|
|
| (2 intermediate revisions by the same user not shown) |
| Line 1: |
Line 1: |
| = Introduction=
| |
| [[File:Banana_PI_BPI-EAI80_3.JPG|thumb|BPI-EAI80 AI board Gree EAI80 chip design]]
| |
| [[File:Banana_PI_BPI-EAI80_5.JPG|thumb|[[BPI-EAI80 AI board]] Gree EAI80 chip design]]
| |
| [[File:BPI-AI_1.JPG|thumb|[[BPI-AI]] Kendryte K210 RISC-V]]
| |
| [[File:Webduino_gif.gif|thumb|[[BPI-Bit]] with ESP32 design ]]
| |
| [[File:BPI-K210_1.JPG|thumb|[[BPI-K210 RISC-V AIoT board]]]]
| |
|
| |
|
|
| |
| =About Edgeless EAI series=
| |
|
| |
| EAI series crossover AI MCU, CPU core is based on ARM Cortex-M4, ARMv7-M supports a
| |
| predefined 32-bit address space, with subdivision for code, data, and peripherals, and regions for
| |
| on-chip and off-chip resources, where on-chip refers to resources that are tightly coupled to the
| |
| processor.
| |
| EAI is a multi-core microcontroller implementing Dual-ARM Cortex-M4 cores. All cores have
| |
| access to the complete memory map. One ARM Cortex-M4 is used as the master processor. The
| |
| other ARM Cortex-M4 core can be used as a co-processor to off-load the ARM Cortex-M4 and to
| |
| perform complicated mathematical calculations.
| |
| CNN processor is integrated in EAI, which can handle image detection and recognition use deep
| |
| learning methods with high performance and low energy consumption. It supports mainstream
| |
| CNN model such as Resnet-18, Resnet-34, Vgg16, GoogleNet, Lenet etc, convolutional with kernel
| |
| size from 1 up to 7, channel/feature number up to 512, max/average pooling function with kernel
| |