effecientnetv2

🚀 Deepfake Detector – Open-source tool to spot fake images, videos & audio using EfficientNetV2 + MTCNN. ⚡ Frame-by-frame analysis for high-accuracy detection, built simple for researchers, devs & security analysts.

Deep learning system for non-invasive cardiovascular risk prediction using retinal fundus images. Hybrid EfficientNet-B3 + ViT with clinical data fusion.

Multi-modal deepfake detection system (image, video, audio) using fine-tuned EfficientNet-B4. React + Vite frontend, FastAPI + PyTorch backend, Firebase auth. Pinnacle 6 capstone at Atlas SkillTech University.

Pneumonia detection from chest X-rays using classical ML (LBP+HOG, KNN, Gradient Boosting), deep learning (custom CNN, autoencoder), transfer learning (ResNet50, VGG16, EfficientNetB0), and sequential/transformer models (RNN, LSTM, GRU, ViT). Best result: ResNet50 at 95.19% accuracy and 0.9892 ROC-AUC.

Detect fake and AI images using deep learning and FFT techniques.