shining_love's repositories
deepsort_tensorrt
This is a TensorRT based deepsort project
libtorch-yolov5
A LibTorch inference implementation of the yolov5
nutonomy_pointpillars
Convert pointpillars Pytorch Model To ONNX for TensorRT Inference
yolov5_tensorrt_int8
TensorRT int8 量化部署 yolov5s 4.0 模型,实测3.3ms一帧!
Active-learning-for-object-detection
Active learning for deep object detection using YOLO
analytics-zoo
Distributed Tensorflow, Keras and PyTorch on Apache Spark/Flink & Ray
BiPointNet
This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.
bottom-up-attention.pytorch
An PyTorch reimplementation of bottom-up-attention models
CGNet
CGNet: A Light-weight Context Guided Network for Semantic Segmentation [IEEE Transactions on Image Processing 2020]
code-samples
Source code examples from the Parallel Forall Blog
copy-paste-aug
Copy-paste augmentation for segmentation and detection tasks
cuda-samples
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
few-shot-meta-baseline
A New Meta-Baseline for Few-Shot Learning
fvcore
Collection of common code that's shared among different research projects in FAIR computer vision team.
mmdetection_libtorch
mmdetection in python训练, libtorch in c++部署
Model-Compression-Deploy
model compression and deploy. compression: 1、quantization: quantization-aware-training, 16/8/4/2-bit(dorefa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、ternary/binary(twn/bnn/xnor-net); post-training-quantization, 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization folding for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
onnx-custom-plugin
This repo demonstrates how to use plugins written in C++ with the TensorRT Python bindings and onnx Parser.
onnx-simplifier
Simplify your onnx model
OSDN
Keras implementation for the research paper "Towards Open Set Deep Networks" A Bendale, T Boult, CVPR 2016
PyTorch-CPP-1
PyTorch C++ inference with LibTorch
RepVGG_TensorRT_int8
RepVGG TensorRT int8 量化,实测推理不到1ms一帧!
tensorflow-serving-yolov3
主要对原tensorflow版本算法进行了网络修改,显示调整,数据处理等细节优化,详细说明了 从本地训练到serving端部署yolov3的整个流程,训练了Visdrone2019无人机数据集, 准确率 较高, 训练工业检测数据集(非80类中的一类),mAP为97.51,FPS在1080上测试15-20帧!
tensorrt-plugin-demo
Simple demo of tensorrt plugin
tensorrtx
Implementation of popular deep learning networks with TensorRT network definition API
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.
yolov5
YOLOv5 in PyTorch > ONNX > CoreML > TFLite
YOLOv5_NCNN
🍅 Ncnn deployment on mobile,support:YOLOv5s,YOLOv4-tiny,MobileNetV2-YOLOv3-nano,Simple-Pose,Yolact,ChineseOCR-lite,ENet,Landmark106,DBFace,MBNv2-FCN and MBNv3-Seg-small on camera.