IBM PowerAI Inference Engine

DeepRED: Machine Learning Development Platform 

IBM PowerAI Inference Engine based on Xilinx ZYNQ SoC 

DeepRED

 

DeepRED is an embedded artificial intelligence development system, based on XILINX's high-performance Zynq SoC FPGAs, which can be used to meet real-time demanding reasoning requirements. The system supports IBM's inference engine (PIE), which automates the conversion of FPGA code for deep learning models, enabling users to quickly transit the trained model to hardware deployment for fast algorithm validation. 

At the same time, DeepRED platform can also support 
Xilinx reVISION and SDSoC development process, greatly speeding up the process of embedded vision development.

deepred 2

It supports the PIE tool from IBM's world-leading PowerAI system, a cloud-based FPGA code conversion tool that currently supports neural network models trained by the Caffe. In order to achieve high accuracy, it is recommended to use Caffe Ristritto version of the model to quantify, and then upload a good model. Supports convolution layer, maximum pooling layer, full connection layer, BN layer and ReLU activation function. The sum of the total connection layer and the convolution layer should be less than 16. 

deepred 1


DeepRED Experimental Cases

Basic Experiments

1. HDMI output color bar video experiment

2. HDMI video input and output experiment

Deep Learning Experiments

1. Cifar10 Image Classification Experiment Based on OpenCV and PowerAI

2. Cifar10 Classification Experiment Based on Video Stream and PowerAI

3. Vehicle and Pedestrian Detection Experiment Based on YOLO and MATLAB

4. Vehicle and Pedestrian Detection Experiment Based on YOLO and Video Stream

5. Face Detection Video Stream Display Experiment

6. Face detection and recognition experiment

SDSoC Experiments

1. Experiments based on the acceleration (optical flow) of OpenCV library function of SDSoC

2. Based on SDSoC OpenCV Library Function Acceleration Experiment



Course Registration Form


Course Title
Invalid Input

or Key in Your Own Title
Invalid Input

Course Start Date

Invalid Input

Sponsorship (*)
Invalid Input


Contact Person


Salutation(*)
Invalid Input

Name(*)
Invalid Input

Designation/ Department/ Division(*)
Invalid Input

Company(*)
Invalid Input

Billing Address (*)
Invalid Input

Street Address

(*)
Invalid Input

Street Address Line 2

City(*)
Invalid Input

State / Province(*)
Invalid Input

Postal / Zip Code(*)
Invalid Input

Telephone(*)
Invalid Input

Fax
Invalid Input

Email Address (*)
Invalid Input


Participant Details


Participant Salution 1
Invalid Input

Participant Name1
Invalid Input

Designation/ Department/ Division
Invalid Input

Telephone
Invalid Input

Fax
Invalid Input

Email Address
Invalid Input

Dietary Requirement
Invalid Input


Participant Salution 2
Invalid Input

Participant Name2
Invalid Input

Designation/ Department/ Division
Invalid Input

Telephone
Invalid Input

Fax
Invalid Input

Email Address
Invalid Input

Dietary Requirement
Invalid Input


Participant Salution 3
Invalid Input

Participant Name 3
Invalid Input

Designation/ Department/ Division
Invalid Input

Telephone
Invalid Input

Fax
Invalid Input

Email Address
Invalid Input

Dietary Requirement
Invalid Input


Payment Method(*)
Invalid Input

Cheque number
Invalid Input

PO Number
Invalid Input

How did you get to know about this programme?(*)
Invalid Input

Terms and Conditions
Invalid Input

Invalid Input