{"id":27373367,"url":"https://github.com/abdul-rafay19/cnnect-classifier","last_synced_at":"2026-04-11T13:05:29.676Z","repository":{"id":287528879,"uuid":"965026175","full_name":"abdul-rafay19/CNNect-Classifier","owner":"abdul-rafay19","description":"A real-time image classification app built with PyTorch and deployed using Streamlit. CNNect-Classifier uses a custom-trained CNN on the CIFAR-10 dataset to predict image classes with confidence scores. Designed to demonstrate end-to-end deep learning deployment — from training to user-facing web app.","archived":false,"fork":false,"pushed_at":"2025-04-12T08:57:53.000Z","size":1999,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-13T11:14:28.257Z","etag":null,"topics":["ai","artificial-intelligence","artificial-intelligence-algorithms","artificial-neural-networks","cifar-10","cifar10","cnn","cnn-classification","cnn-model","cnnect","deep-learning","machine-learning","neural-network","neural-networks","numpy","python","pytorch","pytorch-cnn","streamlit","streamlit-webapp"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/abdul-rafay19.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-04-12T08:46:13.000Z","updated_at":"2025-04-12T09:02:11.000Z","dependencies_parsed_at":"2025-04-12T09:51:22.290Z","dependency_job_id":null,"html_url":"https://github.com/abdul-rafay19/CNNect-Classifier","commit_stats":null,"previous_names":["abdul-rafay19/cnnect-classifier"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abdul-rafay19%2FCNNect-Classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abdul-rafay19%2FCNNect-Classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abdul-rafay19%2FCNNect-Classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abdul-rafay19%2FCNNect-Classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/abdul-rafay19","download_url":"https://codeload.github.com/abdul-rafay19/CNNect-Classifier/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248703200,"owners_count":21148118,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","artificial-intelligence","artificial-intelligence-algorithms","artificial-neural-networks","cifar-10","cifar10","cnn","cnn-classification","cnn-model","cnnect","deep-learning","machine-learning","neural-network","neural-networks","numpy","python","pytorch","pytorch-cnn","streamlit","streamlit-webapp"],"created_at":"2025-04-13T11:14:31.136Z","updated_at":"2025-12-30T23:05:04.677Z","avatar_url":"https://github.com/abdul-rafay19.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CNNect-Classifier\n**Abdul Rafay** | BS Software Engineering\n\nCNNect-Classifier is a deep learning-powered web application that performs real-time image classification on the CIFAR-10 dataset. Built as part of my Machine Learning Internship at Intern Intelligence, this project represents a complete end-to-end pipeline — from model training to deployment — wrapped inside a user-friendly interface.\n\nThis project started as a task but turned into something much bigger. Inspired by a post that said Streamlit is the fastest way to build AI apps and impress future employers, I took that challenge seriously. I moved beyond notebooks and built a fully functional deep learning app.\n\n## What It Does\n\n- Takes an input image via upload  \n- Runs it through a custom-trained CNN model  \n- Outputs predicted class with probability scores  \n- Provides a clean, mobile-friendly UI for interaction  \n\n## Behind the Scenes\n\n- Built a CNN from scratch using PyTorch for image classification  \n- Used convolutional layers, pooling, dropout, and fully connected layers  \n- Trained and fine-tuned the model on CIFAR-10 for optimal accuracy  \n- Switched from TensorFlow to PyTorch for smoother experimentation  \n- Deployed using Streamlit to create a real-time web interface  \n\n## Tech Stack\n\n- PyTorch  \n- Torchvision  \n- Streamlit  \n- PIL  \n- NumPy  \n- HTML/CSS  \n\n## Features\n\n- 📷 Image Upload Interface  \n- ⚡ Real-Time Predictions  \n- 📊 Class-wise Confidence Breakdown  \n- 💻 Mobile-Responsive, Minimalist UI  \n\n## Installation\n\nTo run the app locally, follow these steps:\n\n```bash\ngit clone https://github.com/YourGitHubUsername/CNNect-Classifier.git\ncd CNNect-Classifier\nstreamlit run app.py\n```\n\nMake sure you have the trained model file `cifar10_model.pt` in the same directory as `app.py`.\n\n## File Structure\n\n- `app.py` – Streamlit frontend with prediction logic  \n- `task.ipynb` – Model building and training notebook  \n- `cifar10_model.pt` – Saved PyTorch model weights (not included in repo)  \n\n## Classes Predicted\n\n- Airplane  \n- Automobile  \n- Bird  \n- Cat  \n- Deer  \n- Dog  \n- Frog  \n- Horse  \n- Ship  \n- Truck  \n\n## Why This Project Matters\n\nThis wasn’t just about training a model — it was about making machine learning usable. I learned how to bridge the gap between model performance and user experience. CNNect-Classifier represents my journey into real-world AI application development, with hands-on deployment and user-facing design.\n\n## Connect with Me\n\n📌 [LinkedIn – Abdul Rafay](https://www.linkedin.com/in/abdul-rafay19)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabdul-rafay19%2Fcnnect-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fabdul-rafay19%2Fcnnect-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabdul-rafay19%2Fcnnect-classifier/lists"}