DeepFruits: Dataset of Fruits Images with different combinations for Fruit Recognition and Calories Estimation

A new labeled dataset consists of 21,122 fruit images of 20 diverse kinds of Fruits based on 8 different fruit set combinations. The number of images per class differs from one class to another. Sample images of all Fruit combinations are also attached. The train and test CSV files contain the Label of each corresponding Fruit class in each image based on the image file name.

本全新标注数据集包含基于8组不同水果组合构建的20类多样化水果的21122张图像。各类别对应的图像数量并不统一。所有水果组合的样本图像亦随附于本数据集内。训练与测试CSV文件均依据图像文件名，标注了每张图像所属的对应水果类别标签。

搜集汇总

背景与挑战

背景概述

DeepFruits是一个用于水果识别和卡路里估计的图像数据集，包含21,122张图像，涵盖20种不同水果，基于8种水果组合方式构建。数据集已预分为训练集和测试集，并提供CSV标签文件，适用于计算机视觉和深度学习任务，如图像分类和决策支持。