This dataset is just like the CIFAR-10, except it has 100 classes containing 600 images each. There are 500 training images and 100 testing images per class. The 100 classes in the CIFAR-100 are grouped into 20 superclasses. Each image comes with a "fine" label (the class to which it belongs) and a "coarse" label (the superclass to which it belongs).
Here is the list of classes in the CIFAR-100:

Yes, I know mushrooms aren't really fruit or vegetables and bears aren't really carnivores.

Dataset layout

Python / Matlab versions

The python and Matlab versions are identical in layout to the CIFAR-10, so I won't waste space describing them here.

Binary version

The binary version of the CIFAR-100 is just like the binary version of the CIFAR-10, except that each image has two label bytes (coarse and fine) and 3072 pixel bytes, so the binary files look like this:

<1 x coarse label><1 x fine label><3072 x pixel>
...
<1 x coarse label><1 x fine label><3072 x pixel>

Indices into the original 80 million tiny images dataset

Sivan Sabato was kind enough to provide this file, which maps CIFAR-100 images to images in the 80 million tiny images dataset. Sivan Writes:

The file has 60000 rows, each row contains a single index into the tiny db,
where the first image in the tiny db is indexed "1". "0" stands for an image that is not from the tiny db.
The first 50000 lines correspond to the training set, and the last 10000 lines correspond
to the test set.