M1W 인공지능 lOT 모듈 -K210칩, 딥러닝
(M1W AI+lOT Module K210 Deep learning)
개요
- 본 제품은 M1W AI+lOT 모듈 -K210칩, 딥러닝입니다.
- K210 칩을 코어로 탑재한 제품으로 신경망 하드웨어 엑셀러레이터 KPU, 음성 처리 유닛 APU, 프로그래밍 가능 I/O 어레이 (FPIOA/IOMUX), Fast Fourier Transform Accelerator를 장착하고 있습니다.
- M1W 모듈은 M1칩 기반의 WiFi 기능을 가지고 있습니다.
특징
- CPU: RISC-V dual-core 64 bit
- Debugging Support: high-speed UART and JTAG interface for debugging
- Neural Network Processor: each payer of convolutional neural network parameter can be configured separately, including the number of inpu and output channels, and the input and output line width and column height.
- Image Recognition: QVGA@60FPS/VGA@30FPS
- Audio Processor: support up to 8 channels of audio input data, ie 4 stereo channels
Support for 12 bit, 16 bit, 24 bit and 32 bit input data widths
Up to 192KHz sample rate
- Static Random-Access Memory(SRAM): the SRAM is split into two parts, 6MiB of on-chip general-purpose SRAM and 2 MiB of on-chip AI SRAM
- Field Programmable IO Array: FPIOA allows users to map 255 internal functions to 48 free IOs on the chip
- Digital Video Port: maximum frame size 640 x 480
- FFT Accelerator: the FFT accelerator is a hardware implementation of the Fast Fourier Transform(FFT)
- Deep Learning: TensorFlow/Keras/Darknet
- Peripherals: FPIOA, UART, GPIO, SPI, I2C, I2S, WDT, TIMER, RTC, etc.
- WiFi: support 2.4G 802.11.b/g/n
- Dimension: 25.4 25.4 3.3mm/110.13"
- 72-pin Full Lead-out
- Input Voltage: 5.0V±0.2V(DC)
- Input Current: >300mA(5V)
- Operating Temperature: -30ºC~85ºC
- Compliant with IEEE754-2008 Standard
- MCU: ESP8285 Tensilica L106 32-bit MCU
- Wireless Standard: 802.11b/g/n
- Frequency Range: 2400Mhz-2483.5Mhz
- Transmit Power(Conduction Test): 802.11.b:+15dBm
802.11.n:+10dBm(65Mbps)
- WiFi Mode: Station/SoftAP/SoftAP+Station
- Communication Interface: serial port