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
460
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
AI 人工智慧學校分享
blue chen
April 20, 2018
More Decks by blue chen
See All by blue chen
RelaJet Caption
iamblue
0
150
The future of hearing device - 聽覺領域新的機會及挑戰
iamblue
2
300
20180918-Digitime 導入MCU設計 催熟智慧語音辨識應用市場
iamblue
0
270
Pixnet hackthon - workshop
iamblue
0
150
Javascript -Full stack 物聯網開發
iamblue
0
180
MCS Lite 私有雲物聯網開發
iamblue
0
340
Blockchain for IoT 應用
iamblue
1
280
2017.01.16 Embedded system
iamblue
0
170
microlattice.js ( World of tech 2016 )
iamblue
1
330
Featured
See All Featured
Ten Tips & Tricks for a 🌱 transition
stuffmc
0
160
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
10k
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
akihiro_kokubo
PRO
72
41k
Leadership Guide Workshop - DevTernity 2021
reverentgeek
1
330
Java REST API Framework Comparison - PWX 2021
mraible
34
9.6k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
17k
The Curse of the Amulet
leimatthew05
2
13k
Crafting Experiences
bethany
1
240
The SEO identity crisis: Don't let AI make you average
varn
0
520
Speed Design
sergeychernyshev
33
2k
Building a A Zero-Code AI SEO Workflow
portentint
PRO
0
650
Being A Developer After 40
akosma
91
590k
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