Junli Gu's starred repositories
deeplearning4j
Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running math code and a java based math library on top of the core c++ library. Also includes samediff: a pytorch/tensorflow like library for running deep learn...
deep-residual-networks
Deep Residual Learning for Image Recognition
SqueezeNet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters
deepframeworks
Evaluation of Deep Learning Frameworks
caffe-segnet
Implementation of SegNet: A Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-Wise Labelling
caffenet-benchmark
Evaluation of the CNN design choices performance on ImageNet-2012.
ck
Collective Knowledge (CK) is an educational community project to learn how to run AI, ML and other emerging workloads in the most efficient and cost-effective way across diverse models, data sets, software and hardware using MLCommons CM (Collective Mind workflow automation framework)
viennacl-dev
Developer repository for ViennaCL. Visit http://viennacl.sourceforge.net/ for the latest releases.
Google_Refexp_toolbox
The toolbox for the Google Refexp dataset proposed in this paper: http://arxiv.org/abs/1511.02283
GTAVisionExport
Code to export full segmentations from GTA
OpenCL-Benchmark
Bench OpenCL
wfvopencl-benchmarks
OpenCL Benchmarks, mostly from the AMD APP SDK. Some were slightly modified to allow better benchmarking of whole-function vectorization.
project-ideas
Ideas for projects
caffe-cvprw15
:heart::coffee: Deep Learning of Binary Hash Codes for Fast Image Retrieval (CVPRW15)
torch-residual-networks
This is a Torch implementation of ["Deep Residual Learning for Image Recognition",Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun](http://arxiv.org/abs/1512.03385) the winners of the 2015 ILSVRC and COCO challenges.