Author: EDGENeural

How do you ensure the security and integrity of my datasets and models? Can anyone access my models or datasets?

Datasets downloaded for training, are deleted on training completion and no part of the data remains with EDGENeural.ai . No member of our team can view or download the data on the user’s behalf and have no access to any of the user’s datasets.  All the stored trained models are part of the users account…

Do I need to have my own HW device for development and testing? Or will you provide me with a virtual device?

Yes, the user needs to have edge hardware for deployment. We do not provide a virtual device.

Can I bring my model?

If your model architecture is not supported within ENAP or you have a customized model for which you want to use ENAP Studio, please write it as a feedback in ENAP Studio or write a mail to connect@edgeneural.ai. We will contact you soon.

How does ENAP Studio help me?

ENAP Studio enables developers to leverage AI at the Edge easily and efficiently. Edge AI applications can be built within a few weeks thereby helping developers to focus on the main project without being bothered by the complexities involved. It provides a platform to easily train, optimize, deploy and manage AI models for edge for…

Which activities can be performed with ENAP Studio?

1. Training an AI model Simple user interface to train various computer vision models with just few selections.  Select the model details, which prefills the default parameters like epochs and batch size for best training performance, upload the dataset, and begin training. 2. Optimizing an AI model The trained AI model from the previous step…

What is ENAP Studio?

ENAP Studio is EDGENeural’s EDGE AI Platform designed to simplify and accelerate the Edge AI development cycle. It is a software-defined platform focused on developing effective AI models for Edge devices. It provides a modular fully-integrated workflow that allows developers to easily Train, Optimize and Deploy Neural Networks for Edge devices. A unified, cloud-neutral, and…

How is developing AI for Edge devices different from that for the cloud?

One of the major factors that differentiate Cloud AI from Edge AI is the infrastructure support. Deep neural networks are growing deep and becoming computationally heavy which can be easily supported with cloud infrastructure. But with Edge AI, the neural networks are deployed on resource-constrained devices. To deploy these huge neural architectures on edge devices…

What is Edge AI?

Edge AI is essentially bringing the data processing near to the source. AI algorithms run locally on the hardware device or edge nodes utilizing the edge computing infrastructure. Data is thus processed in real-time at the source or near to the source. It helps to mitigate few of the challenges associated with cloud AI like…

Model Zoo

It gives the user access to a repository of pre-trained and pre-optimized models. You can directly start using these for your tasks. The hardware supported, accuracy levels, and size of the model is specified in the respective models. Detailed steps to use these are mentioned in the model selected.

Deploying the model

1. Device Registration You need to enter the machine ID details and select the hardware type. Machine ID can be retrieved using command cat/etc/machine-id. Click on submit which gives you the pop up of device registered. Click on View Details in the pop up screen or go to device management and you will get a…