Opensource Hisilicon SoCs SDK

hisilicon sdk

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

Actively maintained ONNX Optimizer

deep learning for image processing including classification and object-detection etc.

标注自己的数据集，训练、评估、测试、部署自己的人工智能算法

PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference

[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs

OpenMMLab Model Deployment Framework

Model Compression—YOLOv3 with multi lightweight backbones(ShuffleNetV2 HuaWei GhostNet), attention, prune and quantization

INCREASING COMPACTNESS OF DEEP LEARNING BASED SPEECH ENHANCEMENT MODELS WITH PARAMETER PRUNING AND QUANTIZATION TECHNIQUES

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

🔥🔥🔥 专注于YOLOv5，YOLOv7、YOLOv8、YOLOv9改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀

yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏

Train neural networks with joint quantization and pruning on both weights and activations using any pytorch modules

PyTorch Implementation of Weights Pruning

A Keras implementation of YOLOv3 (Tensorflow backend)

A PyTorch implementation of the YOLO v3 object detection algorithm

本仓库我将使用谷歌TensorFlow2框架逐一复现经典的卷积神经网络：LeNet、AlexNet、VGG系列、GooLeNet、ResNet 系列、DenseNet 系列，以及现在比较经典的目标检测网络、语义分割网络等。

用opencv的dnn模块做yolov5目标检测，包含C++和Python两个版本的程序

最新版本yolov5+deepsort目标检测和追踪，能够显示目标类别，支持5.0版本可训练自己数据集

pytorch实现Grad-CAM和Grad-CAM++,可以可视化任意分类网络的Class Activation Map (CAM)图,包括自定义的网络;同时也实现了目标检测faster r-cnn和retinanet两个网络的CAM图;欢迎试用、关注并反馈问题...

基于小目标检测头的改进YOLOv5红外遥感图像小目标检测系统

A technical report on convolution arithmetic in the context of deep learning

ReMASC: Realistic Replay Attack Corpus for Voice Controlled Systems

SincNet is a neural architecture for efficiently processing raw audio samples.

Time-domain synthetic speech detection net (TSSDNet), having the classic ResNet and Inception Net style structures (Res-TSSDNet and Inc-TSSDNet), for end-to-end synthetic speech detection. They ach…

Resources and Implementations of Generative Adversarial Nets: GAN, DCGAN, WGAN, CGAN, InfoGAN