nvoliver

Deep-Learning-Accelerator-SW

NVIDIA DLA-SW, the recipes and tools for running deep learning workloads on NVIDIA DLA cores for inference applications.

caffe-yolov2

Cutout

2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552

DeepLabV3Plus-Pytorch

DeepLabv3, DeepLabv3+ and pretrained models on VOC & Cityscapes

docker

Docker - the open-source application container engine

onnx

Open standard for machine learning interoperability

onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

onnx2caffe

pytorch to caffe by onnx

TensorRT

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

tpu

Reference models and tools for Cloud TPUs.

nvoliver/onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

nvoliver/onnx2caffe

pytorch to caffe by onnx

nvoliver/caffe-yolov2

nvoliver/Cutout

2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552

nvoliver/DeepLabV3Plus-Pytorch

DeepLabv3, DeepLabv3+ and pretrained models on VOC & Cityscapes

nvoliver/docker

Docker - the open-source application container engine

nvoliver/onnx

Open standard for machine learning interoperability

nvoliver/TensorRT

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

nvoliver/tpu

Reference models and tools for Cloud TPUs.