1. 简介
    MicroImageNet classification challenge is similar to the classification challenge in the full ImageNet ILSVRC. MicroImageNet contains 200 classes for training. Each class has 500 images. The test set contains 10,000 images. All images are 64x64 colored ones.

Your objective is to classify the 10,000 test set as accurately as possible.

  1. 下载
wget http://cs231n.stanford.edu/tiny-imagenet-200.zip
unzip tiny-imagenet-200.zip