akshaychawla / Binary-Neural-NetworksLinks
Exploring "Binary Neural Networks" (https://arxiv.org/abs/1602.02830) in Theano. A set of experiments that use binarised weights and/or activations to reduce computational load of convolutional neural networks.
☆17Updated 8 years ago
Alternatives and similar repositories for Binary-Neural-Networks
Users that are interested in Binary-Neural-Networks are comparing it to the libraries listed below
Sorting:
- BNN implementation in tensorflow☆167Updated 7 years ago
- Implementation for Trained Ternary Network.☆107Updated 8 years ago
- Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1☆303Updated 3 years ago
- Implementation of Ternary Weight Networks In Caffe☆63Updated 8 years ago
- Reducing the size of convolutional neural networks☆111Updated 7 years ago
- BinaryNets in TensorFlow with XNOR GEMM op☆156Updated 8 years ago
- Training Deep Neural Networks with binary weights during propagations☆382Updated 9 years ago
- Quantized Neural Networks - networks trained for inference at arbitrary low precision.☆147Updated 7 years ago
- Code example for the ICLR 2018 oral paper☆153Updated 7 years ago
- This is a collection of works on neural networks and neural accelerators.☆40Updated 6 years ago
- ☆119Updated 7 years ago
- binary weight neural network implementation on tensorflow☆54Updated 7 years ago
- Ternary Weights and Activations☆24Updated 7 years ago
- Keras implementations of BinaryNet and XNORNet☆55Updated 7 years ago
- Residual Binarized Neural Network☆43Updated 7 years ago
- collection of works aiming at reducing model sizes or the ASIC/FPGA accelerator for machine learning☆562Updated last year
- Reproduction of WAGE in PyTorch.☆44Updated 6 years ago
- CaffePresso: An Optimized Library for Deep Learning on Embedded Accelerator-based platforms☆87Updated 11 months ago
- ☆14Updated 5 years ago
- Header-only C library for Binary Neural Network Feedforward Inference (targeting small devices)☆47Updated 3 years ago
- An exploration of log domain "alternative floating point" for hardware ML/AI accelerators.☆394Updated 2 years ago
- Caffe implementation of accurate low-precision neural networks☆117Updated 6 years ago
- OpenCL Labs for PAPAA Summer School 2016 Edition☆46Updated 8 years ago
- XNOR-Net, with binary gemm and binary conv2d kernels, support both CPU and GPU.☆86Updated 6 years ago
- ☆52Updated 6 years ago
- Implementing CNN code in CUDA and OpenCL to evaluate its performance on NVIDIA GPUs, AMD GPUs, and an FPGA platform.☆54Updated 8 years ago
- Jupyter notebook examples on image classification with quantized neural networks☆69Updated 5 years ago
- ☆62Updated 7 years ago
- Efficient Sparse-Winograd Convolutional Neural Networks (ICLR 2018)☆193Updated 6 years ago
- The 1st place winner's source codes for DAC 2018 System Design Contest, FPGA Track☆90Updated 6 years ago