CNN AI IP Core

Overview

DeepMentor has developed an AI IP that combines low-power and high-performance features with the RISC-V SOC. This integration allows customers to quickly create unique AI SOC without worrying about software integration or system development issues. DeepLogCore supports both RISC-V and ARM systems, enabling faster and more flexible development.

DeepLogcore is a soft AI IP compatible with a wide range of processes, particularly mature and power-saving low-cost processes between 28nm to 130nm. As a result, customers can control their manufacturing costs according to their specific needs and market demands.

Key Features

  • High-efficiency Al Silicon Intellectual Property
    • The performance of Al silicon can reach @SO 0Mhz 1 TOP/s.
  • Supports DeepMentor Exclusive Low-distortion MAT Training Models
    • In the case of Int4, the accuracy is only reduced by 1-2%. (Example: yolov4 - 416x416, coco, etc.)
  • High Integrity of Software and Hardware
    • DeepLogCore service includes the operating system, the silicon intellectual property driver, and the establishment and deployment of Al models. Clients don't need to bother to research and integrate silicon intellectual property.
  • Complete Maintenance and Retraining Systems
    • Products can be updated at any time by using the maintenance and retraining services on our DeepLogMaker platform.

Benefits

  • power-saving low-cost processes (28nm~130nm)
  • Development time 30~100x faster than manual Verilog coding
  • Flexible to update the latest AI features
  • Supports DeepMentor Exclusive Low-distortion Training Models

Block Diagram

CNN AI IP Core Block Diagram

Applications

  • Object classification
  • Object detection
  • Face detection/identification
  • Human pose detection
  • Hand-gesture recognition
  • Eye tracking
  • Image segmentation
  • Image beautification
  • Super resolution
     

Technical Specifications

Short description
CNN AI IP Core
Vendor
Vendor Name
×
Semiconductor IP