SlideShare ist ein Scribd-Unternehmen logo

Object Detection with Tensorflow

•Als PPTX, PDF herunterladen•
•
ElifTech
ElifTech

The main things you need to know about Object Detection with Tensorflow by Anatolii Shkurpylo

Software
1 von 26
Object Detection with Tensorflow by Anatolii Shkurpylo, Software Developer
www.eliftech.com Agenda ▪ Intro ▪ What is Object Detection ▪ State of Object Detection ▪ Tensorflow Object Detection API ▪ Preparing Data ▪ Training & Evaluating ▪ Links
www.eliftech.com Intro
www.eliftech.com Use cases
www.eliftech.com What is Object Detection
www.eliftech.com Object detection = Object Classification + Object Localization
www.eliftech.com One model for two tasks? Object detection - output is the one number (index) of a class Object localization - output is the four numbers - coordinates of bounding box. Po bx1 bx2 by1 by2 c1 c2 c3 … cn - is object exists - bounding box coordinates - object’s variables
www.eliftech.com State of Object Detection
www.eliftech.com Approaches ▪ Classical approach (Haar features) - first OD real time framework (Viola-Jones) ▪ Deep learning approach - now state of the art in OD ▪ OverFeat ▪ R-CNN ▪ Fast R-CNN ▪ YOLO ▪ Faster R-CNN ▪ SSD and R-FCN
www.eliftech.com Deep learning approach OverFeat - published in 2013, multi-scale sliding window algorithm using Convolutional Neural Networks (CNNs). R-CNN - Regions with CNN features. Three stage approach: - Extract possible objects using a region proposal method (the most popular one being Selective Search). - Extract features from each region using a CNN. - Classify each region with SVMs.
www.eliftech.com Fast R-CNN - Similar to R-CNN, it used Selective Search to generate object proposals, but instead of extracting all of them independently and using SVM classifiers, it applied the CNN on the complete image and then used both Region of Interest (RoI) Pooling on the feature map with a final feed forward network for classification and regression. YOLO - You Only Look Once: a simple convolutional neural network approach which has both great results and high speed, allowing for the first time real time object detection. Deep learning approach
www.eliftech.com Faster R-CNN - Faster R-CNN added what they called a Region Proposal Network (RPN), in an attempt to get rid of the Selective Search algorithm and make the model completely trainable end-to-end. SSD and R-FCN Finally, there are two notable papers, Single Shot Detector (SSD) which takes on YOLO by using multiple sized convolutional feature maps achieving better results and speed, and Region-based Fully Convolutional Networks (R-FCN) which takes the architecture of Faster R-CNN but with only convolutional networks. Deep learning approach
www.eliftech.com Tensorflow Object Detection API
www.eliftech.com TF Object Detection API ▪ Open Source from 2017-07-15 ▪ Built on top of TensorFlow ▪ Contains trainable detection models ▪ Contains frozen weights ▪ Contains Jupyter Notebook ▪ Makes easy to construct, train and deploy object detection models
www.eliftech.com Getting started ▪ Protobuf 2.6 ▪ Python-tk ▪ Pillow 1.0 ▪ lxml ▪ Tf Slim (included) ▪ Jupyter notebook ▪ Matplotlib ▪ Tensorflow (tensorflow- gpu) ▪ Cython ▪ cocoapi Dependencies: If model will be trained locally - better to install tensorflow-gpu. Dependencies for tensorflow-gpu: ▪ NVIDIA GPU with CUDA Compute Capability 3.0 (list) ▪ Ubuntu 16.04 at least ▪ CUDA® Toolkit 9.0 ▪ NVIDIA drivers associated with CUDA Toolkit 9.0. ▪ cuDNN v7.0 ▪ libcupti-dev Installation instruction Installation instruction Latest version of CUDA Toolkit - 9.1 not compatible with tensorflow 1.6, need to install 9.0
www.eliftech.com Creating a dataset
www.eliftech.com Dataset ▪ Tensorflow Object Detection API uses the TFRecord file format ▪ There is available third-party scripts to convert PASCAL VOC and Oxford Pet Format ▪ In other case explanation of format available in git repo. ▪ Input data to create TFRecord - annotated image
www.eliftech.com Getting images Grab from internet ▪ Scrap images from google or Pixabay or whatever ▪ For batch downloading - Faktun Bulk Image Downloader ▪ For data mining by multiplying existing images - ImageMagic Create own images ▪ Record video with needed object/objects (in 640x480) ▪ Process video and split on screenshots - ffmpeg Tips ▪ Create images with different lights, background and so on. ▪ If object is able to have different forms - better to catch them all. ▪ Try to make 30%-50% of images with overlaid object ▪ Tool for image augmentation
www.eliftech.com Labeling (Annotation) an images Tools ▪ LabelImg ▪ FIAT (Fast Image Data Annotation Tool) ▪ input: images ▪ output: .xml files with bounding boxes coordinates
www.eliftech.com Creating TFRecord ▪ Tensorflow object detection API repo contains folder dataset_tools with scripts to coverts common structures of data in TFRecord. ▪ If output data has another structure - here is explanation how to convert it
www.eliftech.com Training
www.eliftech.com Selecting a model Tensorflow OD API provides a collection of detection models pre-trained on the COCO dataset, the Kitti dataset, and the Open Images dataset. - model name corresponds to a config file that was used to train this model. - speed - running time in ms per 600x600 image - mAP stands for mean average precision, which indicates how well the model performed on the COCO dataset. - Outputs types (Boxes, and Masks if applicable)
www.eliftech.com Configuring ● label.pbtx ● pipeline.config train_config: { fine_tune_checkpoint: "<path_to_model.ckpt>" num_steps: 200000 } train_input_reader { label_map_path: "<path_to_labels.pbtxt>" tf_record_input_reader { input_path: "<path_to_train.record>" } } eval_config { num_examples: 8000 max_evals: 10 use_moving_averages: false } eval_input_reader { label_map_path: "<path_to_labels.pbtxt>" shuffle: false num_readers: 1 tf_record_input_reader { input_path: "<path_to_test.record>" } } ● Folders structure instruction
www.eliftech.com Training & Evaluating # From the tensorflow/models/research directory python object_detection/eval.py --logtostderr --pipeline_config_path=${PATH_TO_YOUR_PIPELINE_CONFIG} --checkpoint_dir=${PATH_TO_TRAIN_DIR} --eval_dir=${PATH_TO_EVAL_DIR} # From the tensorflow/models/research directory python object_detection/train.py --logtostderr -- pipeline_config_path=/tensorflow/models/object_detection/samples/configs/ssd_mobilenet_v1_p ets.config --train_dir=${PATH_TO_ROOT_TRAIN_FOLDER}
www.eliftech.com Links ▪ https://towardsdatascience.com/how-to-train-your-own-object-detector-with- tensorflows-object-detector-api-bec72ecfe1d9 ▪ https://www.kdnuggets.com/2017/10/deep-learning-object-detection- comprehensive-review.html ▪ http://www.machinelearninguru.com/deep_learning/tensorflow/basics/tfrecord/tfreco rd.html ▪ https://www.coursera.org/learn/convolutional-neural-networks ▪ https://medium.com/comet-app/review-of-deep-learning-algorithms-for-object- detection-c1f3d437b852 ▪ https://towardsdatascience.com/evolution-of-object-detection-and-localization- algorithms-e241021d8bad ▪ https://medium.freecodecamp.org/how-to-play-quidditch-using-the-tensorflow- object-detection-api-b0742b99065d
www.eliftech.com Don’t forget to subscribe! Find us at eliftech.com Have a question? Contact us: info@eliftech.com

Empfohlen

Object detection with Tensorflow Api
Object detection with Tensorflow ApiObject detection with Tensorflow Api
Object detection with Tensorflow ApiArwinKhan1
 
TensorFlow Object Detection API
TensorFlow Object Detection APITensorFlow Object Detection API
TensorFlow Object Detection APIAlgoscale Technologies Inc.
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learningSushant Shrivastava
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detectionBrodmann17
 
Moving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNNMoving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNNNITISHKUMAR1401
 
TensorFlow Object Detection | Realtime Object Detection with TensorFlow | Ten...
TensorFlow Object Detection | Realtime Object Detection with TensorFlow | Ten...TensorFlow Object Detection | Realtime Object Detection with TensorFlow | Ten...
TensorFlow Object Detection | Realtime Object Detection with TensorFlow | Ten...Edureka!
 
Object detection
Object detectionObject detection
Object detectionJksuryawanshi
 
Object tracking presentation
Object tracking presentationObject tracking presentation
Object tracking presentationMrsShwetaBanait1
 

Empfohlen

Object detection with Tensorflow Api
Object detection with Tensorflow ApiObject detection with Tensorflow Api
Object detection with Tensorflow ApiArwinKhan1
 
TensorFlow Object Detection API
TensorFlow Object Detection APITensorFlow Object Detection API
TensorFlow Object Detection APIAlgoscale Technologies Inc.
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learningSushant Shrivastava
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detectionBrodmann17
 
Moving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNNMoving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNNNITISHKUMAR1401
 
TensorFlow Object Detection | Realtime Object Detection with TensorFlow | Ten...
TensorFlow Object Detection | Realtime Object Detection with TensorFlow | Ten...TensorFlow Object Detection | Realtime Object Detection with TensorFlow | Ten...
TensorFlow Object Detection | Realtime Object Detection with TensorFlow | Ten...Edureka!
 
Object detection
Object detectionObject detection
Object detectionJksuryawanshi
 
Object tracking presentation
Object tracking presentationObject tracking presentation
Object tracking presentationMrsShwetaBanait1
 
Moving object detection in video surveillance
Moving object detection in video surveillanceMoving object detection in video surveillance
Moving object detection in video surveillanceAshfaqul Haque John
 
Object Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksObject Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksUsman Qayyum
 
Yolo
YoloYolo
YoloSourav Garai
 
You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)Universitat Politècnica de Catalunya
 
Face recognition using artificial neural network
Face recognition using artificial neural networkFace recognition using artificial neural network
Face recognition using artificial neural networkSumeet Kakani
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkNader Karimi
 
Deep learning based object detection basics
Deep learning based object detection basicsDeep learning based object detection basics
Deep learning based object detection basicsBrodmann17
 
Object tracking
Object trackingObject tracking
Object trackingSri vidhya k
 
You Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionYou Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionDADAJONJURAKUZIEV
 
Tutorial on Object Detection (Faster R-CNN)
Tutorial on Object Detection (Faster R-CNN)Tutorial on Object Detection (Faster R-CNN)
Tutorial on Object Detection (Faster R-CNN)Hwa Pyung Kim
 
Deep learning for object detection
Deep learning for object detectionDeep learning for object detection
Deep learning for object detectionWenjing Chen
 
Object detection and Instance Segmentation
Object detection and Instance SegmentationObject detection and Instance Segmentation
Object detection and Instance SegmentationHichem Felouat
 
Object detection
Object detectionObject detection
Object detectionSomesh Vyas
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesFellowship at Vodafone FutureLab
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksChristian Perone
 
YOLO
YOLOYOLO
YOLOgeothomas18
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & TrackingAkshay Gujarathi
 
Deep learning
Deep learning Deep learning
Deep learning Rajgupta258
 
Object detection
Object detectionObject detection
Object detectionROUSHAN RAJ KUMAR
 
Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural networkSmriti Tikoo
 
odtslide-180529073940.pptx
odtslide-180529073940.pptxodtslide-180529073940.pptx
odtslide-180529073940.pptxahmedchammam
 
S. Bartoli & F. Pompermaier – A Semantic Big Data Companion
S. Bartoli & F. Pompermaier – A Semantic Big Data CompanionS. Bartoli & F. Pompermaier – A Semantic Big Data Companion
S. Bartoli & F. Pompermaier – A Semantic Big Data CompanionFlink Forward
 

Weitere ähnliche Inhalte

Was ist angesagt?

Moving object detection in video surveillance
Moving object detection in video surveillanceMoving object detection in video surveillance
Moving object detection in video surveillanceAshfaqul Haque John
 
Object Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksObject Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksUsman Qayyum
 
You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)Universitat Politècnica de Catalunya
 
Face recognition using artificial neural network
Face recognition using artificial neural networkFace recognition using artificial neural network
Face recognition using artificial neural networkSumeet Kakani
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkNader Karimi
 
Deep learning based object detection basics
Deep learning based object detection basicsDeep learning based object detection basics
Deep learning based object detection basicsBrodmann17
 
You Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionYou Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionDADAJONJURAKUZIEV
 
Tutorial on Object Detection (Faster R-CNN)
Tutorial on Object Detection (Faster R-CNN)Tutorial on Object Detection (Faster R-CNN)
Tutorial on Object Detection (Faster R-CNN)Hwa Pyung Kim
 
Deep learning for object detection
Deep learning for object detectionDeep learning for object detection
Deep learning for object detectionWenjing Chen
 
Object detection and Instance Segmentation
Object detection and Instance SegmentationObject detection and Instance Segmentation
Object detection and Instance SegmentationHichem Felouat
 
Object detection
Object detectionObject detection
Object detectionSomesh Vyas
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesFellowship at Vodafone FutureLab
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksChristian Perone
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & TrackingAkshay Gujarathi
 
Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural networkSmriti Tikoo
 

Was ist angesagt? (20)

Moving object detection in video surveillance
Moving object detection in video surveillanceMoving object detection in video surveillance
Moving object detection in video surveillance
 
Object Detection using Deep Neural Networks
Object Detection using Deep Neural NetworksObject Detection using Deep Neural Networks
Object Detection using Deep Neural Networks
 
Yolo
YoloYolo
Yolo
 
You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)
 
Face recognition using artificial neural network
Face recognition using artificial neural networkFace recognition using artificial neural network
Face recognition using artificial neural network
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning Framework
 
Deep learning based object detection basics
Deep learning based object detection basicsDeep learning based object detection basics
Deep learning based object detection basics
 
Object tracking
Object trackingObject tracking
Object tracking
 
You Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionYou Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object Detection
 
Tutorial on Object Detection (Faster R-CNN)
Tutorial on Object Detection (Faster R-CNN)Tutorial on Object Detection (Faster R-CNN)
Tutorial on Object Detection (Faster R-CNN)
 
Deep learning for object detection
Deep learning for object detectionDeep learning for object detection
Deep learning for object detection
 
Object detection and Instance Segmentation
Object detection and Instance SegmentationObject detection and Instance Segmentation
Object detection and Instance Segmentation
 
Object detection
Object detectionObject detection
Object detection
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network Approaches
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
 
YOLO
YOLOYOLO
YOLO
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & Tracking
 
Deep learning
Deep learning Deep learning
Deep learning
 
Object detection
Object detectionObject detection
Object detection
 
Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural network
 

Ähnlich wie Object Detection with Tensorflow

odtslide-180529073940.pptx
odtslide-180529073940.pptxodtslide-180529073940.pptx
odtslide-180529073940.pptxahmedchammam
 
S. Bartoli & F. Pompermaier – A Semantic Big Data Companion
S. Bartoli & F. Pompermaier – A Semantic Big Data CompanionS. Bartoli & F. Pompermaier – A Semantic Big Data Companion
S. Bartoli & F. Pompermaier – A Semantic Big Data CompanionFlink Forward
 
Mastering Terraform and the Provider for OCI
Mastering Terraform and the Provider for OCIMastering Terraform and the Provider for OCI
Mastering Terraform and the Provider for OCIGregory GUILLOU
 
Building a Knowledge Graph using NLP and Ontologies
Building a Knowledge Graph using NLP and OntologiesBuilding a Knowledge Graph using NLP and Ontologies
Building a Knowledge Graph using NLP and OntologiesNeo4j
 
502021435-12345678Minor-Project-Ppt.pptx
502021435-12345678Minor-Project-Ppt.pptx502021435-12345678Minor-Project-Ppt.pptx
502021435-12345678Minor-Project-Ppt.pptxshrey4922
 
O365Engage17 - How to Automate SharePoint Provisioning with PNP Framework
O365Engage17 - How to Automate SharePoint Provisioning with PNP FrameworkO365Engage17 - How to Automate SharePoint Provisioning with PNP Framework
O365Engage17 - How to Automate SharePoint Provisioning with PNP FrameworkNCCOMMS
 
Online Security Analytics on Large Scale Video Surveillance System by Yu Cao ...
Online Security Analytics on Large Scale Video Surveillance System by Yu Cao ...Online Security Analytics on Large Scale Video Surveillance System by Yu Cao ...
Online Security Analytics on Large Scale Video Surveillance System by Yu Cao ...Spark Summit
 
ifcOWL - An ontology for building data
ifcOWL - An ontology for building dataifcOWL - An ontology for building data
ifcOWL - An ontology for building dataLD4SC
 
Big Data and Machine Learning with FIWARE
Big Data and Machine Learning with FIWAREBig Data and Machine Learning with FIWARE
Big Data and Machine Learning with FIWAREFernando Lopez Aguilar
 
Suneel Marthi - Deep Learning with Apache Flink and DL4J
Suneel Marthi - Deep Learning with Apache Flink and DL4JSuneel Marthi - Deep Learning with Apache Flink and DL4J
Suneel Marthi - Deep Learning with Apache Flink and DL4JFlink Forward
 
How to NLProc from .NET
How to NLProc from .NETHow to NLProc from .NET
How to NLProc from .NETSergey Tihon
 
ADS Team 8 Final Presentation
ADS Team 8 Final PresentationADS Team 8 Final Presentation
ADS Team 8 Final PresentationPranay Mankad
 
Constrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiConstrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiIvo Andreev
 
Transfer learning, active learning using tensorflow object detection api
Transfer learning, active learning using tensorflow object detection apiTransfer learning, active learning using tensorflow object detection api
Transfer learning, active learning using tensorflow object detection api설기 김
 
Autonomous Machines with Project Bonsai
Autonomous Machines with Project BonsaiAutonomous Machines with Project Bonsai
Autonomous Machines with Project BonsaiIvo Andreev
 
Machine Learning Platform in LINE Fukuoka
Machine Learning Platform in LINE FukuokaMachine Learning Platform in LINE Fukuoka
Machine Learning Platform in LINE FukuokaLINE Corporation
 
Deep Learning: DL4J and DataVec
Deep Learning: DL4J and DataVecDeep Learning: DL4J and DataVec
Deep Learning: DL4J and DataVecJosh Patterson
 

Ähnlich wie Object Detection with Tensorflow (20)

odtslide-180529073940.pptx
odtslide-180529073940.pptxodtslide-180529073940.pptx
odtslide-180529073940.pptx
 
S. Bartoli & F. Pompermaier – A Semantic Big Data Companion
S. Bartoli & F. Pompermaier – A Semantic Big Data CompanionS. Bartoli & F. Pompermaier – A Semantic Big Data Companion
S. Bartoli & F. Pompermaier – A Semantic Big Data Companion
 
Icpp power ai-workshop 2018
Icpp power ai-workshop 2018Icpp power ai-workshop 2018
Icpp power ai-workshop 2018
 
Mastering Terraform and the Provider for OCI
Mastering Terraform and the Provider for OCIMastering Terraform and the Provider for OCI
Mastering Terraform and the Provider for OCI
 
Building a Knowledge Graph using NLP and Ontologies
Building a Knowledge Graph using NLP and OntologiesBuilding a Knowledge Graph using NLP and Ontologies
Building a Knowledge Graph using NLP and Ontologies
 
502021435-12345678Minor-Project-Ppt.pptx
502021435-12345678Minor-Project-Ppt.pptx502021435-12345678Minor-Project-Ppt.pptx
502021435-12345678Minor-Project-Ppt.pptx
 
O365Engage17 - How to Automate SharePoint Provisioning with PNP Framework
O365Engage17 - How to Automate SharePoint Provisioning with PNP FrameworkO365Engage17 - How to Automate SharePoint Provisioning with PNP Framework
O365Engage17 - How to Automate SharePoint Provisioning with PNP Framework
 
Online Security Analytics on Large Scale Video Surveillance System by Yu Cao ...
Online Security Analytics on Large Scale Video Surveillance System by Yu Cao ...Online Security Analytics on Large Scale Video Surveillance System by Yu Cao ...
Online Security Analytics on Large Scale Video Surveillance System by Yu Cao ...
 
20220811 - computer vision
20220811 - computer vision20220811 - computer vision
20220811 - computer vision
 
ifcOWL - An ontology for building data
ifcOWL - An ontology for building dataifcOWL - An ontology for building data
ifcOWL - An ontology for building data
 
Big Data and Machine Learning with FIWARE
Big Data and Machine Learning with FIWAREBig Data and Machine Learning with FIWARE
Big Data and Machine Learning with FIWARE
 
Suneel Marthi - Deep Learning with Apache Flink and DL4J
Suneel Marthi - Deep Learning with Apache Flink and DL4JSuneel Marthi - Deep Learning with Apache Flink and DL4J
Suneel Marthi - Deep Learning with Apache Flink and DL4J
 
How to NLProc from .NET
How to NLProc from .NETHow to NLProc from .NET
How to NLProc from .NET
 
ADS Team 8 Final Presentation
ADS Team 8 Final PresentationADS Team 8 Final Presentation
ADS Team 8 Final Presentation
 
Constrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiConstrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project Bonsai
 
CV machine learning freelancer
CV machine learning freelancerCV machine learning freelancer
CV machine learning freelancer
 
Transfer learning, active learning using tensorflow object detection api
Transfer learning, active learning using tensorflow object detection apiTransfer learning, active learning using tensorflow object detection api
Transfer learning, active learning using tensorflow object detection api
 
Autonomous Machines with Project Bonsai
Autonomous Machines with Project BonsaiAutonomous Machines with Project Bonsai
Autonomous Machines with Project Bonsai
 
Machine Learning Platform in LINE Fukuoka
Machine Learning Platform in LINE FukuokaMachine Learning Platform in LINE Fukuoka
Machine Learning Platform in LINE Fukuoka
 
Deep Learning: DL4J and DataVec
Deep Learning: DL4J and DataVecDeep Learning: DL4J and DataVec
Deep Learning: DL4J and DataVec
 

Mehr von ElifTech

Go Concurrency Patterns
Go Concurrency PatternsGo Concurrency Patterns
Go Concurrency PatternsElifTech
 
Go Concurrency Basics
Go Concurrency Basics Go Concurrency Basics
Go Concurrency Basics ElifTech
 
Domain Logic Patterns
Domain Logic PatternsDomain Logic Patterns
Domain Logic PatternsElifTech
 
Dive into .Net Core framework
Dive into .Net Core framework Dive into .Net Core framework
Dive into .Net Core framework ElifTech
 
VR digest. August 2018
VR digest. August 2018VR digest. August 2018
VR digest. August 2018ElifTech
 
JS digest. July 2018
JS digest. July 2018JS digest. July 2018
JS digest. July 2018ElifTech
 
VR digest. July 2018
VR digest. July 2018VR digest. July 2018
VR digest. July 2018ElifTech
 
IoT digest. July 2018
IoT digest. July 2018IoT digest. July 2018
IoT digest. July 2018ElifTech
 
VR digest. June 2018
VR digest. June 2018VR digest. June 2018
VR digest. June 2018ElifTech
 
IoT digest. June 2018
IoT digest. June 2018IoT digest. June 2018
IoT digest. June 2018ElifTech
 
IoT digest. May 2018
IoT digest. May 2018IoT digest. May 2018
IoT digest. May 2018ElifTech
 
VR digest. May 2018
VR digest. May 2018VR digest. May 2018
VR digest. May 2018ElifTech
 
Polymer: brief introduction
Polymer: brief introduction Polymer: brief introduction
Polymer: brief introduction ElifTech
 
JS digest. April 2018
JS digest. April 2018JS digest. April 2018
JS digest. April 2018ElifTech
 
VR digest. April, 2018
VR digest. April, 2018 VR digest. April, 2018
VR digest. April, 2018 ElifTech
 
IoT digest. April 2018
IoT digest. April 2018IoT digest. April 2018
IoT digest. April 2018ElifTech
 
IoT digest. March 2018
IoT digest. March 2018IoT digest. March 2018
IoT digest. March 2018ElifTech
 
VR digest. March, 2018
VR digest. March, 2018VR digest. March, 2018
VR digest. March, 2018ElifTech
 
VR digest. February, 2018
VR digest. February, 2018VR digest. February, 2018
VR digest. February, 2018ElifTech
 
IoT digest. February 2018
IoT digest. February 2018IoT digest. February 2018
IoT digest. February 2018ElifTech
 

Mehr von ElifTech (20)

Go Concurrency Patterns
Go Concurrency PatternsGo Concurrency Patterns
Go Concurrency Patterns
 
Go Concurrency Basics
Go Concurrency Basics Go Concurrency Basics
Go Concurrency Basics
 
Domain Logic Patterns
Domain Logic PatternsDomain Logic Patterns
Domain Logic Patterns
 
Dive into .Net Core framework
Dive into .Net Core framework Dive into .Net Core framework
Dive into .Net Core framework
 
VR digest. August 2018
VR digest. August 2018VR digest. August 2018
VR digest. August 2018
 
JS digest. July 2018
JS digest. July 2018JS digest. July 2018
JS digest. July 2018
 
VR digest. July 2018
VR digest. July 2018VR digest. July 2018
VR digest. July 2018
 
IoT digest. July 2018
IoT digest. July 2018IoT digest. July 2018
IoT digest. July 2018
 
VR digest. June 2018
VR digest. June 2018VR digest. June 2018
VR digest. June 2018
 
IoT digest. June 2018
IoT digest. June 2018IoT digest. June 2018
IoT digest. June 2018
 
IoT digest. May 2018
IoT digest. May 2018IoT digest. May 2018
IoT digest. May 2018
 
VR digest. May 2018
VR digest. May 2018VR digest. May 2018
VR digest. May 2018
 
Polymer: brief introduction
Polymer: brief introduction Polymer: brief introduction
Polymer: brief introduction
 
JS digest. April 2018
JS digest. April 2018JS digest. April 2018
JS digest. April 2018
 
VR digest. April, 2018
VR digest. April, 2018 VR digest. April, 2018
VR digest. April, 2018
 
IoT digest. April 2018
IoT digest. April 2018IoT digest. April 2018
IoT digest. April 2018
 
IoT digest. March 2018
IoT digest. March 2018IoT digest. March 2018
IoT digest. March 2018
 
VR digest. March, 2018
VR digest. March, 2018VR digest. March, 2018
VR digest. March, 2018
 
VR digest. February, 2018
VR digest. February, 2018VR digest. February, 2018
VR digest. February, 2018
 
IoT digest. February 2018
IoT digest. February 2018IoT digest. February 2018
IoT digest. February 2018
 

Kürzlich hochgeladen

Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...OnePlan Solutions
 
OpenChain Education Work Group Monthly Meeting - 2024-04-10 - Full Recording
OpenChain Education Work Group Monthly Meeting - 2024-04-10 - Full RecordingOpenChain Education Work Group Monthly Meeting - 2024-04-10 - Full Recording
OpenChain Education Work Group Monthly Meeting - 2024-04-10 - Full RecordingShane Coughlan
 
eSoftTools IMAP Backup Software and migration tools
eSoftTools IMAP Backup Software and migration toolseSoftTools IMAP Backup Software and migration tools
eSoftTools IMAP Backup Software and migration toolsosttopstonverter
 
Alfresco TTL#157 - Troubleshooting Made Easy: Deciphering Alfresco mTLS Confi...
Alfresco TTL#157 - Troubleshooting Made Easy: Deciphering Alfresco mTLS Confi...Alfresco TTL#157 - Troubleshooting Made Easy: Deciphering Alfresco mTLS Confi...
Alfresco TTL#157 - Troubleshooting Made Easy: Deciphering Alfresco mTLS Confi...Angel Borroy López
 
Comparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdfComparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdfDrew Moseley
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsSafe Software
 
Osi security architecture in network.pptx
Osi security architecture in network.pptxOsi security architecture in network.pptx
Osi security architecture in network.pptxVinzoCenzo
 
How to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion ApplicationHow to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion ApplicationBradBedford3
 
Machine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their EngineeringMachine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their EngineeringHironori Washizaki
 
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...OnePlan Solutions
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Cizo Technology Services
 
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdfExploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdfkalichargn70th171
 
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptxThe Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptxRTS corp
 
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptxReal-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptxRTS corp
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtimeandrehoraa
 
UI5ers live - Custom Controls wrapping 3rd-party libs.pptx
UI5ers live - Custom Controls wrapping 3rd-party libs.pptxUI5ers live - Custom Controls wrapping 3rd-party libs.pptx
UI5ers live - Custom Controls wrapping 3rd-party libs.pptxAndreas Kunz
 
Sending Calendar Invites on SES and Calendarsnack.pdf
Sending Calendar Invites on SES and Calendarsnack.pdfSending Calendar Invites on SES and Calendarsnack.pdf
Sending Calendar Invites on SES and Calendarsnack.pdf31events.com
 
What’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 UpdatesWhat’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 UpdatesVictoriaMetrics
 
Leveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + KobitonLeveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + KobitonApplitools
 
Amazon Bedrock in Action - presentation of the Bedrock's capabilities
Amazon Bedrock in Action - presentation of the Bedrock's capabilitiesAmazon Bedrock in Action - presentation of the Bedrock's capabilities
Amazon Bedrock in Action - presentation of the Bedrock's capabilitiesKrzysztofKkol1
 

Kürzlich hochgeladen (20)

Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
 
OpenChain Education Work Group Monthly Meeting - 2024-04-10 - Full Recording
OpenChain Education Work Group Monthly Meeting - 2024-04-10 - Full RecordingOpenChain Education Work Group Monthly Meeting - 2024-04-10 - Full Recording
OpenChain Education Work Group Monthly Meeting - 2024-04-10 - Full Recording
 
eSoftTools IMAP Backup Software and migration tools
eSoftTools IMAP Backup Software and migration toolseSoftTools IMAP Backup Software and migration tools
eSoftTools IMAP Backup Software and migration tools
 
Alfresco TTL#157 - Troubleshooting Made Easy: Deciphering Alfresco mTLS Confi...
Alfresco TTL#157 - Troubleshooting Made Easy: Deciphering Alfresco mTLS Confi...Alfresco TTL#157 - Troubleshooting Made Easy: Deciphering Alfresco mTLS Confi...
Alfresco TTL#157 - Troubleshooting Made Easy: Deciphering Alfresco mTLS Confi...
 
Comparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdfComparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdf
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data Streams
 
Osi security architecture in network.pptx
Osi security architecture in network.pptxOsi security architecture in network.pptx
Osi security architecture in network.pptx
 
How to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion ApplicationHow to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion Application
 
Machine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their EngineeringMachine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their Engineering
 
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
 
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdfExploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
 
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptxThe Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
 
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptxReal-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtime
 
UI5ers live - Custom Controls wrapping 3rd-party libs.pptx
UI5ers live - Custom Controls wrapping 3rd-party libs.pptxUI5ers live - Custom Controls wrapping 3rd-party libs.pptx
UI5ers live - Custom Controls wrapping 3rd-party libs.pptx
 
Sending Calendar Invites on SES and Calendarsnack.pdf
Sending Calendar Invites on SES and Calendarsnack.pdfSending Calendar Invites on SES and Calendarsnack.pdf
Sending Calendar Invites on SES and Calendarsnack.pdf
 
What’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 UpdatesWhat’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 Updates
 
Leveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + KobitonLeveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
 
Amazon Bedrock in Action - presentation of the Bedrock's capabilities
Amazon Bedrock in Action - presentation of the Bedrock's capabilitiesAmazon Bedrock in Action - presentation of the Bedrock's capabilities
Amazon Bedrock in Action - presentation of the Bedrock's capabilities
 

Object Detection with Tensorflow

  • 1. Object Detection with Tensorflow by Anatolii Shkurpylo, Software Developer
  • 2. www.eliftech.com Agenda ▪ Intro ▪ What is Object Detection ▪ State of Object Detection ▪ Tensorflow Object Detection API ▪ Preparing Data ▪ Training & Evaluating ▪ Links
  • 6. www.eliftech.com Object detection = Object Classification + Object Localization
  • 7. www.eliftech.com One model for two tasks? Object detection - output is the one number (index) of a class Object localization - output is the four numbers - coordinates of bounding box. Po bx1 bx2 by1 by2 c1 c2 c3 … cn - is object exists - bounding box coordinates - object’s variables
  • 9. www.eliftech.com Approaches ▪ Classical approach (Haar features) - first OD real time framework (Viola-Jones) ▪ Deep learning approach - now state of the art in OD ▪ OverFeat ▪ R-CNN ▪ Fast R-CNN ▪ YOLO ▪ Faster R-CNN ▪ SSD and R-FCN
  • 10. www.eliftech.com Deep learning approach OverFeat - published in 2013, multi-scale sliding window algorithm using Convolutional Neural Networks (CNNs). R-CNN - Regions with CNN features. Three stage approach: - Extract possible objects using a region proposal method (the most popular one being Selective Search). - Extract features from each region using a CNN. - Classify each region with SVMs.
  • 11. www.eliftech.com Fast R-CNN - Similar to R-CNN, it used Selective Search to generate object proposals, but instead of extracting all of them independently and using SVM classifiers, it applied the CNN on the complete image and then used both Region of Interest (RoI) Pooling on the feature map with a final feed forward network for classification and regression. YOLO - You Only Look Once: a simple convolutional neural network approach which has both great results and high speed, allowing for the first time real time object detection. Deep learning approach
  • 12. www.eliftech.com Faster R-CNN - Faster R-CNN added what they called a Region Proposal Network (RPN), in an attempt to get rid of the Selective Search algorithm and make the model completely trainable end-to-end. SSD and R-FCN Finally, there are two notable papers, Single Shot Detector (SSD) which takes on YOLO by using multiple sized convolutional feature maps achieving better results and speed, and Region-based Fully Convolutional Networks (R-FCN) which takes the architecture of Faster R-CNN but with only convolutional networks. Deep learning approach
  • 14. www.eliftech.com TF Object Detection API ▪ Open Source from 2017-07-15 ▪ Built on top of TensorFlow ▪ Contains trainable detection models ▪ Contains frozen weights ▪ Contains Jupyter Notebook ▪ Makes easy to construct, train and deploy object detection models
  • 15. www.eliftech.com Getting started ▪ Protobuf 2.6 ▪ Python-tk ▪ Pillow 1.0 ▪ lxml ▪ Tf Slim (included) ▪ Jupyter notebook ▪ Matplotlib ▪ Tensorflow (tensorflow- gpu) ▪ Cython ▪ cocoapi Dependencies: If model will be trained locally - better to install tensorflow-gpu. Dependencies for tensorflow-gpu: ▪ NVIDIA GPU with CUDA Compute Capability 3.0 (list) ▪ Ubuntu 16.04 at least ▪ CUDA® Toolkit 9.0 ▪ NVIDIA drivers associated with CUDA Toolkit 9.0. ▪ cuDNN v7.0 ▪ libcupti-dev Installation instruction Installation instruction Latest version of CUDA Toolkit - 9.1 not compatible with tensorflow 1.6, need to install 9.0
  • 17. www.eliftech.com Dataset ▪ Tensorflow Object Detection API uses the TFRecord file format ▪ There is available third-party scripts to convert PASCAL VOC and Oxford Pet Format ▪ In other case explanation of format available in git repo. ▪ Input data to create TFRecord - annotated image
  • 18. www.eliftech.com Getting images Grab from internet ▪ Scrap images from google or Pixabay or whatever ▪ For batch downloading - Faktun Bulk Image Downloader ▪ For data mining by multiplying existing images - ImageMagic Create own images ▪ Record video with needed object/objects (in 640x480) ▪ Process video and split on screenshots - ffmpeg Tips ▪ Create images with different lights, background and so on. ▪ If object is able to have different forms - better to catch them all. ▪ Try to make 30%-50% of images with overlaid object ▪ Tool for image augmentation
  • 19. www.eliftech.com Labeling (Annotation) an images Tools ▪ LabelImg ▪ FIAT (Fast Image Data Annotation Tool) ▪ input: images ▪ output: .xml files with bounding boxes coordinates
  • 20. www.eliftech.com Creating TFRecord ▪ Tensorflow object detection API repo contains folder dataset_tools with scripts to coverts common structures of data in TFRecord. ▪ If output data has another structure - here is explanation how to convert it
  • 22. www.eliftech.com Selecting a model Tensorflow OD API provides a collection of detection models pre-trained on the COCO dataset, the Kitti dataset, and the Open Images dataset. - model name corresponds to a config file that was used to train this model. - speed - running time in ms per 600x600 image - mAP stands for mean average precision, which indicates how well the model performed on the COCO dataset. - Outputs types (Boxes, and Masks if applicable)
  • 23. www.eliftech.com Configuring ● label.pbtx ● pipeline.config train_config: { fine_tune_checkpoint: "<path_to_model.ckpt>" num_steps: 200000 } train_input_reader { label_map_path: "<path_to_labels.pbtxt>" tf_record_input_reader { input_path: "<path_to_train.record>" } } eval_config { num_examples: 8000 max_evals: 10 use_moving_averages: false } eval_input_reader { label_map_path: "<path_to_labels.pbtxt>" shuffle: false num_readers: 1 tf_record_input_reader { input_path: "<path_to_test.record>" } } ● Folders structure instruction
  • 24. www.eliftech.com Training & Evaluating # From the tensorflow/models/research directory python object_detection/eval.py --logtostderr --pipeline_config_path=${PATH_TO_YOUR_PIPELINE_CONFIG} --checkpoint_dir=${PATH_TO_TRAIN_DIR} --eval_dir=${PATH_TO_EVAL_DIR} # From the tensorflow/models/research directory python object_detection/train.py --logtostderr -- pipeline_config_path=/tensorflow/models/object_detection/samples/configs/ssd_mobilenet_v1_p ets.config --train_dir=${PATH_TO_ROOT_TRAIN_FOLDER}
  • 25. www.eliftech.com Links ▪ https://towardsdatascience.com/how-to-train-your-own-object-detector-with- tensorflows-object-detector-api-bec72ecfe1d9 ▪ https://www.kdnuggets.com/2017/10/deep-learning-object-detection- comprehensive-review.html ▪ http://www.machinelearninguru.com/deep_learning/tensorflow/basics/tfrecord/tfreco rd.html ▪ https://www.coursera.org/learn/convolutional-neural-networks ▪ https://medium.com/comet-app/review-of-deep-learning-algorithms-for-object- detection-c1f3d437b852 ▪ https://towardsdatascience.com/evolution-of-object-detection-and-localization- algorithms-e241021d8bad ▪ https://medium.freecodecamp.org/how-to-play-quidditch-using-the-tensorflow- object-detection-api-b0742b99065d
  • 26. www.eliftech.com Don’t forget to subscribe! Find us at eliftech.com Have a question? Contact us: info@eliftech.com