All content for object detection

Development User documentation

Panning and zooming

To use Hasty, you will need to manipulate the work area in such a way that you can label whatever you see fit to annotate. For this, we have two …

Deploy Development User documentation

Pascal VOC

The well-known Pascal VOC format is well documented here . With the Pascal VOC page from Oxford being down at the moment, the links point to a …

Development Deploy MP Wiki


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

Deploy MP Wiki

Primitive deployment using web frameworks

General scenario to deploy a ML model into production In general cases, we mostly follow the above diagram for deployment. There are 4 layers to …

Development User documentation

Project Overview

Our project overview page is the first page you will see in Hasty when logging in. Here you can see your datasets, create new projects, and edit …

Development User documentation

Project Summary

You can access a project-specific report by clicking the three dots on the card of the project you want to see the summary of, and then click …

Development MP Wiki


In this type of split, the input data in randomly assigned to the test, train and validation set according to the given sizes. The split is done …

Deploy Development MP Wiki


ReduceLROnPlateau is a scheduling technique that monitors a quantity and decays the learning rate when the quantity stops improving. The improvement …

Development Deploy MP Wiki


General Information RetinaNet was first introduced to discuss Focal Loss and its use in one-stage object detectors. It had been observed that the …

Development Deploy MP Wiki


RMSprop is another optimization technique where there is a different learning rate for each parameter. The learning rate is varied by calculating the …

Development Deploy MP Wiki


All of us have experienced getting different results after successive iterations of an algorithm with the same data. This can occur due to randomness …

Development Deploy User documentation

Semantic Segmentation (png images)

Export archive directory and file structure project_folder |-- label_classes.json |-- dataset1_name |-- image1.png |-- image2.png |-- ... |-- …

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.