.
Both
and
are commonly used in computer vision projects. Below, we compare and contrast
and
This architecture provides good realtime results on limited compute. It's designed to run in realtime (30 frames per second) even on mobile devices.
How to AugmentHow to LabelHow to Plot PredictionsHow to Filter PredictionsHow to Create a Confusion MatrixThe tiny and fast version of YOLOv4 - good for training and deployment on limited compute resources, and getting a feel for your dataset
How to AugmentHow to LabelHow to Plot PredictionsHow to Filter PredictionsHow to Create a Confusion MatrixJoin 250,000 developers curating high quality datasets and deploying better models with Roboflow.
Get started