densechen / eth-80-preprocess Goto Github PK

The ETH-80 dataset [1] contains visual object images from 8 different categories including apples, cars, cows,cups, dogs, horses, pears and tomatoes. For each category, there are 10 object instances and 41 images for each object instance captured from different viewpoints.

We reorganize the dataset, which can directly be loaded by torchvision.dataset.ImageFolder.

The original data comes from here.

References

[1] B. Leibe and, B.Schiele. Analyzing Appearance and Contour Based Methods for Object Categorization. CVPR, vol.2, pp. 409-415, 2003