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

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.

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

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

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💖

Automated Shorthand Recognition using Optimized DNNs

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.

Vision-lanugage model example code.

DA2Lite is an automated model compression toolkit for PyTorch.

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

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

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

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

A deep learning framework 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.

quantization example for pqt & qat

compares different pretrained object classification with per-layer and per-channel quantization using pytorch

Some DNN model optimization experiments and notebooks