xingjinglu Goto Github PK

nmt

TensorFlow Neural Machine Translation Tutorial

notedown

Markdown <=> IPython Notebook

numa-stream

The classic STREAM benchmark, extended to measure NUMA effects.

onnx-simplifier

Simplify your onnx model

onnxruntime_utils

openai-gemm

Open single and half precision gemm implementations

opencl

My custom OpenCL samples

openframeworks

openFrameworks is a community-developed cross platform toolkit for creative coding in C++.

parac-testcase

parafinder

parafinder-hash

pdf-books

:books: PDF 书籍库

perfailibs

petabricks

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-mobilenet

PyTorch MobileNet Implementation of "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications"

pytorch-mobilenet-v3

MobileNetV3 in pytorch and ImageNet pretrained models

pytorch2onnx_custom_op

qnnpack

Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators

reference

Reference implementations of MLPerf benchmarks

runtime

A performant and modular runtime for TensorFlow

skimcaffe

Caffe for Sparse Convolutional Neural Network

sparseconvnet

Submanifold sparse convolutional networks

sparseconvnet-1

Spatially-sparse convolutional networks. Allows processing of sparse 2, 3 and 4 dimensional data.Build CNNs on the square/cubic/hypercubic or triangular/tetrahedral/hyper-tetrahedral lattices.

tengine

Tengine is a lite, high performance, modular inference engine for embedded device

tensor2tensor

A library for generalized sequence to sequence models

tensorflow

An Open Source Machine Learning Framework for Everyone

tflite2onnx

Convert TensorFlow Lite models (*.tflite) to ONNX.

tnn

TNN：由腾讯优图实验室打造，移动端高性能、轻量级推理框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推理框架进一步完善。

turingas

Assembler for NVIDIA Volta and Turing GPUs