Model Evaluation: Compare models on accuracy and latency
Now after you train a model, its accuracy and latency are both benchmarked on your test data using Roboflow's Serverless API. That makes it easier to compare it against the other models in your workspace without having to initiate tests yourself, and pick the model that offers the best mix of accuracy and speed for your deployment.
PreviousGPT-6 Astra in Auto Label: Automate data annotation with plain language prompts
NextVision Events: Automate what happens when a new event occurs
Was this helpful?