Implementation for paper "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization"

• Python version 3.6 or 3.7
• Tensorflow version 1.14+ or 2.0.0
• Larq version 0.2.0
• Zookeeper version 0.1.1

You can also check out one of our prebuilt docker images.

This is a complete Python module. To install it in your local Python environment, cd into the folder containing setup.py and run:

pip install -e .

To train a model locally, you can use the cli:

bnno train binarynet --dataset cifar10

To reproduce the runs exploring various hyperparameters, run:

bnno train binarynet \
    --dataset cifar10 \
    --preprocess-fn resize_and_flip \
    --hparams-set bop \
    --hparams threshold=1e-6,gamma=1e-3

where you use the appropriate values for threshold and gamma.

To achieve the accuracy in the paper of 91.3%, run:

bnno train binarynet \
    --dataset cifar10 \
    --preprocess-fn resize_and_flip \
    --hparams-set bop_sec52 \
    --epochs 500

To achieve the accuracy in the paper of 54.2%, run:

bnno train birealnet --dataset imagenet2012 --hparams-set bop --epochs 100