Open AccessPerformance Evaluation of Fine-tuned Faster R-CNN on specific MS COCO Objects
Author(s) -
Garima Devnani,
Ayush Jaiswal,
Roshni John,
Rajat Chaurasia,
Neha Tirpude
Publication year - 2019
Publication title -
international journal of electrical and computer engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.277
H-Index - 22
ISSN - 2088-8708
DOI - 10.11591/ijece.v9i4.pp2548-2555
Subject(s) - computer science , convolutional neural network , set (abstract data type) , process (computing) , context (archaeology) , artificial intelligence , test set , training set , range (aeronautics) , image (mathematics) , machine learning , data mining , pattern recognition (psychology) , programming language , composite material , biology , paleontology , materials science
Fine-tuning of a model is a method that is most often required to cater to the users’ explicit requirements. But the question remains whether the model is accurate enough to be used for a certain application. This paper strives to present the metrics used for performance evaluation of a Convolutional Neural Network (CNN) model. The evaluation is based on the training process which provides us with intermediate models after every 1000 iterations. While 1000 iterations are not substantial enough over the range of 490k iterations, the groups are sized with 100k iterations each. Now, the intention was to compare the recorded metrics to evaluate the model in terms of accuracy. The training model used the set of specific categories chosen from the Microsoft Common Objects in Context (MS COCO) dataset while allowing the users to use their externally available images to test the model’s accuracy. Our trained model ensured that all the objects are detected that are present in the image to depict the effect of precision.