Adding dataset Tiny-Imagenet

🚀 The feature

Hello,

I would like to contribute to torchvision by providing a implementation of Tiny-Imagenet dataset.

home : https://www.kaggle.com/c/tiny-imagenet
paper : http://vision.stanford.edu/teaching/cs231n/reports/2015/pdfs/yle_project.pdf
zip : http://cs231n.stanford.edu/tiny-imagenet-200.zip

This challenge is part of Stanford Class CS 231N.
Label Classes and Bounding Boxes are provided

details:
classes : 200
image_size : 64x64x3
bbox : x0, y0, x1, y1 for each image
train split : 100 000 (500 per class)
val split : 10 000 (50 per class)
test split : 10 000 (50 per class)

Motivation, pitch

Note: the original test split doesn't have targets and bboxes.
Thus, in this implementation, I used the val split when passing train=True.

Features:

• fast loading by creating numpy files (npy/*.npy) from the raw folder/image datasets
• can leverage bbox

Structure:

root
├───tiny-imagenet-200.zip
├───tiny-imagenet-200
│   ├───npy <-- generated
│   │       ├───test_bboxes.npy
│   │       ├───test_data.npy
│   │       ├───test_targets.npy
│   │       ├───train_bboxes.npy
│   │       ├───train_data.npy
│   │       ├───train_targets.npy
│   ├───test
│   ├───train
│   ├───val
│   ├───words.txt
│   └───wnids.txt

Here the implementation:
https://github.com/towzeur/vision/commit/a67feb569361f440fd48ed492183de8bd8f6b585

Alternatives

No response

Additional context

No response

cc @pmeier @YosuaMichael

Review the linked commit and the Tiny-ImageNet structure described in the issue, including the train, val, test, words.txt, wnids.txt, and generated npy files. Confirm how the proposed dataset handles targets, bounding boxes, splits, and the test set without targets; done means a reviewed torchvision implementation with those behaviors clearly defined.