Open eVision Deep Learning Studio
Open eVision Deep Learning Studio
Open eVision Deep Learning Studio
Open eVision Deep Learning Studio
Open eVision Deep Learning Studio

 

Open eVision Deep Learning Studio

Deep Learning training and evaluation application

At a glance
  • Ease the evaluation of Open eVision’s Deep Learning tools
  • Dataset creation and image annotation for classification and segmentation
  • Configure and display the data augmentation transformations
  • Classifier and segmenter training
  • Analysis of classifier and segmenter performance
  • Free of charge


Compare Where to buy


Open eVision Deep Learning Studio
Open eVision Deep Learning Studio

Open eVision Deep Learning Studio is an application that assists the user during the creation of the dataset as well as the training and testing of the Deep Learning tools of Open eVision.

Open eVision Deep Learning Studio is free and does not require any license. It allows you to test the Deep Learning libraries using your own images. No programming is required.

Just click on DOWNLOAD OPEN EVISION DEEP LEARNING STUDIO and install Open eVision. Sample images, manuals and example programs are included.

Data augmentation
Data augmentation

The rich data augmentation capabilities of EasyClassify and EasySegment are available in Deep Learning Studio. Tune the geometric, color and noise data augmentations, then check the results on the training dataset.

Annotation tool for segmentation
Annotation tool for segmentation

Deep Learning Studio integrates an annotation tool for drawing the ground truth segmentation mask required by the supervised mode of EasySegment. Deep Learning Studio can also import the predicted segmentation computed with any EasySegment tool as a ground truth annotation. This makes the process of annotating your datasets simpler and faster.

Deep Learning tools
Deep Learning tools

Deep Learning Studio supports all the features of the classification (EasyClassify) and segmentation (EasySegment) libraries.

You can easily configure the parameters of the tools such as their input resolution, or the device on which to execute the neural network (CPU or one or several GPUs).

The validation process is customized for each library to allow you to get the most out of data

Visualize the training process
Visualize the training process

The training process window shows the evolution of the metrics used to evaluate the accuracy of the model. Operating on CPU or GPU, the training can be interrupted and restarted at any time.

Region of interest and mask edition
Region of interest and mask edition

Global- or per-image-regions and masks can be edited in Deep Learning Studio. These features are used to restrict the training to some parts of the input images.

Training results analysis
Training results analysis

A comprehensive set of tools and graphs is available to analyze and explore the results of the training process. The confusion matrix, score histogram and ROI curve are useful to understand the strengths and weaknesses of the trained model.

Ordering Information
Product code - Description