github.com/roboflow-ai and github.com/SkalskiP! ⭐
Roboflow 100 (RF100) is a crowdsourced object detection benchmark. It consists of 100 datasets, 224,714 images, 804 label classes divided into 7 domains. RF100 should be used in tandem with COCO to measure models performance.
This video is a step-by-step tutorial showing how to use RF100 and benchmark models in Google Colab and Docker. We use YOLOv5 and YOLOv7 as examples.
Chapters:
0:00 WTF COCO
2:02 Roboflow 100
3:13 Plan of Attack
4:02 Google Colab YOLOv7 benchmark example
9:22 Docker YOLOv5 benchmark example
11:33 YOLOv5 vs YOLOv7 comparison
12:29 Outro
Website: rf100.org
Blog post: blog.roboflow.com/roboflow-100
Github: github.com/roboflow-ai/roboflow-100-benchmark
Paper: arxiv.org/abs/2211.13523
Papers with Code: paperswithcode.com/dataset/rf100
Google Colab Tutorial: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-use-rf100.ipynb
Roboflow Notebooks: github.com/roboflow-ai/notebooks
Explore the datasets: universe.roboflow.com/roboflow-100
Stay up to date with the projects I'm working on at github.com/roboflow-ai and github.com/SkalskiP! ⭐





![Deploy YOLOv8 via Hosted Inference API
[Video excerpt from How to Train YOLOv8: https://youtu.be/wuZtUMEiKWY]
Using Roboflows pip package, you can upload weights from your YOLOv8 model to Roboflow. When you upload your weights, you will be able to use your model through our API.
Join us in this video to learn how to upload your model weights and prepare a production-ready API for your model in only a few lines of code.
Resources
Whats New in YOLOv8: https://blog.roboflow.com/whats-new-in-yolov8/
How to train a YOLOv8 object detection model: https://blog.roboflow.com/how-to-train-yolov8-on-a-custom-dataset/
YOLOv8 Models and APIs: https://universe.roboflow.com/search?q=model:yolov8
Roboflow Notebooks, with tutorials on training models using YOLOv8: https://github.com/roboflow/notebooks Deploy YOLOv8 via Hosted Inference API](https://i.ytimg.com/vi/kyHb2RTHjNI/mqdefault.jpg)




