lukasc-ch,Lukas Cavigelli,github

bbox-label-tool

A simple tool for labeling object bounding boxes in images

binaryconnect

Training Deep Neural Networks with binary weights during propagations

cbinfer

Code for the Change-Based Inference Paper (CBinfer)

cnn-eeg

CNN classifier to classify MI-EEG signals

combinational-bnn

System Verilog code describing a fully combinational binarized neural network.

cuda-winograd

Fast CUDA Kernels for ResNet Inference. Using Winograd algorithm to optimize the efficiency of convolutional computing.

drills

DRiLLS: Deep Reinforcement Learning for Logic Synthesis Optimization (ASPDAC'20)

driving-object-detection

Traffic Light detection using Tensorflow Object Detection API v1 and v2

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks. EDVR has been merged into BasicSR and this repo is a mirror of BasicSR.

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

extendedbitplanecompression

Provides the code for the paper "EBPC: Extended Bit-Plane Compression for Deep Neural Network Inference and Training Accelerators" by Lukas Cavigelli, Georg Rutishauser, Luca Benini.

fann-on-arm

FANN-on-ARM: Optimized FANN Inference for ARM Cortex M-series

flexflow

A distributed deep learning framework.

hashingdeeplearning

Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"

human-pose-estimation.pytorch

The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

jetson-tx2-pytorch

Installing PyTorch on the Nvidia Jetson TX1/TX2

object_detection_on_zynq_mpsoc

pyscatwave

Fast Scattering Transform with CuPy/PyTorch

pytorch-revnet

Implementation of the reversible residual network in pytorch

pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.