🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.

DataFlex is a data-centric training framework that enhances model performance by either selecting the most influential samples, optimizing their weights, or adjusting their mixing ratios.

PyTorch model training and layer saturation monitor

A script that can be used to capture various porn novels for machine learning / 一个可以用于抓取各类色情小说用于机器学习的脚本

Simplified Deep Image Matting training code with keras on tensorflow

Experiments with Model Training, Deployment & Monitoring

Fine-tune LLMs and ML models with automatic dataset conversion, hyperparameter sweeps, and custom RL environments

skrobot is a Python module for designing, running and tracking Machine Learning experiments / tasks. It is built on top of scikit-learn framework.

Implements an entire machine learning pipeline to train and evaluate a Random Forest Classifier on labeled gait data for walking. Data generated during the experiment has led to helpful insights in to the problem domain.

A Streamlit-powered machine learning playground that automatically detects classification or regression tasks, builds pipelines with preprocessing, trains models interactively, and visualizes metrics using Plotly. Backward-compatible, fully responsive, and deployable on Streamlit Cloud or Docker.

Implementation of TSDS: Data Selection for Task-Specific Model Finetuning. An optimal-transport framework for selecting domain-specific and task-specific training data to improve LLM finetuning and instruction tuning.

🍎 Fruit & vegetable image classifier using TensorFlow CNN. 18 categories, Streamlit web app, Jupyter training notebooks, modular Python code. Learn computer vision & deep learning. Automated preprocessing, metrics visualization, easy deployment. Educational ML project with clean architecture.

A working prototype is implemented for machine learning based ticket assignment that can suggest who is suitable for what type of ticket by taking ticket descriptions as input. This machine learning prototype is implemented using Python and Machine Learning with past records of the ticket assignment data for model training.

python script to download & process data to train a speech-synthesis model of Vietnamese M.C. Nguyễn Ngọc Ngạn

This is a capstone project associated with MLOps Zoomcamp. The end goal of the project is to build an end-to-end machine learning project containing feature engineering, training, validation, tracking, modeel deployment, hosting, and general engineering best practices aimed at making house price predictions.

Code for paper "Accelerating Federated Learning for IoT in Big Data Analytics with Pruning, Quantization and Selective Updating"

Bittensor Subnet for crypto prediction, including TAO, BTC, ETH so on...

🚀 Accelerate your AI projects with flashtensors, a fast inference engine that loads large models on a single GPU in under 2 seconds.

Containerized image classification training utility with Streamlit-based interface designed to choose between common architectures and optimizers for quick hyperparameter tuning.