In Homework 2 we are going to train models that can recommend hashtags based on the content of an image. We will use the dataset "HARRISON". Please refer to the paper (https://arxiv.org/abs/1605.05054) for more details about the dataset.

The original data of HARRISON can be downloaded here: (https://drive.google.com/file/d/1B9NZf42J_GpslRNlTTAxvM5c9WRVl_1Z/view?usp=sharing). You can download the images and take a look, but this is not mandatory. We already extracted the image features for you and upload to Kaggle "harrison_features.npz".

The demo code separates the training process into two stages: word2vec training and image-to-word2vec training. To evaluate the performance, the top 10 hashtags recommended from your model will be used to calculate the hamming loss of ground truth.  Get your computer ready and have fun!