Data
tiniest-imagenet-200

tiniest-imagenet-200

active ARFF DbCL v1.0 Visibility: public Uploaded 09-10-2024 by Subhaditya Mukherjee
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Tiny ImageNet contains 100000 images of 200 classes (500 for each class) downsized to 64 x 64 colored images. !!! This dataset only links to 20 images per class (instead of the usual 500) and is ONLY for quickly testing a framework. !!! Each class has 500 training images, 50 validation images, and 50 test images. The dataset here just contains links to the images and the labels. The dataset can be downloaded from the official website ![here](http://cs231n.stanford.edu/tiny-imagenet-200.zip). /n Link to the paper - [Tiny ImageNet Classification with CNN](https://cs231n.stanford.edu/reports/2017/pdfs/930.pdf)

2 features

label (target)string200 unique values
0 missing
image_pathstring4000 unique values
0 missing

19 properties

4000
Number of instances (rows) of the dataset.
2
Number of attributes (columns) of the dataset.
200
Number of distinct values of the target attribute (if it is nominal).
0
Number of missing values in the dataset.
0
Number of instances with at least one value missing.
0
Number of numeric attributes.
0
Number of nominal attributes.
0
Percentage of binary attributes.
0
Percentage of instances having missing values.
0
Percentage of missing values.
1
Average class difference between consecutive instances.
0
Percentage of numeric attributes.
0
Number of attributes divided by the number of instances.
0
Percentage of nominal attributes.
0.5
Percentage of instances belonging to the most frequent class.
20
Number of instances belonging to the most frequent class.
0.5
Percentage of instances belonging to the least frequent class.
20
Number of instances belonging to the least frequent class.
0
Number of binary attributes.

1 tasks

1 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: label
Define a new task