A New Video Tutorial: YOLOv4 in PyTorch
Joseph NelsonPublished May 31, 2020
We heard your feedback!
More video walkthroughs (opens in a new tab). Many users report that video tutorials help round out the edges of their knowledge to get the most from Roboflow. Seeing how others use Roboflow in real-time aids their own comprehension.
Make YOLOv4 more accessible. YOLOv4 is a mere month old, and given the records it has shattered, we're not surprised to see booming interest in the architecture. We've written about data augmentation in YOLOv4, how to train YOLOv4 using the Darknet framework, and a deep dive into the YOLOv4 architecture.
YOLOv5 is Out!
Consider jumping right to our post on How To Train YOLOv5. You'll have a trained YOLOv5 model on your custom data in a matter of minutes.
Train YOLOv5Now, we're introducing a comprehensive walkthrough on using Roboflow to train your own YOLOv4 model using an even more popular framework: PyTorch. We're first sharing the walkthrough in the form of a comprehensive 20-minute YOLOv4 video tutorial (opens in a new tab), and we'll soon have a drafted written article to follow along, too.
It was only a few months ago that we were blown away with the performance of EfficientDet (opens in a new tab) compared to YOLOv3 (opens in a new tab) on some tasks. We're excited to see the state-of-the-art continuing to advance to quickly.
A note on licensing: YOLOv5 is released under AGPL-3.0, which affects commercial use:
- On Roboflow cloud: a commercial license is included for every user, including the free plan.
- Self-hosted: you need an Enterprise license add-on, or you must open-source your application under AGPL-3.0.
- Permissive alternative: RF-DETR (opens in a new tab) is Apache 2.0, free for commercial use anywhere.
Keep the feedback coming! We're listening.
