Technical Library

Convert and optimize a U-Net-based model for brain tumor segmentation to maximize inference performance on Intel® architecture.

Accelerate object detection by using asynchronous inferencing and distributing workloads to multiple types of processing units.

Build a solution to analyze customer expressions and reactions to product advertising positioned on retail shelves.

Run inference on a pre-trained people detection model from the Intel Distribution of OpenVINO™ toolkit to detect people in a retail setting.

Perform object detection and inference with multiple video and image input feeds simultaneously. Monitor customer activity and track product inventory using a pretrained neural network.

Classify the probability of pneumonia in x-ray images using a pretrained neural network and the Intel® Distribution of OpenVINO™ toolkit. Use Class Activation Maps for insight into network decisions.

Build a modular GStreamer* pipeline to perform object detection, tracking, and classification using the Intel® Distribution of OpenVINO™ toolkit.

Learn how to use DevCloud's benchmarking tool to evaluate the performance of your model's synchronous and asynchronous inference.

Restyle images and video frames using a pretrained network and the Intel® Distribution of OpenVINO™ toolkit.

Perform object detection on images and video using a pretrained network and the Intel® Distribution of OpenVINO™ toolkit.

Migrate your IoT application from DevCloud to your local edge device.

Migrate your IoT application from DevCloud to your local edge device.