top of page

Neurocle Offers Multi-model Deep Learning and Easier Data Management with Neuro-T and Neuro-R 3.1

Updated: Nov 17, 2022

Neurocle, a deep learning vision software company, released Neuro-T 3.1 and Neuro-R 3.1 on the 11th.

Neuro-T 3.1 and Neuro-R 3.1, the latest release since version 3.0 released in May 2022, introduce multi-model utilization and improved data and model management. Users can expect higher work efficiency and stability by predicting the performance of multiple models before actual deployment. New ways to manage data and models increase user convenience and project management efficiency during collaboration.

▲Neuro-T 3.1 & Neuro-R 3.1 / Neurocle

Neurocle has a host of new features for v3.1:

Neuro-T now comes with an Inference Center, a space where users predict and evaluate model performance before deploying a model to the field. This function allows users to design projects by visualizing the models and modifying their projects based on inference time predictions. The user can minimize trial and error by freely changing the model until they achieve the desired inference time.

The Rotation model is a model that automatically rotates images in the correct orientation. For a collection of images in different rotations, the rotation angle for each image is predicted and automatically rotated so that the orientation for all images are consistent. This model acts as a preprocessor for other models where the rotation angle of images impacts the results, increasing the final accuracy and reducing computation time.

Tag & Flag is a function to categorize image data and models into colors. This function allows the user to manage data easily and efficiently, especially for collaboration. For example, when different users work on data preprocessing together, tags can classify image files by user or date. Users can also flag models with high accuracy, making selection easier for projects with many models.

Other features include: ▲Korean language support ▲Image file name modification ▲Training time optimization ▲Measurement tool

"Neurocle ultimately aims to create a deep learning vision ecosystem," said Hongsuk Lee, Neurocle CEO. "We are one step closer to that goal with the release of version 3.1. Through continuous updates, we will build an all-in-one platform that provides functions and services from data preprocessing to model generation and evaluation," he added.

Neurocle is a deep learning vision software company developing deep learning vision software that allows anyone to create a deep learning model and classify images regardless of whether they have deep learning or coding knowledge. Neurocle is currently conducting business with ten countries in Asia and Europe, accelerating its global business expansion.


bottom of page