All content for software engineers

Development MP Wiki

Random

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 …

Development Deploy MP Wiki

Random Crop

This data augmentation option allows you to crop the images into a certain dimension, creating synthetic data. The cropping could yield any patch of …

Development Deploy MP Wiki

Random Sized Crop

This data augmentation feature allows you to crop an image to any size within a certain specified bound. Like all other augmentation, this creates …

Development Deploy MP Wiki

Recall

Recall indicates how many ground truth labels your classifier is able to pick up. It is derived from the confusion matrix . It is the counterpart of …

Deploy Development MP Wiki

ReduceLROnPlateau

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

Resize

This tool further creates diversity in the training data by rotating some of your training images. The fraction of the images rotated depends on the …

Development Deploy MP Wiki

ResNet

ResNet is the most popular architecture for classifiers with over 20,000 citations. The authors were able to build a very deep, powerful network …

Development Deploy MP Wiki

RetinaNet

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

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

Design Development MP Wiki

Rotate

This tool further creates diversity in the training data by rotating some of your training images. The fraction of the images rotated depends on the …

Development Deploy MP Wiki

Seed

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

Deploy User documentation

Semantic Segmentation

Sample inference script for torchscript exported semantic segmentation model import torch import numpy as np from PIL import Image import torchvision …

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.