Computer Vision Accuracy Analysis with Deep Learning Model Using TensorFlow
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2020, Vol 8, Issue 4
Abstract
Deep learning has absolutely dominated computer vision with creating a model that most accurately classifies the given image in the dataset and surpassing human performance. In previous research works many deep learning models are created and tested for image Classification on various datasets like MNIST, CIFAR-10, ImageNet using Python. Though they got good results of Accuracy for Classification, in this paper I have extended the work of measuring the performance analysis of Accuracy for Classification and also for the Predictions on CPU and GPU using TensorFlow2.0 and Keras on CIFAR-10 dataset having 50000 images of 10 datasets having a lot of different classes with very low resolutions. TensorFlow is an emerging technology on top of Python libraries developed by Google. This work reached an Accuracy 85% on GPU of Intel® Core™ i3-7100U CPU which is acceptable with datasets used in this work are not easy to deal and all with very low resolutions having a lot of classes. That’s why it’s impacting the performance of the network. To classify and predict very low-resolution images from more datasets is really challenging one, it’s a great thing the computer vision accuracy performed excellent in my work.
Authors and Affiliations
T. Tritva Jyothi Kiran
Keywords
Related Articles
- EP ID EP747779
- DOI 10.21276/ijircst.2020.8.4.13
- Views 1
- Downloads 0
An Overview of Cellular Network as A Sensor: From Mobile Phones Data to Real-time Road Traffic Monitoring
Versatile cell organizations might go about as pervasive actual portability sensors. Dependent just upon anonymized flagging information assembled from a versatile cell organization, we present a procedure for surmising...
Use of Smart Intrusion Detection System for Enhancing the Security in Hierarchical Wireless Sensor Network
Trusted environment provides safety measures for the sensor network. There are many problems that occur during the management of resources. Memory management and computation overhead or CPU usage are the major issues. Se...
Snowfall Prediction Using Artificial Recurrent Neural Network (RNN)
Prediction of weather is an attempt done by meteorologists to forecast the weather conditions of an area at some time in the future that may be expected. The parameters of the climatic condition are based on the humidity...
Exploratory Data Analysis of Global Power Plants using Various Machine Learning Algorithms
Nuclear plants' rewards and prices, etc and severe negative costs, are determined by their technology and the amount of electricity they create. Most nations, especially emerging ones where electricity output is expected...
Sentiment Based Product Recommendation System for E-Commerce Using Machine Learning Approaches
Today, e-commerce is a thriving industry. We do not need to approach every customer to accept their orders here. A business creates a website to offer things to clients, who can then purchase the stuff they need within t...