Evaluation Data (Image Classification)
ImageNet-1K
#Evaluation Metrics - Acc@1, Acc@5
Data description:
ImageNet-1K dataset is a subset of the ImageNet dataset used in ILSVRC2012, consisting of 1,000 classes. The training set contains approximately 1.2 million images, and the validation set contains 50,000 images. 30,000 images are sampled from the original training set as the validation set, and the original validation set serves as the test set.
Dataset structure:
Amount of source data:
The dataset is divided into auxiliary training set (1,251,167), validation set (30,000), and test set (50,000).
Amount of test data:
All 50,000 test examples from the source dataset test set.
Data detail:
| KEYS | EXPLAIN |
|---|---|
| images | RGB images used as input |
| labels | Category label of the image |
Sample of source dataset:
RGB image：
label：
n01440764
Paper citation:
@inproceedings{deng2009imagenet,
title={Imagenet: A large-scale hierarchical image database},
author={Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Li, Kai and Fei-Fei, Li},
booktitle={Computer Vision and Pattern Recognition},
pages={248--255},
year={2009},
organization={IEEE}
}Place365 Standard
#Evaluation Metrics - Acc@1, Acc@5
Data description:
The Places365 Standard dataset is a scene recognition dataset with 1,800,000 training images from 365 scene classes and 36,500 validation images. 18,000 images are sampled from the original training set to form the validation set, and the remaining images are used as the training set. The original validation set serves as the test set.
Dataset structure:
Amount of source data:
The dataset is divided into auxiliary training set (1,782,000), validation set (18,000), and test set (36,500).
Amount of test data:
All 36,500 test examples from the source dataset test set.
Data detail:
| KEYS | EXPLAIN |
|---|---|
| images | RGB images used as input |
| labels | Category label of the image |
Sample of source dataset:
RGB image：
label：
airfield
Paper citation:
@article{zhou2017places,
title={Places: A 10 million image database for scene recognition},
author={Zhou, Bolei and Lapedriza, Agata and Khosla, Aditya and Oliva, Aude and Torralba, Antonio},
journal={IEEE transactions on pattern analysis and machine intelligence},
volume={40},
number={6},
pages={1452--1464},
year={2017},
publisher={IEEE}
}