EchoSign was made as part of an IBM internship project which we won with this project. It uses transfer learning on MobileNet on a hand-curated dataset of ASL images. The website for this classification was developed in Flask and it uses TTS technology for ASL text to speech conversion.
CSE204 Machine Learning Final project at Ecole Polytechnique
Production-grade MLOps pipeline for AI-generated product image detection. EfficientNet-B0, FastAPI, DVC, MLflow, Vertex AI Pipelines, Terraform, Cloud Run, Prometheus/Grafana monitoring.
An industrial-grade automated optical inspection (AOI) system for Printed Circuit Boards (PCBs). Features a computer vision pipeline for precise defect localization, a fine-tuned EfficientNetB0 model achieving 97.8% classification accuracy, and a full-stack Streamlit dashboard with real-time analytics, batch processing, and automated PDF reporting.
🔍 Deepfake Detection Platform | CNN/MTCNN, FastAPI, React | ~92% accuracy
Kaggle's plant disease image classification competition. Finetuning pre-trained CNN models, loss functions, and optimizers in order to achieve better results.
An Introductory Notebook to EfficientNet
AI web app that detects pneumonia from chest X-rays (EfficientNetB0, 91.5% accuracy)
Ahrireyes 모델 및 파일들 저장소
AI-powered document fraud detection system using EfficientNetB0 (Transfer Learning) & Flask. Classifies documents as Genuine or Fraudulent with 84%+ accuracy. Features real-time predictions, confidence scoring, and a responsive web interface. Built with TensorFlow, Keras, OpenCV & Python.
AI web app that detects and classifies 9 common skin conditions using a locally-trained PyTorch EfficientNet-B0 model alongside Google Gemini Vision for diagnosis and personalised dermatological advice.
our team techtitans was developed this project in order to help xp children using IA
Coral reef health classification using EfficientNet-B0 ensemble with Grad-CAM explainability — 98.11% accuracy. Flask + React web app & Flutter mobile app.
A CNN benchmark on TrashNet, six waste classes over 2,527 images. ResNet50, EfficientNet-B0 and MobileNetV2 compared under an imbalance-aware pipeline, fused into a soft-voting ensemble, explained with Grad-CAM.
A deep learning project for 7-class Facial Expression Recognition with post-hoc explainability using LIME and SHAP. Two CNN architectures — ResNet-50 and EfficientNet-B0 — are trained and evaluated on FER2013 and RAF-DB, with pixel-level and region-level explanations generated for every prediction.
🌿 AI-powered plant disease detection from leaf images — 38 diseases, 14 species, built with EfficientNetB4 and Flask.
Forest fire solution combining thermal/RGB cameras with optimized deep learning models (EfficientNet + MobileViT) for real-time wildfire detection in Pakistan's forests. Deployable on Raspberry Pi, featuring Grad-CAM exploitability and multi-sensor fusion to reduce false alarms.
An Image Classifier built with Transfer Learning and PyTorch that can classify images into 12 different Indian Dishes.
Plant Disease Detection Web Application using CNN BioShield AI (MobileNetV2 & EfficientNetB0) with Flask and Transfer Learning.
AI-powered skin condition analysis platform using deep learning, EfficientNetV2B0, explainable AI, and Flask.
To associate your repository with the efficientnet topic, visit your repo's landing page and select "manage topics."