Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
AI 人工智慧學校分享
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
blue chen
April 20, 2018
0
420
AI 人工智慧學校分享
blue chen
April 20, 2018
Tweet
Share
More Decks by blue chen
See All by blue chen
RelaJet Caption
iamblue
0
130
The future of hearing device - 聽覺領域新的機會及挑戰
iamblue
2
270
20180918-Digitime 導入MCU設計 催熟智慧語音辨識應用市場
iamblue
0
240
Pixnet hackthon - workshop
iamblue
0
130
Javascript -Full stack 物聯網開發
iamblue
0
160
MCS Lite 私有雲物聯網開發
iamblue
0
320
Blockchain for IoT 應用
iamblue
1
240
2017.01.16 Embedded system
iamblue
0
130
microlattice.js ( World of tech 2016 )
iamblue
1
310
Featured
See All Featured
技術選定の審美眼(2025年版) / Understanding the Spiral of Technologies 2025 edition
twada
PRO
118
110k
Paper Plane (Part 1)
katiecoart
PRO
0
5.1k
How GitHub (no longer) Works
holman
316
140k
Tips & Tricks on How to Get Your First Job In Tech
honzajavorek
0
450
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
soudai
PRO
62
51k
Visual Storytelling: How to be a Superhuman Communicator
reverentgeek
2
460
The Curse of the Amulet
leimatthew05
1
9.6k
職位にかかわらず全員がリーダーシップを発揮するチーム作り / Building a team where everyone can demonstrate leadership regardless of position
madoxten
61
52k
The AI Search Optimization Roadmap by Aleyda Solis
aleyda
1
5.4k
The World Runs on Bad Software
bkeepers
PRO
72
12k
Testing 201, or: Great Expectations
jmmastey
46
8.1k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
17k
Transcript
洞洞 ⾒見見 未 來來 Deep learning on MicroControllerUnit Blue Chen
(
[email protected]
) 2018/04/20 ⼈人⼯工智慧學校
NN Layer Output Input 算法上的幾個關鍵 轉換 轉換 1. FFT (audio)
2. MFCC (audio) 3. RGB resize (vision) 4. Object detection (vision) 5. Face detection (vision) 1. IFFT (audio) 2. IMFCC (audio) 1. Model Size 2. Memory size 3. int / float (HW 加速)
NN Layer Output Input 以視覺辨識為例例 轉換 轉換 最後輸出 N x
1 維度
以聲⾳音輸出為例例 NN Layer Output Input 轉換 轉換
NN Layer Output Input 軟體 Support Effort 很龐⼤大 (先不論 AI
model 設計) 轉換 轉換 1.OS driver porting 2. 轉換器算法 3. openCV/ open VX 4. Dlib 5. FFmpeg (streaming) Coretex A - Android NN Coretex M - CMSIS NN 1. IFFT, IMFCC… 2. Trigger Application 極度不成熟 缺少比較新的 layer support Porting 底層⼈人才稀少 後續應⽤用層 ⼜又是另外⼀一層 Know how
不要隨便便說⾃自⼰己是 AI 公司 真正的 AI 公司,本質是超強的軟體團隊
Training Deployment RelaJet Zoo (各種模型) RelaJet 團隊開發架構 (視覺為例例) Caffe OpenCV
Linux OS Win/Mac Android OS IOS Tensorflow Theano Keras Caffe2 Caffe Pytorch … etc Base on Cortex A / X86 powerful platform OpenVX Base on CortexM 單⼼心片架構系統 語⾔言層 C / C++ C / C++ python/Js/ .. etc C / C++
One more thing….
RelaJet C series https://www.relajet.com/c-series
We provide 1. Vision tool 2. Tensorflow / Caffe /
Caffe2 / Keras model transfer tool 3. Capture Image and video tool 4. Training model tool RelaJet Omnism 全知 platform USD 79
Cifar10
聽覺產品敬請期待! Mail:
[email protected]
FB/ Line / Wechat ID: iambluechen
13 www.relajet.com