Skip to content


Switch branches/tags

Latest commit


Git stats


Failed to load latest commit information.
Latest commit message
Commit time

mini-ImageNet Logo

Tools for mini-ImageNet Dataset

LICENSE Python PyPI Downloads CodeFactor Grade

This repo provides python source code for creating mini-ImageNet dataset from ImageNet and the utils for generating batches during training. This repo is related to our work on few-shot learning: Meta-Transfer Learning.


About mini-ImageNet

The mini-ImageNet dataset was proposed by Vinyals et al. for few-shot learning evaluation. Its complexity is high due to the use of ImageNet images but requires fewer resources and infrastructure than running on the full ImageNet dataset. In total, there are 100 classes with 600 samples of 84×84 color images per class. These 100 classes are divided into 64, 16, and 20 classes respectively for sampling tasks for meta-training, meta-validation, and meta-test.

Please note that the split files in csv_files folder are created by Ravi and Larochelle (GitHub link). Vinyals et al. didn't include their split files for mini-ImageNet when they first released their paper, so Ravi and Larochelle created their own splits. Additional split files are provided here.


  • Python 2.7 or 3.x
  • numpy
  • tqdm
  • opencv-python
  • Pillow


Install via PyPI:

pip install miniimagenettools

Install via GitHub:

git clone


First, you need to download the image source files from ImageNet website. If you already have it, you may use it directly. Some people report the ImageNet website is not working. Here is an alternative download link. Please carefully read the terms for ImageNet before you download it.

Filename: ILSVRC2012_img_train.tar
Size: 138 GB
MD5: 1d675b47d978889d74fa0da5fadfb00e

Then clone the repo:

git clone
cd mini-imagenet-tools

To generate mini-ImageNet dataset from tar file:

python --tar_dir [your_path_of_the_ILSVRC2012_img_train.tar]

To generate mini-ImageNet dataset from untarred folder:

python --imagenet_dir [your_path_of_imagenet_folder]

If you want to resize the images to the specified resolution:

python --tar_dir [your_path_of_the_ILSVRC2012_img_train.tar] --image_resize 100

P.S. In default settings, the images will be resized to 84 × 84.

If you don't want to resize the images, you may set --image_resize 0.

To use the MiniImageNetDataLoader class:

from miniimagenettools.mini_imagenet_dataloader import MiniImageNetDataLoader

dataloader = MiniImageNetDataLoader(shot_num=5, way_num=5, episode_test_sample_num=15)



for idx in range(total_train_step):
    episode_train_img, episode_train_label, episode_test_img, episode_test_label = \
        dataloader.get_batch(phase='train', idx=idx)


Check the SOTA results for mini-ImageNet on this page.

Download Processed Images

Download jpg files (Thanks for the contribution by @vainaijr)

Download tar files


Model-Agnostic Meta-Learning

Optimization as a Model for Few-Shot Learning

Meta-Learning for Semi-Supervised Few-Shot Classification