چکیده مقاله
The U Net architecture, initially designed for biomedical image segmentation, canbe repurposed for edge detection tasks by reconfiguring the network’s focus This paperinvestigates the impact of batch size, a critical hyperparameter in U Net, on the network’sperformance for edge detection We conduct experiments with three different image sizes andvarying batch sizes for each image size By analyzing the trade offs between accuracy andstability, we identify the optimal batch size that enhances the U Net model’s performance inedge detection tasks Our study contributes valuable insights into effectively configuring batchsize to improve U Net’s performance in edge detection applications
کلیدواژهها
نویسندگان
Zeinab Sedaghatjoo
Department of Mathematics, Persian Gulf University, Bushehr, Iran
شیوه ارجاع
Sedaghatjoo, Zeinab,1403,An Experiment Study on Optimal Batch size of U-Net Convolutional Neural Network for Edge detection,1st International Biennial Conference of Artificial Intelligence and Data Science 2024,Bushehr
ارائهشده در
مجموعه مقالات اولین کنفرانس بین المللی دوسالانه هوش مصنوعی و علوم داده3 اردیبهشت 1403 · بوشهر