Everything you need for vision AI in one place

We have spent the last two years creating hundreds of content pieces helping you to be successful with vision AI in general, and Hasty in particular. Here, you can find anything from user documentation to upcoming events.

All

Development Software Engineer ML Engineer Project Manager

Building the data flywheel to overcome data shift

How companies like Tesla and Amazon make sure that their ML-models in production adapt to ever-changing environments

Tobias Schaffrath Rosario

Development ML Engineer Software Engineer

Building a Xmas GAN

Here's a fun little side project about training a GAN to Christmasify images.

Hasnain Raza

Development All users

From start to pro in Hasty

Over the last few months, Hasty has seen continued, accelerating growth. To keep the momentum going and deliver on our promise of built for and by …

Tristan Rouillard

All stages Project Manager ML Engineer Software Engineer

We need "Agile" in machine learning

It’s time for a non-linear, iterative approach that builds highly performant vision AI applications.

Tobias Schaffrath Rosario

Development ML Engineer Project Manager Domain Expert Annotator Admin

Levels of annotation automation

This post is a high-level exploration of the most common ways of implementing image-based deep learning (often referred to as image-based Artificial …

Tristan Rouillard

Development Deploy Project Manager ML Engineer Software Engineer

Accuracy

The accuracy is the overall percentage of predictions without errors. It's derived from the confusion matrix . Accuracy used for multi-label …

Deploy Development Project Manager ML Engineer Software Engineer

Adadelta

Adadelta was proposed with the aim to solve the diminishing learning rate problem that was seen in the Adagrad. Adagrad uses the knowledge of all the …

Development Deploy Project Manager ML Engineer Software Engineer

Adagrad

Adagrad , short for adaptive gradient, is a gradient based optimizer that automatically tunes its learning rate in the training process. The learning …

Development Deploy Project Manager ML Engineer Software Engineer

Adam

Adam solvers are the hassle free standard for optimizers. Empirically, Adam solvers converge faster and are more robust towards hyper-parameter …

Development Deploy Software Engineer ML Engineer Project Manager

AdaMax

Adam can be understood as updating weights inversely proportional to the scaled L2 norm (squared) of past gradients. AdaMax extends this to the …

Development Deploy Project Manager ML Engineer Software Engineer

Adamw

AdamW is very similar to Adam . It only differs in the way how the weight decay is implemented. The way how it's implemented in Adam came from the …

Development Project Manager ML Engineer Annotator Admin

Advanced options

In advanced options we currently only have one option available to users. The "Automated tools generate..." toggle allows you to decide if our …

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

Hasty.ai 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.