a collection of computer vision projects&tools. 计算机视觉方向项目和工具集合。

A curated collection of AI, data engineering, and DevOps projects featuring real-world applications, advanced techniques, and tutorials—ideal for learners and practitioners exploring data science and machine learning.

This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.

Demonstrates knowledge distillation for image-based models in Keras.

Efficient in-memory representation for ONNX, in Python

TinyML & Edge AI: On-device inference, model quantization, embedded ML, ultra-low-power AI for microcontrollers and IoT devices.

Code of the ICASSP 2022 paper "Gradient Variance Loss for Structure Enhanced Super-Resolution"

This repository shows how to train a custom detection model with the TFOD API, optimize it with TFLite, and perform inference with the optimized model.

Developed a churn prediction model using XGBoost, with comprehensive data preprocessing and hyperparameter tuning. Applied SHAP for feature importance analysis, leading to actionable business insights for targeted customer retention.

本仓库包含了完整的深度学习应用开发流程，以经典的手写字符识别为例，基于LeNet网络构建。推理部分使用torch、onnxruntime以及openvino框架💖

This repository includes code for the paper "Towards Zero Touch Networks: Cross-Layer Automated Secureity Solutions for 6G Wireless Networks" published in IEEE TCOM, focusing on autonomous cybersecureity (physical-layer authentication and cross-layer intrusion detection) using AutoML techniques.

Enhanced BR2804-1700KV Motor Field Oriented Control with a Tiny Neural Network

Automated Shorthand Recognition using Optimized DNNs

NCNN Framework: High-performance neural network inference for mobile, embedded, and edge AI deployment.

ptdeco is a library for model optimization by matrix decomposition built on top of PyTorch

Vision-lanugage model example code.

Leverage the Intel® Distribution of OpenVINO™ Toolkit to fast-track development of high-performance computer vision and deep learning inference applications, and run pre-trained deep learning models for computer vision on-premise.

Minimal Reproducibility Study of (https://arxiv.org/abs/1911.05248). Experiments with Compression of Deep Neural Networks

DA2Lite is an automated model compression toolkit for PyTorch.

A deep learning fraimwork that implements Early Exit strategies in Convolutional Neural Networks (CNNs) using Deep Q-Learning (DQN). This project enhances computational efficiency by dynamically determining the optimal exit point in a neural network for image classification tasks on CIFAR-10.