
Support image dataset
DLHUB supports loading image data by pointing to an image folder. The subfolder names will be defined as output class names.
DLHUB is a graphical deep learning platform that enables deep learning design without requiring any programming skills. User can develop, train, and evaluate deep learning models to tackle real-life industrial solutions by merely drag-and-drop technique and utilizing the model verification feature. It is ideal for engineers who do not have a profound knowledge of deep learning and Python or C# programming skills to properly design a deep learning neural network with the desired architecture. User can effortlessly develop the deep learning model in DLHUB and integrate it into any applications with minimal API calls.
Equipped with a user-friendly graphical interface and model verification feature, DLHUB allows users to complete any deep learning design tasks with ease. Users can construct any deep learning architecture by graphically adding and configuring appropriate deep learning layers into this architecture. DLHUB supports various deep learning layer types from core layers such as a fully connected layer (Dense), convolutional layer (Con2D), pooling layer (Pool2D) to advanced layers that include transfer learning model (TLModel), and residual neural network layer (ResNet).
DLHUB supports advanced training algorithms, including AdaDelta, AdaGrad, Adam, FSAdaGrad, RMSProp, SGD, and Momentum SDG that help to improve the convergence rate. During the training process, a graphics processing unit (GPU) will be detected and enable automatically to speeding up training speed. Mini-batch training technique is also supported to handle big data problem. DLHUB also supports a built-in graphical test interface to evaluate and test the trained deep learning model on an unseen test data before deployment.
DLHUB does not require programming skills to design a deep learning neural network model for any applications. The friendly graphical user interface with drag-and-drop features that help to construct deep learning model with few simple clicks.
DLHUB supports advanced training algorithms, including AdaDelta, AdaGrad, FSAdaGrad, Adam, RMSProp, MomentumSGD, and SGD with mini-batch support. DLHUB also supports GPU to accelerate the training process.
DLHUB supports evaluating trained deep learning model with the new dataset to give a designer instant feedback on how good the trained model can cope with unknown data. As a result, the necessary tweak can be made to improve model stability.
DLHUB supports different types of nodes, including Conv2D, Pool2D, Dense, Flatten, Drop, ResNet, Activation, TLModel (transfer learning), and recurrent nodes to allow a designer to customize a deep neural network structure.
Trained neural network model can be easily deployed in real-time applications developed various programming languages such as LabVIEW, LabVIEW NXG, LabWindow CVI, C.C++, and C# by using supported APIs provided by ANSCENTER.
DLHUB supports different dataset formats to simplify the data processing task. DLHUB supports template scripts that help a designer choose an appropriate deep learning architecture for a given application and dataset type.
DLHUB supports different type of dataset, including text file, image files, and image folders. When a dataset is loaded into DLHUB, data normalization procedure is automatically applied.
DLHUB supports various deep learning node types that help to construct any deep learning neural network model with ease. A designer needs to select node type (1), modify its parameters (2), re-arrange deep learning architecture (3), and verify it this deep learning model is valid or not (4). During the designing process, the designer can save and load this model configuration into the “cfg” file. DLHUB also provides model templates with different deep learning architectures that helps a designer speed-up designing task.
DLHUB supports various training algorithms to allow multiple design options for specific problems. The designer needs to select appropriate training algorithm with its parameters (1) and stopping criteria (2) that decide when to stop before starting the training process (3). The graphical user interface allows a designer to access visual feedback during the training process. The designer can stop training at any time to tweak training parameters. GPU is automatically detected and enabled to accelerate the training process.
DLHUB supports evaluating a trained deep learning model with the new dataset. That helps the designer to validate the deep learning model in different test scenarios before deciding to use the trained model in an actual production environment/application.
Although evaluation helps designer selecting correct trained model architecture, it is useful to test the trained model again with completely unknown test data to see how the trained model behaves before exporting it for deployment.
DLHUB supports loading image data by pointing to an image folder. The subfolder names will be defined as output class names.
DLHUB supports transfer learning that can re-use proven-to-work trained deep learning models.
DLHUB provides editing tools to help a designer efficiently designing a customized deep learning model.
DLHUB supports loading pre-defined templates that help accelerate the design process.
DLHUB supports loading different test dataset format. For image data, folder option is supported.
DLHUB supports loading test image for final validation before deployment.
Learn DLHUB via case studies
ANSCENTER provides elegant solutions to simplify machine learning and deep learning design and deployment for any applications.
We support multiple hardware platforms and programming languages, including LabVIEW, LabVIEW NXG, LabWindow CVI, C/C++/C#, and Arduino.