Deploy your Flask web app classifier on Heroku which is written using fastai library.

Demo of Face Recognition web service

We use pretrained networks VGGnet, AlexNet, GoogLeNet, ResNet which trained on the ImageNet dataset as a feature extractor to classify images.

Detect objects from a webcam in your browser with Cloudflare Workers AI!

Django + Bootstrap + Rasa | Our project aims to develop an attractive online instruments shop for a family-owned shop to alleviate the aforementioned problems.

MAT-CNN-SOPC: Motionless Analysis of Traffic Using Convolutional Neural Networks on System-On-a-Programmable-Chip

Traffic sign classification using Resnet deep network

Explainable Speaker Recognition system

Image Style Recognition using Transfer Learning with Pre-trained ResNet

Iris Recognition in CNN ResNet

Used Car Model Classification Project

Cotton disease detection using CNN

BrainAI is an advanced web application developed to analyze, classify, and predict brain tumors. By leveraging cutting-edge technologies like data augmentation with Generative Adversarial Networks (GANs), ResNet for tumor type classification, and time series analysis for tumor growth predictions. it helps in early tumor detection.

4 competitions + bigquery(ML | SQL)

Project Website for the Deep Learning Online Seminar at University

🐮 CUAI Deep Learning Study Materials (2020.01 - 2020.03) 🧠

A web-based animal classification system using Zero-Shot Learning and ResNet, built with Flask and PyTorch. This application can classify animals in images without being explicitly trained on them, using semantic embeddings to make predictions.

Dog breed classification using AWS SageMaker. This project fine-tunes a pre-trained ResNet model with transfer learning, applies hyperparameter tuning, and leverages SageMaker Debugger and Profiler for performance optimization. The trained model is deployed to a real-time endpoint to serve image predictions.

Predict the apparent age of a person possibly in real time. The model used is pre-trained on VGG16 architecture and then trained using a convolutional neural network on the ChaLearn LAP dataset which consists of 8000 image samples. Test Accuracy achieved – 84%.

2020 FlyAI 你画我猜