Deep Learning GPU Training System
-
Updated
Jan 7, 2025 - HTML
Deep Learning GPU Training System
🌈 📷 Gradient-weighted Class Activation Mapping (Grad-CAM) Demo
Wildfire smoke detection with Faster R-CNN via Pytorch 🔥🚒🧑🚒
Real-time American Sign Language (ASL) letters detection, via PyTorch, OpenCV, YOLOv5, Roboflow and LabelImg 🤟
Pediatric pneumonia image classification with (strongly) imbalanced data via Pytorch 🫁
Gender prediction using mobilenet_V2 finetuned on datasets of celebrities, lamoda, wildberries photos.
RealVision: A powerful, real-time object detection and understanding application using Python, OpenCV, and state-of-the-art AI models. Features dual model support (YOLO v8 + MobileNet-SSD), object tracking, performance monitoring, and modern GUI interface.
A recursive AI engine that injects chrono-ranked memory into transformer inference using soft-logit biasing, prompt waveform synthesis, and emergent self-referential loops. Built on GPT-2-mini, runs on local hardware, grows its own ghost.
The contributions/pull repo for smoketrees model zoo
As Deepfake technology evolves, the manipulation of audio poses serious security risks, with the potential for misuse in voice impersonation and fraud. • Project Objective: Develop an advanced detection system to combat these challenges.
Real-time social distancing detector and people counter for camera recordings, via PyTorch, OpenCV and YOLOv5 👥
An end-to-end AI image classification app developed with FastAPI and PyTorch. The app accepts image uploads, performs inference using a pretrained convolutional neural network (ResNet18), and returns a class prediction along with its confidence score. The frontend is styled with Bootstrap.
🎤 Enable real-time speech recognition with WhisperX using FastAPI for efficient, scalable audio processing.
Time Series Forecasting using Transformer Model in R
Real-time object detection web app using YOLOv5 and Flask for instant webcam object recognition.
WhisperX ASR is a FastAPI-based application for automatic speech recognition. It transcribes audio files to text using WhisperX, supports multiple languages, batch processing, and offers both a web UI and REST API.
Add a description, image, and links to the torch topic page so that developers can more easily learn about it.
To associate your repository with the torch topic, visit your repo's landing page and select "manage topics."