deepimagehashing-VAE

This is the main repository for our improvement on Auto-Encoding Twin-Bottleneck Hashing. Note that the codebase is also an adapted version of the TBH repository.

Requirements

python=3.6
tensorflow>=2.5
numpy
matplotlib

Data

This work supports tf.data.TFRecordDataset as the data feed. We use the cifar10 dataset provided by the TBH authors:

• Cifar-10 (Training, Test)

For other datasets, please refer to util/data/make_data.py to build TFRecords.

Please organize the data folder as follows:

data
  |-cifar10 (or other dataset names)
    |-train.tfrecords
    |-test.tfrecords

Simply run

python ./run_tbh.py

to train the model.

The resulting checkpoints will be placed in ./result/set_name/model/date_of_today with tensorboard events in ./result/set_name/log/date_of_today.

The mAP results shown on tensorboard are just for illustration (the actual score would be slightly higher than the ones on tensorboard), since I do not update all dataset codes upon testing. Please kindly evaluate the results by saving the proceeded codes after training.

The visualisations can be recreated by running

python ./vis.py