pytorc

基于 YOLOV5 的 3D 打印件自动分拣，包含零件拓扑特征分析

Twitter Sentiment analysis using RNS like LSTMs, GRUs and enhancing the performance with ELMo embeddings and a self-attention model

A Python-based news sentiment analysis using Hugging Face Sentiment Analysis Model and Dataset.

A text diffusion model based on DDPM operating in embedding space, generating coherent sequences by denoising continuous latent representations instead of discrete tokens.

🛰️🌲Terra_Mask 2.0 is an end-to-end computer vision project for semantic segmentation in land cover classification. It uses deep learning with PyTorch to classify features in high-resolution satellite imagery — such as buildings, woodland, water, and roads.

SandBox tuning project to generate new fake data deceptively from real data

Code for ASD-FEAT: a multi-modal, video-derived infant dataset for early ASD risk prediction. Two-stage pipeline — transformer behavior detection (look-face, look-object, smile, vocalization) followed by risk classification on per-session aggregate features.

Deep Learning models from basics

Img2img translation of pizza images using GANs (cyclegan,pix2pix,variant of cycle gan)

PPO-GNN framework for stochastic fuel delivery optimization. Achieves 1.9% optimality gap with 40× speedup vs exact solvers.

Application to train a CNN to classify flowers using pytorch and a pretrained model from torchvision and make predictions on new images.

Computer vision system for tyre defect detection — MobileNetV2, 89.6% accuracy, Streamlit dashboard

A Simple Chat Bot App in PyTorch | Graduation Project 2025

An object detection application built with Python and PyTorch using YOLOv5 to identify items, calculate confidence scores, and save labeled visual outputs.

This project explores multimodal AI for content creators, combining audio and video streams to automatically classify events and provide intelligent insights.

An unforced, asynchronous 3D Navier-Stokes & Euler operator engine implementing runtime verification of finite-time blow-up attractors in Sobolev spaces, bypasses Python's lack of Tail-Call Optimization (TCO), eliminates heap allocation churn, and delivers deterministic O(1) space complexity for infinite data streams and complex PDEs.

Multi-dimensional Image-to-Image

A controlled study of YOLO11 input resolution (640 vs. 800) for pulmonary opacity detection in chest X-rays, evaluating detection accuracy, size-based recall, and efficiency.

some practise codes on machine learning and courses assignments

Next-day stock direction classifier using a Gradient Boosted ensemble trained on fused TF-IDF headline embeddings and 19 engineered OHLCV features. Built with Python, scikit-learn, and PostgreSQL