Coaxpress Frame Grabbers
Camera Link Frame Grabbers
Non-Standard AnalogFrame Grabbers
Standard PAL/NTSC/1080Pvideo capture cards
Image AnalysisSoftware Tools
Evaluation andprototyping applications
Image acquisition software
GigE Vision, USB3 Vision, CoaXPress
IMX Pregius, MIPI CSI‑2
Machine Vision Development Kit
HD-SDI/HDMIvideo encoders
Deep Learning training and evaluation application
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.
The rich data augmentation capabilities of EasyClassify, EasySegment and EasyLocate are available in Deep Learning Studio. Tune the geometric, color and noise data augmentations, then check the results on the training dataset.
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 Studio supports all the features of the classification (EasyClassify), segmentation (EasySegment) and localization (EasyLocate) 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.
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.
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.
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.
To access this area, enter your email address and password below and click “SIGN IN”
Enter your email address and click “CREATE AN ACCOUNT”. You will receive a confirmation email shortly. Just click the link in that email to register.
It’s free and easy !