All content for software engineers

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 |-- ... |-- …

Development Deploy MP Wiki

Semantic Segmentor

Semantic Segmentors create pixel-perfect masks of a given image and assign each pixel to a class. The most relevant property of semantic segmentation …

Deploy Development MP Wiki

SGD

Deep learning optimizer literature starts with Gradient Descent and the Stochastic Gradient Descent (SGD) is one very widely used version of it. The …

Development Deploy MP Wiki

Shift Scale Rotate

Parameters Probability It is the probability of applying the transformation to the sample images. Higher probability means that the expected number …

Development Deploy MP Wiki

Smallest max size

Parameters Minimum size of smallest side The parameter that specifies the length of the maximum size that is to be used to resize minimum side of the …

Development User documentation

Split Results

What will you see after splits? After creating a split for a particular machine learning task with given sets of data, the user is able to see the …

Deploy Development MP Wiki

StepLR

StepLR decays the initial learning rate with some multiplicative factor. The decaying happens every N epochs or every N eval period (in case …

Development MP Wiki

Stratification

Some classification problems do not have a balanced number of examples for each class label. For example, for a simple classification task, there …

Deploy User documentation

TorchScript Sample Inference Scripts

In the following pages we provide sample scripts which can be used to run TorchScript models in python. Please keep in mind that these models can …

Development Deploy MP Wiki

U-Net

Architecture The architecture in UNET consists of two paths. Contracting path (encoder network) followed by an expansive path (decoder network). …

Development Deploy MP Wiki

U-Net++

UNet++ is a new versatile image segmentation architecture designed to improve image segmentation accuracy. UNet++ consists of U-Nets of varying …

Development Deploy MP Wiki

Vertical Flip

This data augmentation allows the user to vertically flip images with a certain probability. Parameters Probability This produces the probability of …

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.