Neural networks training pipeline based on PyTorch

My repo for training neural nets using pytorch-lightning and hydra

A lightweight, open-source, and intelligent wake word detection engine. Train custom, high-accuracy models with minimal effort.

Curriculum training

YOLOv12 Underwater Object Detection is an open-source suite for underwater object detection, built on YOLOv12. It offers an end-to-end pipeline with GPU-accelerated training, customizable data augmentations, real-time inference via Gradio, and support for model export (ONNX & PyTorch).

tracebloc notebook to launch and manage experiments in collaboration

Deep Learning training and deployment pipeline, reduce repetitive work from research to deployment

This repository features an image sharpening pipeline using Knowledge Distillation. A high-capacity Restormer acts as the teacher model, while a lightweight Mini-UNet is trained as the student to mimic its performance.

Immutable checkpoint storage for ML training pipelines. Kernel-level protection, anomaly detection, score-gated rollback, and self-healing recovery. Built in Rust.

Training an image classification model with CIFAR-10 dataset

Train custom wake word models with openWakeWord. A granular 13-step pipeline with compatibility patches for torchaudio 2.10+, Piper TTS, and speechbrain. Generates tiny ONNX models (~200 KB) for real-time keyword detection — like building your own "Hey Siri" trigger. WSL2/Linux + CUDA required.

🧠 Deep-Learning Evolution: Unified collection of TensorFlow & PyTorch projects, featuring custom CUDA kernels, distributed training, memory‑efficient methods, and production‑ready pipelines. Showcases advanced GPU optimizations, from foundational models to cutting‑edge architectures. 🚀

SPIRA Model Trainer v2 (redesigned pipeline) by @danlawand

Internship projects completed as part of the Shristi24 program offered by IIIT Hyderabad

Machine Learning in Production

AI Message Labels: Packaging and pipelines for deep learning text classification models

PyTorch detailed analysis to create Machine learning to Deep learning model

Configurable PyTorch training pipeline

YoloLint is a tool for automatic validation of dataset structure, annotation files, and image sizes in YOLO projects. It helps you catch typical errors in directory structure, YAML files, annotation files, and now also ensures all your images have the correct size before you start model training.

A Modular, Production-Style ML Pipeline with Class-Imbalance Handling

Introduction To OpenLoRA: Revolutionizing the Operational Training for Large Language Models

A concurrent training and generation pipeline leveraging active learning to drive synthetic data rendering. By generating customized datasets simultaneously alongside model training, it creates a real-time feedback loop to dynamically refine object detection models.

breast cancer prediction model using PyTorch. It preprocesses the dataset, encodes labels, and trains a neural network on the features. Finally, it evaluates the model's performance on test data to classify tumors as malignant or benign.

How to build and train machine learning (ML) and deep learning (DL) models using consistent, reusable pipeline workflows

end to end classification project , to check whether chicken is healthy or affeccted with coccidiosis based on chicken fecal image collected , Model used - VGG16

A modular and fully-automated pipeline for training high-quality anime character LoRA models with Stable Diffusion. Features include video frame extraction, image cleaning, character filtering, automatic captioning, and training orchestration. Built for scalability across multiple characters and projects.

Desktop toolchain for extracting, annotating, and training YOLO models on ZED SVO2 recordings for drone target tracking

Decoder-only LLM from scratch with reproducible data pipelines, tokenizer/sharding workflows, and GPU training.

AURORA is a lightweight research-oriented AI engineering framework for multi-task NLP training, evaluation, and FastAPI deployment.

A comprehensive framework for experimenting with and comparing modern object detection models including YOLO (v5, v8) and Detectron2. Features automated setup, training pipelines, benchmarking tools, and Jupyter notebooks for computer vision research and development.