SlideShare uma empresa Scribd logo
1 de 35
Baixar para ler offline
Putting Together 
World's Best Data Processing Research 
with Python 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 
Akira Shibata, PhD 
Shiroyagi Corporation
Who am I 
Akira Shibata, PhD. 
TW: @punkphysicist 
CEO, Shiroyagi Corporation (shiroyagi.co.jp) 
Kamelio: Personalised News Curation 
Kamect: Contents Discovery Platform 
2004 - 2010: 
Data Scientist @ NYU 
Statistical data modelling @ LHC, CERN 
2010 - 2013 
Boston Consulting Group 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 2
Copyright 2014 Shiroyagi Corporation. All rights reserved. 3
Statistical modelling of Physics data 
Confirmatory: 
Highly theory driven model building 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 4
Telling discovery from noise 
The model tells you the expected uncertainty 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 5
Copyright 2014 Shiroyagi Corporation. All rights reserved. 6
Copyright 2014 Shiroyagi Corporation. All rights reserved. 7
Copyright 2014 Shiroyagi Corporation. All rights reserved. 8
Copyright 2014 Shiroyagi Corporation. All rights reserved. 9
Copyright 2014 Shiroyagi Corporation. All rights reserved. 10
Kamelio 
“Deep Learning” 
“Internet of 
Things” 
“Medical IT” 
“Global Strategy” 
Collects news through >3M 
topics to chose from 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 11
3 
“Cats” 
“Anime” 
“Cats reaction to sighting 
dogs for the first time” 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 12
Python puts all our tools together 
Image in Detect 
regions 
Object 
recog. Scoring Cropping 
0 1 2 3 4 
Matlab 
+Scipy 
C++ 
+Libraries 
Numpy PIL 
IPython and Python script 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 13
Our approach is 
heavily influenced by 
Berkeley Vision and 
Learning Center 
Acknowledgement 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 14
Detect 
regions 
0 1 2 3 4 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 15
Region detection: Telling where to look at 
How do we find regions to feed into object recognition? 
Default strategy was to look at the center 
1 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 16
Exhaustive windows -> segmentation 
Search over position, 
scale, aspect ratio 
Grouping parts of 
image at different scales 
Exhaustive search far too time inefficient 
for use with Deep Learning 
1 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 17
1 Region detection: in practice 
Install Malab and Selective Search algorithm 
from author 
Run matlab as subprocess 
pid = subprocess.Popen(shlex.split(mc), stdout=open('/dev/null', 
'w'), cwd=script_dirname) 
matlab -nojvm -r "try; selective_search({‘image_file.jpg’}, 
‘output.mat'); catch; exit; end; exit” 
1 
2 
3 
Import output using scipy.io 
all_boxes = list(scipy.io.loadmat(‘output.mat')['all_boxes'][0]) 
subtractor = np.array((1, 1, 0, 0))[np.newaxis, :] 
all_boxes = [boxes - subtractor for boxes in all_boxes] 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 18
1 Region detection: proposals generated 
~200 proposals generated per image 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 19
Object 
recog. 
0 1 2 3 4 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 20
Object recognition 
Deep blue beat Kasparov at chess in 1997… 
2 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 21
2 Deep Learning: Damn good at it 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 22
2 Convoluted Neural Network 
… 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 23
Caffe: open R-CNN framework under rapid dev. 
C++/CUDA with Python wrapper 
2 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 24
Pre-trained models published 
We used 200-category object recog. model 
developed for 2013 ImageNet Challenge 
2 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 25
2 Object recognition: in practice 
Install a bunch of libraries and Caffe 
CUDA, Boost, OpenCV, BLAS… 
Import wrapper and configure 
MODEL_FILE=‘models/bvlc_…_ilsvrc13/deploy.prototxt’ 
PRETRAINED_FILE = ‘models/…/bvlc_…_ilsvrc13.caffemodel’ 
MEAN_FILE = 'caffe/imagenet/ilsvrc_2012_mean.npy' 
detector = caffe.Detector(MODEL_FILE, PRETRAINED_FILE, 
mean=np.load(MEAN_FILE), raw_scale=255, channel_swap=[2,1,0]) 
1 
2 
3 
Pass found regions for object detection 
self.detect_windows(zip(image_fnames, windows_list)) 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 26
2 Object recognition: Result 
Obj Score 
0 domestic cat 1.03649377823 
1 domestic cat 0.0617411136627 
2 domestic cat -0.097744345665 
3 domestic cat -0.738470971584 
4 chair -0.988844156265 
5 skunk -0.999914288521 
6 tv or monitor -1.00460898876 
7 rubber eraser -1.01068615913 
8 chair -1.04896986485 
9 rubber eraser -1.09035253525 
10 band aid -1.09691572189 
Takes minutes to detect all windows 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 27
2 Object recognition: Result 
Obj Score 
0 person 0.126184225082 
1 person 0.0311727523804 
2 person -0.0777613520622 
3 neck brace -0.39757412672 
4 person -0.415030777454 
5 drum -0.421649754047 
6 neck brace -0.481261610985 
7 tie -0.649109125137 
8 neck brace -0.719438135624 
9 face powder -0.789100408554 
10 face powder -0.838757038116 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 28
Scoring 
0 1 2 3 4 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 29
3 Scoring 
1 For every pixel, sum up score from all detections 
for 
i 
in 
xrange(len(detec0ons)): 
arr[ymin:ymax, 
xmin:xmax] 
+= 
math.exp(score) 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 30
Score heatmap 
We used 200-cat object recognition model 
developed for 2013 ImageNet Challenge 
3 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 31
Cropping 
0 1 2 3 4 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 32
4 Cropping 
Generate all possible crop areas 
while 
y+hws 
<= 
h: 
while 
x+hws 
<= 
w: 
window_locs 
= 
np.vstack((window_locs, 
[x, 
y, 
x+hws, 
y+hws])) 
Find the crop that encloses the highest point of 
interest in the centre 
for 
i, 
window_loc 
in 
enumerate(window_locs): 
x1, 
y1, 
x2, 
y2 
= 
window_loc 
if 
max_val 
!= 
np.max(arr_con[y1:y2, 
x1:x2]): 
scores[i]=np.nan 
else: 
scores[i] 
= 
((x1+x2)/2.-­‐xp)**2+ 
((y1+y2)/2.-­‐yp)**2 
1 
2 
3 
Crop and save! 
img_pil 
= 
Image.open(fn) 
crop_area=map(lambda 
x: 
int(x), 
window_locs[scores.argmax()]) 
img_crop 
= 
img_pil.crop(crop_area) 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 33
4 Finally 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 34
Future improvements 
Fast face/human 
detection 
Aspect detection: 
square or rectangle? 
Object weighting 
Magnification 
Unseen object 
Copyright 2014 Shiroyagi Corporation. All rights reserved. 35

Mais conteúdo relacionado

Mais procurados

CVPR2016を自分なりにまとめてみた
CVPR2016を自分なりにまとめてみたCVPR2016を自分なりにまとめてみた
CVPR2016を自分なりにまとめてみたHiroshi Fukui
 
Action Recognitionの歴史と最新動向
Action Recognitionの歴史と最新動向Action Recognitionの歴史と最新動向
Action Recognitionの歴史と最新動向Ohnishi Katsunori
 
[AI07] Revolutionizing Image Processing with Cognitive Toolkit
[AI07] Revolutionizing Image Processing with Cognitive Toolkit[AI07] Revolutionizing Image Processing with Cognitive Toolkit
[AI07] Revolutionizing Image Processing with Cognitive Toolkitde:code 2017
 
FPT17: An object detector based on multiscale sliding window search using a f...
FPT17: An object detector based on multiscale sliding window search using a f...FPT17: An object detector based on multiscale sliding window search using a f...
FPT17: An object detector based on multiscale sliding window search using a f...Hiroki Nakahara
 
【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised LearningまとめDeep Learning JP
 
モデルアーキテクチャ観点からの高速化2019
モデルアーキテクチャ観点からの高速化2019モデルアーキテクチャ観点からの高速化2019
モデルアーキテクチャ観点からの高速化2019Yusuke Uchida
 
Real Time Human Posture Detection with Multiple Depth Sensors
Real Time Human Posture Detection with Multiple Depth SensorsReal Time Human Posture Detection with Multiple Depth Sensors
Real Time Human Posture Detection with Multiple Depth SensorsWassim Filali
 
用 Python 玩 LHC 公開數據
用 Python 玩 LHC 公開數據用 Python 玩 LHC 公開數據
用 Python 玩 LHC 公開數據Yuan CHAO
 
【CVPR 2020 メタサーベイ】Video Analysis and Understanding
【CVPR 2020 メタサーベイ】Video Analysis and Understanding【CVPR 2020 メタサーベイ】Video Analysis and Understanding
【CVPR 2020 メタサーベイ】Video Analysis and Understandingcvpaper. challenge
 
Ice: lightweight, efficient rendering for remote sensing images
Ice: lightweight, efficient rendering for remote sensing imagesIce: lightweight, efficient rendering for remote sensing images
Ice: lightweight, efficient rendering for remote sensing imagesotb
 
Deep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image ProcessingDeep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image ProcessingGrigory Sapunov
 
Orfeo ToolBox workshop at FOSS4G Europe 2015
Orfeo ToolBox workshop at FOSS4G Europe 2015Orfeo ToolBox workshop at FOSS4G Europe 2015
Orfeo ToolBox workshop at FOSS4G Europe 2015otb
 
Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity ...
Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity ...Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity ...
Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity ...Hirokatsu Kataoka
 
kaggle NFL 1st and Future - Impact Detection
kaggle NFL 1st and Future - Impact Detectionkaggle NFL 1st and Future - Impact Detection
kaggle NFL 1st and Future - Impact DetectionKazuyuki Miyazawa
 
Александр Заричковый "Faster than real-time face detection"
Александр Заричковый "Faster than real-time face detection"Александр Заричковый "Faster than real-time face detection"
Александр Заричковый "Faster than real-time face detection"Fwdays
 
Deep Learning in the Wild with Arno Candel
Deep Learning in the Wild with Arno CandelDeep Learning in the Wild with Arno Candel
Deep Learning in the Wild with Arno CandelSri Ambati
 
Pragmatic Remote Sensing - IGARSS 2010
Pragmatic Remote Sensing - IGARSS 2010Pragmatic Remote Sensing - IGARSS 2010
Pragmatic Remote Sensing - IGARSS 2010otb
 
20110220 computer vision_eruhimov_lecture02
20110220 computer vision_eruhimov_lecture0220110220 computer vision_eruhimov_lecture02
20110220 computer vision_eruhimov_lecture02Computer Science Club
 
Machine learning quality for production
Machine learning quality for productionMachine learning quality for production
Machine learning quality for productionyusuke shibui
 

Mais procurados (20)

CVPR2016を自分なりにまとめてみた
CVPR2016を自分なりにまとめてみたCVPR2016を自分なりにまとめてみた
CVPR2016を自分なりにまとめてみた
 
Action Recognitionの歴史と最新動向
Action Recognitionの歴史と最新動向Action Recognitionの歴史と最新動向
Action Recognitionの歴史と最新動向
 
[AI07] Revolutionizing Image Processing with Cognitive Toolkit
[AI07] Revolutionizing Image Processing with Cognitive Toolkit[AI07] Revolutionizing Image Processing with Cognitive Toolkit
[AI07] Revolutionizing Image Processing with Cognitive Toolkit
 
FPT17: An object detector based on multiscale sliding window search using a f...
FPT17: An object detector based on multiscale sliding window search using a f...FPT17: An object detector based on multiscale sliding window search using a f...
FPT17: An object detector based on multiscale sliding window search using a f...
 
【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ
 
モデルアーキテクチャ観点からの高速化2019
モデルアーキテクチャ観点からの高速化2019モデルアーキテクチャ観点からの高速化2019
モデルアーキテクチャ観点からの高速化2019
 
Real Time Human Posture Detection with Multiple Depth Sensors
Real Time Human Posture Detection with Multiple Depth SensorsReal Time Human Posture Detection with Multiple Depth Sensors
Real Time Human Posture Detection with Multiple Depth Sensors
 
用 Python 玩 LHC 公開數據
用 Python 玩 LHC 公開數據用 Python 玩 LHC 公開數據
用 Python 玩 LHC 公開數據
 
Adaptive object detection using adjacency and zoom prediction
Adaptive object detection using adjacency and zoom predictionAdaptive object detection using adjacency and zoom prediction
Adaptive object detection using adjacency and zoom prediction
 
【CVPR 2020 メタサーベイ】Video Analysis and Understanding
【CVPR 2020 メタサーベイ】Video Analysis and Understanding【CVPR 2020 メタサーベイ】Video Analysis and Understanding
【CVPR 2020 メタサーベイ】Video Analysis and Understanding
 
Ice: lightweight, efficient rendering for remote sensing images
Ice: lightweight, efficient rendering for remote sensing imagesIce: lightweight, efficient rendering for remote sensing images
Ice: lightweight, efficient rendering for remote sensing images
 
Deep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image ProcessingDeep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image Processing
 
Orfeo ToolBox workshop at FOSS4G Europe 2015
Orfeo ToolBox workshop at FOSS4G Europe 2015Orfeo ToolBox workshop at FOSS4G Europe 2015
Orfeo ToolBox workshop at FOSS4G Europe 2015
 
Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity ...
Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity ...Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity ...
Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity ...
 
kaggle NFL 1st and Future - Impact Detection
kaggle NFL 1st and Future - Impact Detectionkaggle NFL 1st and Future - Impact Detection
kaggle NFL 1st and Future - Impact Detection
 
Александр Заричковый "Faster than real-time face detection"
Александр Заричковый "Faster than real-time face detection"Александр Заричковый "Faster than real-time face detection"
Александр Заричковый "Faster than real-time face detection"
 
Deep Learning in the Wild with Arno Candel
Deep Learning in the Wild with Arno CandelDeep Learning in the Wild with Arno Candel
Deep Learning in the Wild with Arno Candel
 
Pragmatic Remote Sensing - IGARSS 2010
Pragmatic Remote Sensing - IGARSS 2010Pragmatic Remote Sensing - IGARSS 2010
Pragmatic Remote Sensing - IGARSS 2010
 
20110220 computer vision_eruhimov_lecture02
20110220 computer vision_eruhimov_lecture0220110220 computer vision_eruhimov_lecture02
20110220 computer vision_eruhimov_lecture02
 
Machine learning quality for production
Machine learning quality for productionMachine learning quality for production
Machine learning quality for production
 

Semelhante a PyData NYC by Akira Shibata

Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingChallenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingAdhesh Shrivastava
 
Introduction to Crab - Python Framework for Building Recommender Systems
Introduction to Crab - Python Framework for Building Recommender SystemsIntroduction to Crab - Python Framework for Building Recommender Systems
Introduction to Crab - Python Framework for Building Recommender SystemsMarcel Caraciolo
 
502021435-12345678Minor-Project-Ppt.pptx
502021435-12345678Minor-Project-Ppt.pptx502021435-12345678Minor-Project-Ppt.pptx
502021435-12345678Minor-Project-Ppt.pptxshrey4922
 
20181212 Queensland AI Meetup
20181212 Queensland AI Meetup20181212 Queensland AI Meetup
20181212 Queensland AI MeetupAdam Craven
 
IRJET- Object Detection in an Image using Convolutional Neural Network
IRJET- Object Detection in an Image using Convolutional Neural NetworkIRJET- Object Detection in an Image using Convolutional Neural Network
IRJET- Object Detection in an Image using Convolutional Neural NetworkIRJET Journal
 
Machine_learning_internship_report_facemaskdetection.pptx
Machine_learning_internship_report_facemaskdetection.pptxMachine_learning_internship_report_facemaskdetection.pptx
Machine_learning_internship_report_facemaskdetection.pptxpratikpatil862906
 
Using Deep Learning for Computer Vision Applications
Using Deep Learning for Computer Vision ApplicationsUsing Deep Learning for Computer Vision Applications
Using Deep Learning for Computer Vision ApplicationsFarshid Pirahansiah
 
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...Edureka!
 
Fernando Arnaboldi - Exposing Hidden Exploitable Behaviors Using Extended Dif...
Fernando Arnaboldi - Exposing Hidden Exploitable Behaviors Using Extended Dif...Fernando Arnaboldi - Exposing Hidden Exploitable Behaviors Using Extended Dif...
Fernando Arnaboldi - Exposing Hidden Exploitable Behaviors Using Extended Dif...Codemotion
 
Pytorch kr devcon
Pytorch kr devconPytorch kr devcon
Pytorch kr devconjaewon lee
 
Vipul divyanshu documentation on Kinect and Motion Tracking
Vipul divyanshu documentation  on Kinect and Motion TrackingVipul divyanshu documentation  on Kinect and Motion Tracking
Vipul divyanshu documentation on Kinect and Motion TrackingVipul Divyanshu
 
Crab - A Python Framework for Building Recommendation Systems
Crab - A Python Framework for Building Recommendation SystemsCrab - A Python Framework for Building Recommendation Systems
Crab - A Python Framework for Building Recommendation SystemsMarcel Caraciolo
 
SDOBenchmark - a machine learning image dataset for the prediction of solar f...
SDOBenchmark - a machine learning image dataset for the prediction of solar f...SDOBenchmark - a machine learning image dataset for the prediction of solar f...
SDOBenchmark - a machine learning image dataset for the prediction of solar f...Roman Bolzern
 
Updates from Project Hydrogen: Unifying State-of-the-Art AI and Big Data in A...
Updates from Project Hydrogen: Unifying State-of-the-Art AI and Big Data in A...Updates from Project Hydrogen: Unifying State-of-the-Art AI and Big Data in A...
Updates from Project Hydrogen: Unifying State-of-the-Art AI and Big Data in A...Databricks
 
深層学習フレームワーク概要とChainerの事例紹介
深層学習フレームワーク概要とChainerの事例紹介深層学習フレームワーク概要とChainerの事例紹介
深層学習フレームワーク概要とChainerの事例紹介Kenta Oono
 

Semelhante a PyData NYC by Akira Shibata (20)

Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingChallenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
 
Introduction to Crab - Python Framework for Building Recommender Systems
Introduction to Crab - Python Framework for Building Recommender SystemsIntroduction to Crab - Python Framework for Building Recommender Systems
Introduction to Crab - Python Framework for Building Recommender Systems
 
502021435-12345678Minor-Project-Ppt.pptx
502021435-12345678Minor-Project-Ppt.pptx502021435-12345678Minor-Project-Ppt.pptx
502021435-12345678Minor-Project-Ppt.pptx
 
DS LAB MANUAL.pdf
DS LAB MANUAL.pdfDS LAB MANUAL.pdf
DS LAB MANUAL.pdf
 
20181212 Queensland AI Meetup
20181212 Queensland AI Meetup20181212 Queensland AI Meetup
20181212 Queensland AI Meetup
 
IRJET- Object Detection in an Image using Convolutional Neural Network
IRJET- Object Detection in an Image using Convolutional Neural NetworkIRJET- Object Detection in an Image using Convolutional Neural Network
IRJET- Object Detection in an Image using Convolutional Neural Network
 
Machine_learning_internship_report_facemaskdetection.pptx
Machine_learning_internship_report_facemaskdetection.pptxMachine_learning_internship_report_facemaskdetection.pptx
Machine_learning_internship_report_facemaskdetection.pptx
 
Using Deep Learning for Computer Vision Applications
Using Deep Learning for Computer Vision ApplicationsUsing Deep Learning for Computer Vision Applications
Using Deep Learning for Computer Vision Applications
 
Content-Centric Embedded ~Treasure Hunting Robot~ for LinuxCon Japan 2012
Content-Centric Embedded ~Treasure Hunting Robot~ for LinuxCon Japan 2012Content-Centric Embedded ~Treasure Hunting Robot~ for LinuxCon Japan 2012
Content-Centric Embedded ~Treasure Hunting Robot~ for LinuxCon Japan 2012
 
Content-Centric Embedded
Content-Centric EmbeddedContent-Centric Embedded
Content-Centric Embedded
 
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
 
Obj report
Obj reportObj report
Obj report
 
Fernando Arnaboldi - Exposing Hidden Exploitable Behaviors Using Extended Dif...
Fernando Arnaboldi - Exposing Hidden Exploitable Behaviors Using Extended Dif...Fernando Arnaboldi - Exposing Hidden Exploitable Behaviors Using Extended Dif...
Fernando Arnaboldi - Exposing Hidden Exploitable Behaviors Using Extended Dif...
 
Pytorch kr devcon
Pytorch kr devconPytorch kr devcon
Pytorch kr devcon
 
Vipul divyanshu documentation on Kinect and Motion Tracking
Vipul divyanshu documentation  on Kinect and Motion TrackingVipul divyanshu documentation  on Kinect and Motion Tracking
Vipul divyanshu documentation on Kinect and Motion Tracking
 
Awalin viz sec
Awalin viz secAwalin viz sec
Awalin viz sec
 
Crab - A Python Framework for Building Recommendation Systems
Crab - A Python Framework for Building Recommendation SystemsCrab - A Python Framework for Building Recommendation Systems
Crab - A Python Framework for Building Recommendation Systems
 
SDOBenchmark - a machine learning image dataset for the prediction of solar f...
SDOBenchmark - a machine learning image dataset for the prediction of solar f...SDOBenchmark - a machine learning image dataset for the prediction of solar f...
SDOBenchmark - a machine learning image dataset for the prediction of solar f...
 
Updates from Project Hydrogen: Unifying State-of-the-Art AI and Big Data in A...
Updates from Project Hydrogen: Unifying State-of-the-Art AI and Big Data in A...Updates from Project Hydrogen: Unifying State-of-the-Art AI and Big Data in A...
Updates from Project Hydrogen: Unifying State-of-the-Art AI and Big Data in A...
 
深層学習フレームワーク概要とChainerの事例紹介
深層学習フレームワーク概要とChainerの事例紹介深層学習フレームワーク概要とChainerの事例紹介
深層学習フレームワーク概要とChainerの事例紹介
 

Mais de Akira Shibata

大規模言語モデル開発を支える分散学習技術 - 東京工業大学横田理央研究室の藤井一喜さん
大規模言語モデル開発を支える分散学習技術 - 東京工業大学横田理央研究室の藤井一喜さん大規模言語モデル開発を支える分散学習技術 - 東京工業大学横田理央研究室の藤井一喜さん
大規模言語モデル開発を支える分散学習技術 - 東京工業大学横田理央研究室の藤井一喜さんAkira Shibata
 
W&B monthly meetup#7 Intro.pdf
W&B monthly meetup#7 Intro.pdfW&B monthly meetup#7 Intro.pdf
W&B monthly meetup#7 Intro.pdfAkira Shibata
 
20230705 - Optuna Integration (to share).pdf
20230705 - Optuna Integration (to share).pdf20230705 - Optuna Integration (to share).pdf
20230705 - Optuna Integration (to share).pdfAkira Shibata
 
W&B Seminar #5(to share).pdf
W&B Seminar #5(to share).pdfW&B Seminar #5(to share).pdf
W&B Seminar #5(to share).pdfAkira Shibata
 
makoto shing (stability ai) - image model fine-tuning - wandb_event_230525.pdf
makoto shing (stability ai) - image model fine-tuning - wandb_event_230525.pdfmakoto shing (stability ai) - image model fine-tuning - wandb_event_230525.pdf
makoto shing (stability ai) - image model fine-tuning - wandb_event_230525.pdfAkira Shibata
 
LLM Webinar - シバタアキラ to share.pdf
LLM Webinar - シバタアキラ to share.pdfLLM Webinar - シバタアキラ to share.pdf
LLM Webinar - シバタアキラ to share.pdfAkira Shibata
 
Kaggle and data science
Kaggle and data scienceKaggle and data science
Kaggle and data scienceAkira Shibata
 
Akira shibata at developer summit 2016
Akira shibata at developer summit 2016Akira shibata at developer summit 2016
Akira shibata at developer summit 2016Akira Shibata
 
PyData.Tokyo Hackathon#2 TensorFlow
PyData.Tokyo Hackathon#2 TensorFlowPyData.Tokyo Hackathon#2 TensorFlow
PyData.Tokyo Hackathon#2 TensorFlowAkira Shibata
 
20150421 日経ビッグデータカンファレンス
20150421 日経ビッグデータカンファレンス20150421 日経ビッグデータカンファレンス
20150421 日経ビッグデータカンファレンスAkira Shibata
 
人工知能をビジネスに活かす
人工知能をビジネスに活かす人工知能をビジネスに活かす
人工知能をビジネスに活かすAkira Shibata
 
LHCにおける素粒子ビッグデータの解析とROOTライブラリ(Big Data Analysis at LHC and ROOT)
LHCにおける素粒子ビッグデータの解析とROOTライブラリ(Big Data Analysis at LHC and ROOT)LHCにおける素粒子ビッグデータの解析とROOTライブラリ(Big Data Analysis at LHC and ROOT)
LHCにおける素粒子ビッグデータの解析とROOTライブラリ(Big Data Analysis at LHC and ROOT)Akira Shibata
 
PyData Tokyo Tutorial & Hackathon #1
PyData Tokyo Tutorial & Hackathon #1PyData Tokyo Tutorial & Hackathon #1
PyData Tokyo Tutorial & Hackathon #1Akira Shibata
 
20141127 py datatokyomeetup2
20141127 py datatokyomeetup220141127 py datatokyomeetup2
20141127 py datatokyomeetup2Akira Shibata
 
The LHC Explained by CNN
The LHC Explained by CNNThe LHC Explained by CNN
The LHC Explained by CNNAkira Shibata
 
Analysis Software Development
Analysis Software DevelopmentAnalysis Software Development
Analysis Software DevelopmentAkira Shibata
 

Mais de Akira Shibata (20)

大規模言語モデル開発を支える分散学習技術 - 東京工業大学横田理央研究室の藤井一喜さん
大規模言語モデル開発を支える分散学習技術 - 東京工業大学横田理央研究室の藤井一喜さん大規模言語モデル開発を支える分散学習技術 - 東京工業大学横田理央研究室の藤井一喜さん
大規模言語モデル開発を支える分散学習技術 - 東京工業大学横田理央研究室の藤井一喜さん
 
W&B monthly meetup#7 Intro.pdf
W&B monthly meetup#7 Intro.pdfW&B monthly meetup#7 Intro.pdf
W&B monthly meetup#7 Intro.pdf
 
20230705 - Optuna Integration (to share).pdf
20230705 - Optuna Integration (to share).pdf20230705 - Optuna Integration (to share).pdf
20230705 - Optuna Integration (to share).pdf
 
W&B Seminar #5(to share).pdf
W&B Seminar #5(to share).pdfW&B Seminar #5(to share).pdf
W&B Seminar #5(to share).pdf
 
makoto shing (stability ai) - image model fine-tuning - wandb_event_230525.pdf
makoto shing (stability ai) - image model fine-tuning - wandb_event_230525.pdfmakoto shing (stability ai) - image model fine-tuning - wandb_event_230525.pdf
makoto shing (stability ai) - image model fine-tuning - wandb_event_230525.pdf
 
LLM Webinar - シバタアキラ to share.pdf
LLM Webinar - シバタアキラ to share.pdfLLM Webinar - シバタアキラ to share.pdf
LLM Webinar - シバタアキラ to share.pdf
 
W&B Seminar #4.pdf
W&B Seminar #4.pdfW&B Seminar #4.pdf
W&B Seminar #4.pdf
 
Kaggle and data science
Kaggle and data scienceKaggle and data science
Kaggle and data science
 
Data x
Data xData x
Data x
 
Akira shibata at developer summit 2016
Akira shibata at developer summit 2016Akira shibata at developer summit 2016
Akira shibata at developer summit 2016
 
PyData.Tokyo Hackathon#2 TensorFlow
PyData.Tokyo Hackathon#2 TensorFlowPyData.Tokyo Hackathon#2 TensorFlow
PyData.Tokyo Hackathon#2 TensorFlow
 
20150421 日経ビッグデータカンファレンス
20150421 日経ビッグデータカンファレンス20150421 日経ビッグデータカンファレンス
20150421 日経ビッグデータカンファレンス
 
人工知能をビジネスに活かす
人工知能をビジネスに活かす人工知能をビジネスに活かす
人工知能をビジネスに活かす
 
LHCにおける素粒子ビッグデータの解析とROOTライブラリ(Big Data Analysis at LHC and ROOT)
LHCにおける素粒子ビッグデータの解析とROOTライブラリ(Big Data Analysis at LHC and ROOT)LHCにおける素粒子ビッグデータの解析とROOTライブラリ(Big Data Analysis at LHC and ROOT)
LHCにおける素粒子ビッグデータの解析とROOTライブラリ(Big Data Analysis at LHC and ROOT)
 
PyData Tokyo Tutorial & Hackathon #1
PyData Tokyo Tutorial & Hackathon #1PyData Tokyo Tutorial & Hackathon #1
PyData Tokyo Tutorial & Hackathon #1
 
20150128 cross2015
20150128 cross201520150128 cross2015
20150128 cross2015
 
20141127 py datatokyomeetup2
20141127 py datatokyomeetup220141127 py datatokyomeetup2
20141127 py datatokyomeetup2
 
The LHC Explained by CNN
The LHC Explained by CNNThe LHC Explained by CNN
The LHC Explained by CNN
 
LHC for Students
LHC for StudentsLHC for Students
LHC for Students
 
Analysis Software Development
Analysis Software DevelopmentAnalysis Software Development
Analysis Software Development
 

Último

Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Lokesh Kothari
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSSLeenakshiTyagi
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPirithiRaju
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)Areesha Ahmad
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​kaibalyasahoo82800
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencySheetal Arora
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTSérgio Sacani
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsAArockiyaNisha
 
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxPhysiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxAArockiyaNisha
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...Sérgio Sacani
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRDelhi Call girls
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisDiwakar Mishra
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfSumit Kumar yadav
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxgindu3009
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfSumit Kumar yadav
 
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.Nitya salvi
 

Último (20)

Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSS
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOST
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based Nanomaterials
 
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxPhysiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdf
 
The Philosophy of Science
The Philosophy of ScienceThe Philosophy of Science
The Philosophy of Science
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdf
 
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
 

PyData NYC by Akira Shibata

  • 1. Putting Together World's Best Data Processing Research with Python Copyright 2014 Shiroyagi Corporation. All rights reserved. Akira Shibata, PhD Shiroyagi Corporation
  • 2. Who am I Akira Shibata, PhD. TW: @punkphysicist CEO, Shiroyagi Corporation (shiroyagi.co.jp) Kamelio: Personalised News Curation Kamect: Contents Discovery Platform 2004 - 2010: Data Scientist @ NYU Statistical data modelling @ LHC, CERN 2010 - 2013 Boston Consulting Group Copyright 2014 Shiroyagi Corporation. All rights reserved. 2
  • 3. Copyright 2014 Shiroyagi Corporation. All rights reserved. 3
  • 4. Statistical modelling of Physics data Confirmatory: Highly theory driven model building Copyright 2014 Shiroyagi Corporation. All rights reserved. 4
  • 5. Telling discovery from noise The model tells you the expected uncertainty Copyright 2014 Shiroyagi Corporation. All rights reserved. 5
  • 6. Copyright 2014 Shiroyagi Corporation. All rights reserved. 6
  • 7. Copyright 2014 Shiroyagi Corporation. All rights reserved. 7
  • 8. Copyright 2014 Shiroyagi Corporation. All rights reserved. 8
  • 9. Copyright 2014 Shiroyagi Corporation. All rights reserved. 9
  • 10. Copyright 2014 Shiroyagi Corporation. All rights reserved. 10
  • 11. Kamelio “Deep Learning” “Internet of Things” “Medical IT” “Global Strategy” Collects news through >3M topics to chose from Copyright 2014 Shiroyagi Corporation. All rights reserved. 11
  • 12. 3 “Cats” “Anime” “Cats reaction to sighting dogs for the first time” Copyright 2014 Shiroyagi Corporation. All rights reserved. 12
  • 13. Python puts all our tools together Image in Detect regions Object recog. Scoring Cropping 0 1 2 3 4 Matlab +Scipy C++ +Libraries Numpy PIL IPython and Python script Copyright 2014 Shiroyagi Corporation. All rights reserved. 13
  • 14. Our approach is heavily influenced by Berkeley Vision and Learning Center Acknowledgement Copyright 2014 Shiroyagi Corporation. All rights reserved. 14
  • 15. Detect regions 0 1 2 3 4 Copyright 2014 Shiroyagi Corporation. All rights reserved. 15
  • 16. Region detection: Telling where to look at How do we find regions to feed into object recognition? Default strategy was to look at the center 1 Copyright 2014 Shiroyagi Corporation. All rights reserved. 16
  • 17. Exhaustive windows -> segmentation Search over position, scale, aspect ratio Grouping parts of image at different scales Exhaustive search far too time inefficient for use with Deep Learning 1 Copyright 2014 Shiroyagi Corporation. All rights reserved. 17
  • 18. 1 Region detection: in practice Install Malab and Selective Search algorithm from author Run matlab as subprocess pid = subprocess.Popen(shlex.split(mc), stdout=open('/dev/null', 'w'), cwd=script_dirname) matlab -nojvm -r "try; selective_search({‘image_file.jpg’}, ‘output.mat'); catch; exit; end; exit” 1 2 3 Import output using scipy.io all_boxes = list(scipy.io.loadmat(‘output.mat')['all_boxes'][0]) subtractor = np.array((1, 1, 0, 0))[np.newaxis, :] all_boxes = [boxes - subtractor for boxes in all_boxes] Copyright 2014 Shiroyagi Corporation. All rights reserved. 18
  • 19. 1 Region detection: proposals generated ~200 proposals generated per image Copyright 2014 Shiroyagi Corporation. All rights reserved. 19
  • 20. Object recog. 0 1 2 3 4 Copyright 2014 Shiroyagi Corporation. All rights reserved. 20
  • 21. Object recognition Deep blue beat Kasparov at chess in 1997… 2 Copyright 2014 Shiroyagi Corporation. All rights reserved. 21
  • 22. 2 Deep Learning: Damn good at it Copyright 2014 Shiroyagi Corporation. All rights reserved. 22
  • 23. 2 Convoluted Neural Network … Copyright 2014 Shiroyagi Corporation. All rights reserved. 23
  • 24. Caffe: open R-CNN framework under rapid dev. C++/CUDA with Python wrapper 2 Copyright 2014 Shiroyagi Corporation. All rights reserved. 24
  • 25. Pre-trained models published We used 200-category object recog. model developed for 2013 ImageNet Challenge 2 Copyright 2014 Shiroyagi Corporation. All rights reserved. 25
  • 26. 2 Object recognition: in practice Install a bunch of libraries and Caffe CUDA, Boost, OpenCV, BLAS… Import wrapper and configure MODEL_FILE=‘models/bvlc_…_ilsvrc13/deploy.prototxt’ PRETRAINED_FILE = ‘models/…/bvlc_…_ilsvrc13.caffemodel’ MEAN_FILE = 'caffe/imagenet/ilsvrc_2012_mean.npy' detector = caffe.Detector(MODEL_FILE, PRETRAINED_FILE, mean=np.load(MEAN_FILE), raw_scale=255, channel_swap=[2,1,0]) 1 2 3 Pass found regions for object detection self.detect_windows(zip(image_fnames, windows_list)) Copyright 2014 Shiroyagi Corporation. All rights reserved. 26
  • 27. 2 Object recognition: Result Obj Score 0 domestic cat 1.03649377823 1 domestic cat 0.0617411136627 2 domestic cat -0.097744345665 3 domestic cat -0.738470971584 4 chair -0.988844156265 5 skunk -0.999914288521 6 tv or monitor -1.00460898876 7 rubber eraser -1.01068615913 8 chair -1.04896986485 9 rubber eraser -1.09035253525 10 band aid -1.09691572189 Takes minutes to detect all windows Copyright 2014 Shiroyagi Corporation. All rights reserved. 27
  • 28. 2 Object recognition: Result Obj Score 0 person 0.126184225082 1 person 0.0311727523804 2 person -0.0777613520622 3 neck brace -0.39757412672 4 person -0.415030777454 5 drum -0.421649754047 6 neck brace -0.481261610985 7 tie -0.649109125137 8 neck brace -0.719438135624 9 face powder -0.789100408554 10 face powder -0.838757038116 Copyright 2014 Shiroyagi Corporation. All rights reserved. 28
  • 29. Scoring 0 1 2 3 4 Copyright 2014 Shiroyagi Corporation. All rights reserved. 29
  • 30. 3 Scoring 1 For every pixel, sum up score from all detections for i in xrange(len(detec0ons)): arr[ymin:ymax, xmin:xmax] += math.exp(score) Copyright 2014 Shiroyagi Corporation. All rights reserved. 30
  • 31. Score heatmap We used 200-cat object recognition model developed for 2013 ImageNet Challenge 3 Copyright 2014 Shiroyagi Corporation. All rights reserved. 31
  • 32. Cropping 0 1 2 3 4 Copyright 2014 Shiroyagi Corporation. All rights reserved. 32
  • 33. 4 Cropping Generate all possible crop areas while y+hws <= h: while x+hws <= w: window_locs = np.vstack((window_locs, [x, y, x+hws, y+hws])) Find the crop that encloses the highest point of interest in the centre for i, window_loc in enumerate(window_locs): x1, y1, x2, y2 = window_loc if max_val != np.max(arr_con[y1:y2, x1:x2]): scores[i]=np.nan else: scores[i] = ((x1+x2)/2.-­‐xp)**2+ ((y1+y2)/2.-­‐yp)**2 1 2 3 Crop and save! img_pil = Image.open(fn) crop_area=map(lambda x: int(x), window_locs[scores.argmax()]) img_crop = img_pil.crop(crop_area) Copyright 2014 Shiroyagi Corporation. All rights reserved. 33
  • 34. 4 Finally Copyright 2014 Shiroyagi Corporation. All rights reserved. 34
  • 35. Future improvements Fast face/human detection Aspect detection: square or rectangle? Object weighting Magnification Unseen object Copyright 2014 Shiroyagi Corporation. All rights reserved. 35