Sketch Object Prediction

Slides:



Advertisements
Similar presentations
Operating System.
Advertisements

Fall 2001CS 4471 Chapter 2: Performance CS 447 Jason Bakos.
Back-Propagation MLP Neural Network Optimizer ECE 539 Andrew Beckwith.
CLASSIFICATION: Ensemble Methods
A Simulated-annealing-based Approach for Simultaneous Parameter Optimization and Feature Selection of Back-Propagation Networks (BPN) Shih-Wei Lin, Tsung-Yuan.
DynamicMR: A Dynamic Slot Allocation Optimization Framework for MapReduce Clusters Nanyang Technological University Shanjiang Tang, Bu-Sung Lee, Bingsheng.
ImageNet Classification with Deep Convolutional Neural Networks Presenter: Weicong Chen.
Artificial Neural Network System to Predict Golf Score on the PGA Tour ECE 539 – Fall 2003 Final Project Robert Steffes ID:
Assignment 4: Deep Convolutional Neural Networks
Facial Detection via Convolutional Neural Network Nathan Schneider.
Comparing TensorFlow Deep Learning Performance Using CPUs, GPUs, Local PCs and Cloud Pace University, Research Day, May 5, 2017 John Lawrence, Jonas Malmsten,
TensorFlow The Deep Learning Library You Should Be Using.
Big data classification using neural network
Tenacious Deep Learning
Analysis of Sparse Convolutional Neural Networks
Presented by Khawar Shakeel
Process Management Process Concept Why only the global variables?
Operating System.
Neural Networks for Quantum Simulation
cs638/838 - Spring 2017 (Shavlik©), Week 10
ECRG High-Performance Computing Seminar
Chilimbi, et al. (2014) Microsoft Research
DeepCount Mark Lenson.
Convolutional Neural Fabrics by Shreyas Saxena, Jakob Verbeek
Krishna Kumar Singh, Yong Jae Lee University of California, Davis
Deep Learning in HEP Large number of applications:
A Pool of Deep Models for Event Recognition
Applications of Deep Learning and how to get started with implementation of deep learning Presentation By : Manaswi Advisor : Dr.Chinmay.
Deep Learning Libraries
Overcoming Resource Underutilization in Spatial CNN Accelerators
Multi-Layer Perceptron On A GPU
Ajita Rattani and Reza Derakhshani,
Classification with Perceptrons Reading:
Many-core Software Development Platforms
Comparison Between Deep Learning Packages
Programming Languages
Using Tensorflow to Detect Objects in an Image
Object Recognition & Detection
Bird-species Recognition Using Convolutional Neural Network
Introduction to Neural Networks
MXNet Internals Cyrus M. Vahid, Principal Solutions Architect,
Logistic Regression & Parallel SGD
Construct a Convolutional Neural Network with Python
Introduction to Deep Learning with Keras
Scientific Computational Reproducibility
Oral presentation for ACM International Conference on Multimedia, 2014
Optimization for Fully Connected Neural Network for FPGA application
Detecting Myocardial Infarctions (Heart Attack) using Neural Network
Image to Image Translation using GANs
Declarative Transfer Learning from Deep CNNs at Scale
Neural Networks Geoff Hulten.
Vinit Shah, Joseph Picone and Iyad Obeid
An Experimental Study of the Potential of Using Small
Tuning CNN: Tips & Tricks
GNU gcov gcov is a test coverage program running with gcc.
Object Tracking: Comparison of
Hyperspectral Image Classification Using ResNeXt with Squeeze and Excitation Block Jiayu Wang.
Operating System Introduction.
Heterogeneous convolutional neural networks for visual recognition
Deep Learning Authors: Yann LeCun, Yoshua Bengio, Geoffrey Hinton
Attention for translation
Reuben Feinman Research advised by Brenden Lake
Automatic Handwriting Generation
Authors: Chaim Baskin, Natan Liss, Evgenii Zheltonozhskii, Alex M
Chapter 2: Performance CS 447 Jason Bakos Fall 2001 CS 447.
Neural Machine Translation using CNN
Object Detection Implementations
CRCV REU 2019 Kara Schatz.
Adrian E. Gonzalez , David Parra Department of Computer Science
Machine Learning for Cyber
Presentation transcript:

Sketch Object Prediction Luciano Ricotta

Executive Summary Project Intentions Tasks Performed: Train a CNN for sketch object identification and optimize its performance Tasks Performed: Data Preparation Generalize Implementation Optimize performance Assessment of Project More computing power is needed to use all 345 categories Successful in generalizing the code and optimizing performance

Approaches: Program Keisuke Irie’s implementation of a CNN and ensemble learning had only 4 image classifications Step 1: Debugging the code Step 2: Preparing the rest of the data Step 3: Generalizing the code for N categories Step 4: Optimizing the code by varying: Number of categories Sample size Epochs Convolution layers Batch size Neurons CNN architecture

Approaches: Platform Personal computer for debugging the code Euler for data preparation Used python’s multiprocessing utility to run program in parallel. Allocated 20 CPUs for a significant speed up Euler for training the CNN Data files (not raw) totaled to 382 GB, and each object file was between 0.5 to 1 GB A lot of RAM was required (more than the 12 GB in my laptop)

Results: Image Prediction Number of categories range between 2 and 20 Varying neurons, batch size, and convolution layers does not have much of an effect, although an increase in neurons has a slight accuracy boost. The accuracy generally likes to stay between 80 and 90 for high number of categories and between 90 and 100 for low number of categories. Number of categories 2 4 6 8 12 16 20 Average Accuracy 0.989639 0.965828 0.946669 0.95106 0.827354 0.885874 0.81101

Results: Country Prediction Number of categories range between 4 and 16 Varying neurons, batch size, and convolution layers does not have much of an effect, although an increase in neurons has a slight performance boost. The accuracy is not significantly affected by any of these factors. Number of categories 4 8 12 16 20 Average Accuracy 0.875305 0.87626 0.886038 0.882708 0.885044

Discussion: Moving forward More computing power could let us: Include the other 300+ categories - which could result in poor accuracy, but… This would push us to implement the a common CNN architecture such as the AlexNet architecture to compensate for the increased number of categories.