World's fastest deep learning inference engine "SoftNeuro"
"SoftNeuro" is one of the fastest deep learning inference engines in the world. It utilizes the results of training conducted using major deep learning frameworks to perform high-speed processing in various environments, such as edge devices. Additionally, as a general-purpose inference engine, it can be used not only for image recognition but also for speech recognition and text analysis. It can be licensed as a standalone product, but by integrating it into existing recognition engines like Morpho's "Morpho Deep Recognizer" for images, further acceleration of those existing engines can be achieved.
Inquire About This Product
basic information
1. Achieves inference processing at world-class speeds using only CPU processing. 2. Inference using the results of major deep learning frameworks is possible. 3. Multi-platform support allows for the deployment of learning results to a wide range of operating platforms. 4. Has the capability to encrypt trained networks, reducing the risk of leakage of know-how and results during training.
Price range
Delivery Time
Applications/Examples of results
Morpho has achieved approximately 19 times faster inference of 3D simulations using deep learning on the supercomputer "Fugaku," promoted by the University of Tokyo, Tohoku University, and Kobe University, through the provision of "SoftNeuro."
catalog（1）
Download All Catalogs
Company information
Morpho started in 2004 as a research and development company focused on imaging technology. Based on the belief that computer science is a practical discipline, we consider it our mission to not only conclude cutting-edge research with theory but also to adapt it to societal needs and apply it in the real world. We will contribute to various fields in society through "Imaging AI," which combines the digital image processing technologies we have cultivated so far with cutting-edge artificial intelligence (AI) and deep learning.