Fine-grained classification is a classical task in Computer Vision(CV). The task is to specify the fine-grained category of an object. For example, youe may need to figure out the brand of a car or the name of a bird. In this task, we provide a dataset of 180 bird species. 24497 training images, 900 test images(5 per species) and 900 validation images(5 per species). All images are 224 X 224 X 3 color images in jpg format.

Participants should train their own models using ONLY the training data, and any format of extra data is not allowed. For online evaluation, evaluate your model on the testing data, and record the predictions in a separate .csv file with the same format of train.csv, then upload to the submission page. NOTE that the public leaderboard only shows the accuracy over a subset of the testing set, and the final ranking is based on another subset and is only kept private until the competition ends.