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
Food Image Recognition
Search
Leszek Rybicki
February 27, 2017
Research
0
180
Food Image Recognition
Food Image object detection with deep learning
Leszek Rybicki
February 27, 2017
Tweet
Share
More Decks by Leszek Rybicki
See All by Leszek Rybicki
Let's talk about Fakes
lunardog
0
100
How to Patch Image Classifiers
lunardog
0
1.7k
Towards Realistic Predictors - EN
lunardog
0
1.6k
Towards Realistic Predictors
lunardog
1
2k
Deep Learning Hot Dog Detector
lunardog
0
230
Finding beans in burgers: paper reading notes
lunardog
0
1.3k
Kelner: Serve Your Models
lunardog
0
100
Image Analysis at Cookpad
lunardog
1
1.6k
Kelner: serve your models
lunardog
1
330
Other Decks in Research
See All in Research
Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences
sgk
1
320
ミニ四駆AI用制御装置の事例紹介
aks3g
0
160
Weekly AI Agents News! 9月号 プロダクト/ニュースのアーカイブ
masatoto
2
140
論文紹介/Expectations over Unspoken Alternatives Predict Pragmatic Inferences
chemical_tree
1
260
授業評価アンケートのテキストマイニング
langstat
1
360
クラウドソーシングによる学習データ作成と品質管理(セキュリティキャンプ2024全国大会D2講義資料)
takumi1001
0
280
機械学習でヒトの行動を変える
hiromu1996
1
300
TransformerによるBEV Perception
hf149
1
430
RSJ2024「基盤モデルの実ロボット応用」チュートリアルA(河原塚)
haraduka
3
640
Weekly AI Agents News! 8月号 プロダクト/ニュースのアーカイブ
masatoto
1
190
marukotenant01/tenant-20240826
marketing2024
0
510
Language is primarily a tool for communication rather than thought
ryou0634
4
740
Featured
See All Featured
What's new in Ruby 2.0
geeforr
343
31k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
93
16k
A Philosophy of Restraint
colly
203
16k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
10
720
Adopting Sorbet at Scale
ufuk
73
9.1k
Building an army of robots
kneath
302
43k
Documentation Writing (for coders)
carmenintech
65
4.4k
A designer walks into a library…
pauljervisheath
203
24k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
27
840
Rails Girls Zürich Keynote
gr2m
94
13k
Visualization
eitanlees
145
15k
The Straight Up "How To Draw Better" Workshop
denniskardys
232
140k
Transcript
ྉཧͷը૾ղੳ
ࣗݾհ wϦϏπΩϨγΣοΫ wϙʔϥϯυग़ wʙຊ wʙΫοΫύου wը૾ղੳϦαʔνϟʔ wHJUIVCMVOBSEPH
8BSOJOH 5IJTQSFTFOUBUJPODPOUBJOT JNBHFTUIBUNBZDBVTF IFBWZESPPMJOHBOE TUPNBDIHSVNCMJOH
σʔληοτ wʙ wϨγϐɿສ ຊ wݴޠɺϱࠃ
ྉཧ͖Ζ͘
͜ΕྉཧͰ͔͢ʁ
5WFCTUJCP8"HNKEMT 4C[⋆獒EQQMRCF
קؤ؟د؍د"EQQMRCF )GQTIG*QFCP "RWDNKEFQOCKPRKEVWTGUPGV
#TNGPG+PYQQF"EQQMRCF ,KO-KNNQEM"HNKEMT
TCXGPF"HNKEMT پوڀچٲٞٻچ"EQQMRCF
PGUSVFQPTJUJWFT PGTFMFDUFEJUFNT PGBMMQPTJUJWFT PGBMMJUFNT PGUSVFQPTJUJWFT PGGPPEJUFNT ⑮䛟䙨 RTGEKUKQP 捊⛩䙨 TGECNN
侟ㆇ CEEWTCE[
2/10/17, 5:34 PM https://culurciello.github.io/tech/2016/06/20/training-enet.html ⑮䛟䙨獋獋猷ֻ捊⛩䙨獋獃猷
ଟΫϥεֶश 9GHQWPFVJCVVTCKPKPIVJG OQFGNVQENCUUKH[JCTFGT GZCORNGUCUCPGYENCUU KPETGCUGURTGEKUKQPCPFTGECNN
ྉཧͲ͜Ͱ͔͢ʁ
5BTL (KPFHQQFKPVJGKOCIG&TCY CDQWPFKPIDQZCTQWPFVJG HQQFKVGO+PENWFGVJGFKUJ KHXKUKDNG
5BTL +HVJGTGCTGOWNVKRNG KVGOUFTCYCDQWPFKPI DQZCTQWPFGCEJQPG
ITQWPFVTWVJ DQWPFKPIDQZ 9GEQWPVKVCUC RQUKVKXGFGVGEVKQPKH +PVGTUGEVKQPQXGT 7PKQPTCVKQKU ITGCVGTVJCP
PGUSVFQPTJUJWFT PGHSPVOEUSVUICPYFT PGUSVFQPTJUJWFT PGHFOFSBUFECPYFT ⑮䛟䙨 RTGEKUKQP 捊⛩䙨 TGECNN
.FUIPET
'JSTUJEFB w#VJMEBDMBTTJpFS w1JDL3P*T SFHJPOPGJOUFSFTU w3VODMBTTJpFSPOFBDISFHJPO w3FNPWFEVQMJDBUFEFUFDUJPOT w%0/&ʜ
3$//
hand food grass food
4JOHMF4IPU%FUFDUPS
:0-0 :PV0OMZ-PPL0ODF
Either The Least Or Most Employable Person Ever - The
Huffington Post HJUIVCDPNQKSFEEJF QKSFEEJFDPNEBSLOFU XXXLBHHMFDPNQKSFEEJF +PTFQI3FENPO
None
"*νϟϨϯδίϯςετ IUUQTEFFQBOBMZUJDTKQDPNQF
εέδϡʔϧ ݄̎̌̍̓̍̍̌ʢՐʣɹίϯςετ։࢝ ݄̎̌̍̓̏ɹ̕ʢʣɹίϯςετऴྃ ݄̎̌̍̓̏̍̏ʢ݄ʣɹ༧ଌϞσϧͷఏग़కɹ ݄̎̌̍̓̏ɹɹԼ०ɹɹɹݕऩɾ৹ࠪʹͯೖऀΛܾఆ ݄̎̌̍̓̑ɹɹԼ०ɹɹɹදজࣜ
։࠵෦
,0/*&$