shallowmdream Goto Github PK

bevformer_tensorrt

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

extract_rosbag

Extract the information from rosbag.

flatbuffers

FlatBuffers: Memory Efficient Serialization Library

g3log

G3log is an asynchronous, "crash safe", logger that is easy to use with default logging sinks or you can add your own. G3log is made with plain C++14 (C++11 support up to release 1.3.2) with no external libraries (except gtest used for unit tests). G3log is made to be cross-platform, currently running on OSX, Windows and several Linux distros. See Readme below for details of usage.

gflags

The gflags package contains a C++ library that implements commandline flags processing. It includes built-in support for standard types such as string and the ability to define flags in the source file in which they are used. Online documentation available at:

googletest

Googletest - Google Testing and Mocking Framework

learnight

machinelearning

My blogs and code for machine learning. http://cnblogs.com/pinard

mmdeploy

mnn

MNN is a lightweight deep neural network inference engine.

models

A collection of pre-trained, state-of-the-art models in the ONNX format

opencv

Open Source Computer Vision Library

protobuf

Protocol Buffers - Google's data interchange format

pytorch2caffe

sparse4d

tengine

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

tensorflow

An Open Source Machine Learning Framework for Everyone

tensorflow-1.11.0-cp35-cp35m-linux_aarch64

tensorrt-yolov4

tensorrt5, yolov4, yolov3,yolov3-tniy,yolov3-tniy-prn

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。

tutorials

Tutorials for creating and using ONNX models

tutorials-1

PyTorch tutorials.

vision

Datasets, Transforms and Models specific to Computer Vision

yolo-tensorrt

Support Yolov5s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.