qinyao-he / bit-rnn
Quantize weights and activations in Recurrent Neural Networks.
☆95Updated 6 years ago
Related projects: ⓘ
- Implementation for Trained Ternary Network.☆108Updated 7 years ago
- Recurrent Neural Networks With Limited Numerical Precision☆11Updated 7 years ago
- Training deep neural networks with low precision multiplications☆63Updated 9 years ago
- Implementation of Ternary Weight Networks In Caffe☆63Updated 7 years ago
- Sparse Recurrent Neural Networks -- Pruning Connections and Hidden Sizes (TensorFlow)☆74Updated 4 years ago
- BinaryNets in TensorFlow with XNOR GEMM op☆154Updated 7 years ago
- Implementation of "Iterative pruning" on TensorFlow☆161Updated 3 years ago
- Quantized Neural Networks - networks trained for inference at arbitrary low precision.☆147Updated 6 years ago
- ☆47Updated 4 years ago
- Caffe Implementation for Incremental network quantization☆191Updated 6 years ago
- Caffe implementation of accurate low-precision neural networks☆118Updated 5 years ago
- ☆63Updated 6 years ago
- Training Low-bits DNNs with Stochastic Quantization☆73Updated 7 years ago
- BNN implementation in tensorflow☆165Updated 6 years ago
- Code example for the ICLR 2018 oral paper☆150Updated 6 years ago
- LCNN: Lookup-based Convolutional Neural Network☆52Updated 6 years ago
- Efficient forward propagation for BCNNs☆50Updated 7 years ago
- Caffe implementation for dynamic network surgery.☆187Updated 7 years ago
- This repository represents training examples for the CVPR 2018 paper "SYQ:Learning Symmetric Quantization For Efficient Deep Neural Netwo…☆32Updated 5 years ago
- Caffe for Sparse Convolutional Neural Network☆238Updated last year
- Source code for ``Neural Networks with Few Multiplications'' published at ICLR 2016☆81Updated 8 years ago
- Binarized Dense and Conv2D layers for Keras☆16Updated 7 years ago
- Reducing the size of convolutional neural networks☆112Updated 6 years ago
- ☆51Updated 6 years ago
- Efficient Sparse-Winograd Convolutional Neural Networks (ICLR 2018)☆190Updated 5 years ago
- Fast matrix multiplication for few-bit integer matrices on CPUs.☆27Updated 5 years ago
- A script to convert floating-point CNN models into generalized low-precision ShiftCNN representation☆55Updated 7 years ago
- Implementation of ICLR 2018 paper "Loss-aware Weight Quantization of Deep Networks"☆26Updated 4 years ago
- Training Deep Neural Networks with binary weights during propagations☆377Updated 8 years ago
- Ristretto: Caffe-based approximation of convolutional neural networks.☆292Updated 5 years ago