kunglab / ebnn
Header-only C library for Binary Neural Network Feedforward Inference (targeting small devices)
☆46Updated 2 years ago
Related projects: ⓘ
- Lightweight C implementation of CNNs for Embedded Systems☆53Updated last year
- Implementation of convolution layer in different flavors☆68Updated 6 years ago
- ☆29Updated 3 years ago
- Ternary Weights and Activations☆23Updated 6 years ago
- Binarized Neural Network TF training code + C matrix / eval library.☆98Updated 6 years ago
- CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices☆39Updated 4 years ago
- Implementation of "NITI: Training Integer Neural Networks Using Integer-only Arithmetic" on arxiv☆75Updated 2 years ago
- INT-Q Extension of the CMSIS-NN library for ARM Cortex-M target☆20Updated 4 years ago
- ☆63Updated 6 years ago
- The official, proof-of-concept C++ implementation of PocketNN.☆31Updated 3 months ago
- μNAS is a neural architecture search (NAS) system that designs small-yet-powerful microcontroller-compatible neural networks.☆75Updated 3 years ago
- generate tflite micro code which bypasses the interpreter (directly calls into kernels)☆77Updated 2 years ago
- Binary Neural Network on IceStick FPGA.☆48Updated 6 years ago
- Reducing the size of convolutional neural networks☆112Updated 6 years ago
- ☆54Updated this week
- Implementation for the paper "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization"☆73Updated 4 years ago
- Keras implementations of BinaryNet and XNORNet☆56Updated 6 years ago
- Quantized Neural Networks - networks trained for inference at arbitrary low precision.☆147Updated 6 years ago
- Fast matrix multiplication for few-bit integer matrices on CPUs.☆27Updated 5 years ago
- BNN implementation in tensorflow☆165Updated 6 years ago
- Mobilenet v1 trained on Imagenet for STM32 using extended CMSIS-NN with INT-Q quantization support☆85Updated 4 years ago
- Machine learning inference library for ARC EM and HS Processors☆25Updated 11 months ago
- BinaryNets in TensorFlow with XNOR GEMM op☆154Updated 7 years ago
- Implementation for Trained Ternary Network.☆108Updated 7 years ago
- An exploration of log domain "alternative floating point" for hardware ML/AI accelerators.☆388Updated last year
- Example code and instructions on getting Tensorflow Lite running on a Xilinx Zynq☆49Updated 6 years ago
- Exploring "Binary Neural Networks" (https://arxiv.org/abs/1602.02830) in Theano. A set of experiments that use binarised weights and/or …☆17Updated 7 years ago
- This is a collection of works on neural networks and neural accelerators.☆40Updated 5 years ago
- Reference implementations of popular Binarized Neural Networks☆104Updated last week
- ☆29Updated 4 years ago