binary-neural-networks
Binary Neural Network Framework for FPGA(Differentiable LUT)
Extreme low-bit inference lab: pack weights to 1–1.58 bits and run real XNOR/popcount kernels on CPU/edge — honest STE training, not fake GPU 32× from sign().
BITorch: Open-Source Implementation of Binary Neural Networks with PyTorch
PyTorch extension for alternative backward rules and gradient transforms (STE, gradient jamming, non-standard activations).
