id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_yk2gyqjyvfawrgxcooxtlutl2u	Daisuke Hirahara	Effects of data count and image scaling on Deep Learning training	2020	13	.pdf	application/pdf	4346	645	59	We assumed that increasing the image size using interpolation methods would result of interpolation methods in medical images, we used a Gender01 data set, which is a using an interpolation method with data augmentation by inversion and rotation, we Training the CNN by increasing the image size using the interpolation Effects of data count and image scaling on Deep Learning training. input image data size using the interpolation method. method, the average classification accuracy was improved for all models trained with image Bilinear image interpolation method was 0.675 for 100 training data and an image size of Figure 8 Comparison of the classification accuracy between training models of data augmentation using rotation and inversion and image augmentation using Bilinear. that image interpolation is an effective method to improve accuracy compared with the In this paper, we investigated the effect of using interpolated image sizes for training data	./cache/work_yk2gyqjyvfawrgxcooxtlutl2u.pdf	./txt/work_yk2gyqjyvfawrgxcooxtlutl2u.txt