All content for data scientists and ML engineers

Development User documentation

Manual and semi-automated tools

Hasty offers a wide variety of manual and semi-automated tools to get you started with your annotation efforts. Depending on your project, different …

Development User documentation

Manual Review

Manual review is a quality control interface where you can see all annotations made in a project in one place. You can also filter using one of our …

Development Deploy MP Wiki

mAP (mean Average Precision)

Mean average precision (mAP) is the most meaningful metric for object detectors , instance , and semantic segmentors . It incorporates the trade-off …

Development Deploy MP Wiki

Mask R-CNN

Mask R-CNN is the most used architecture for instance segmentation . It is almost built the same way as Faster R-CNN . The major difference is that …

Development User documentation

Merging polygons/masks into one annotation

When you annotate an object with obfuscation like here: Here we have a player behind an other player that was annotated using 5 separate polygons …

Development Deploy MP Wiki

Min delta

Intuition As a neural network accumulates more parameters, it is more exposed to overfitting. Too many epochs can lead to overfitting of the training …

Development User documentation

Model Dashboard

Model dashboard user interface overview Dashboard overview in detail format Dashboard in widget format Dashboard Information: Split name Experiment …

Development Deploy User documentation

Model Exports

Exporting models for deployment to personal or edge devices In Model Playground, you have the option of exporting the best model from an experiment. …

Development Deploy MP Wiki

Momentum (SGD)

Momentum speeds up the SGD optimizer to reach the local minimum quicker. If we move in the same direction in the loss landscape, the optimizer will …

Development User documentation


This tool is the default tool in Hasty, meaning that it is in use when you first enter the annotation interface. You can use this tool to move …

Deploy Development MP Wiki


MultiStepLR is a scheduler that decays the learning rate with a certain multiplicative factor set by the user when a certain milestone is reached. …

Development User documentation

Object Detection

Widgets GPU Consumption Running time Inference time Average Loss VS Number of Iterations mAP VS Number of Iterations Predictions on classes

Previous Next

Get AI confident. Start using Hasty today.

Our platform is completely free to try. Sign up today to start your two-month trial.

Tuple helped us improve our ML workflow by 40%, which is fantastic. It reduced our overall investment by 90% to get high-quality annotations and an initial model.