ACCURACY IMPROVING OF PRE-TRAINED NEURAL NETWORKS BY FINE TUNING
Abstract
Methods of accuracy improving of pre-trained networks are discussed. Images of ships are input data for the networks. Networks are built and trained using Keras and TensorFlow machine learning libraries. Fine tuning of previously trained convoluted artificial neural networks for pattern recognition tasks is described. Fine tuning of VGG16 and VGG19 networks are done by using Keras Applications. The accuracy of VGG16 network with finetuning of the last convolution unit increased from 94.38% to 95.21%. An increase is only 0.83%. The accuracy of VGG19 network with fine-tuning of the last convolution unit increased from 92.97% to 96.39%, which is 3.42%.
Metrics
Topics
Related Documents
Accuracy improving of pre-trained neural networks by fine tuning
Improving Pre- Trained Weights through Meta - Heuristics Fine- Tuning
Gustavo Henrique de RosaMateus RoderJoão Paulo PapaClaudio Filipi Gonçalves dos Santos
Fine-tuning pre-trained neural networks for medical image classification in small clinical datasets
Newton SpolaôrHuei LeeAna Isabel MendesConceição NogueiraAntonio Rafael Sabino ParmezanWeber Shoity Resende TakakiCláudio Saddy Rodrigues CoyFeng Chung WuRui Fonseca-Pinto
Improving Pantun Generator Performance with Fine Tuning Generative Pre-Trained Transformers
Fine-tuning of pre-trained convolutional neural networks for diabetic retinopathy screening: a clinical study
Yaser M. RoshanAmir Hossein VejdaniSaboora M. RoshanAli Karsaz