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
blue chen
April 20, 2018
0
380
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
100
The future of hearing device - 聽覺領域新的機會及挑戰
iamblue
2
240
20180918-Digitime 導入MCU設計 催熟智慧語音辨識應用市場
iamblue
0
210
Pixnet hackthon - workshop
iamblue
0
97
Javascript -Full stack 物聯網開發
iamblue
0
120
MCS Lite 私有雲物聯網開發
iamblue
0
290
Blockchain for IoT 應用
iamblue
1
210
2017.01.16 Embedded system
iamblue
0
88
microlattice.js ( World of tech 2016 )
iamblue
1
280
Featured
See All Featured
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
657
60k
Mobile First: as difficult as doing things right
swwweet
223
9.7k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
Six Lessons from altMBA
skipperchong
28
3.8k
Principles of Awesome APIs and How to Build Them.
keavy
126
17k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
233
17k
Fantastic passwords and where to find them - at NoRuKo
philnash
51
3.3k
Build The Right Thing And Hit Your Dates
maggiecrowley
36
2.7k
Product Roadmaps are Hard
iamctodd
PRO
53
11k
Typedesign – Prime Four
hannesfritz
42
2.7k
Faster Mobile Websites
deanohume
307
31k
Optimizing for Happiness
mojombo
379
70k
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