In homework, 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, compressed them as "harrison_features.npz", and upload to Kaggle:
https://www.kaggle.com/kuantinglai/harrison-dataset


The training process is split into two stages: hashtag2vec training and image-to-word2vec training. Please refer to the notebook of this competition. The steps are
1. Run https://www.kaggle.com/kuantinglai/train-htag2vec-tf1
2. Download "tag\_list\_word2vec\_64.npz" (The number 64 may be changed, it depends on your vector dimension)
3. Run https://www.kaggle.com/kuantinglai/train-devise-w-ur-htag2vec, upload your  "tag\_list\_word2vec\_64.npz"
4. Download "harrison\_test\_predict.csv" and submit

To evaluate the model performance, we use the mean Average Precision (mAP) @ 10. Enjoy the homework and Have fun!