{"id":35137403,"url":"https://github.com/deepvamja/bug_vision_ai","last_synced_at":"2026-05-21T06:03:11.881Z","repository":{"id":330586733,"uuid":"1123238505","full_name":"Deepvamja/Bug_Vision_AI","owner":"Deepvamja","description":null,"archived":false,"fork":false,"pushed_at":"2025-12-26T15:25:10.000Z","size":13544,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-28T02:24:13.948Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/Deepvamja.png","metadata":{"files":{"readme":"README.txt","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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-26T13:08:30.000Z","updated_at":"2025-12-26T15:25:13.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Deepvamja/Bug_Vision_AI","commit_stats":null,"previous_names":["deepvamja/bug_vision_ai"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Deepvamja/Bug_Vision_AI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepvamja%2FBug_Vision_AI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepvamja%2FBug_Vision_AI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepvamja%2FBug_Vision_AI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepvamja%2FBug_Vision_AI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Deepvamja","download_url":"https://codeload.github.com/Deepvamja/Bug_Vision_AI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepvamja%2FBug_Vision_AI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33290928,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-21T02:57:32.698Z","status":"ssl_error","status_checked_at":"2026-05-21T02:57:31.990Z","response_time":62,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":[],"created_at":"2025-12-28T09:59:03.259Z","updated_at":"2026-05-21T06:03:11.869Z","avatar_url":"https://github.com/Deepvamja.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"🐞 BugVision AI\n\nIntelligent Bug Screenshot Classification \u0026 Explainability System\n\nBugVision AI is a production-style deep learning system that automatically classifies software bug screenshots into real-world error categories and explains why the model made each decision using visual heatmaps.\n\n🚀 The Problem (Real \u0026 Industrial):\n\nIn modern software teams:\n\nQA engineers report bugs using screenshots\n\nDevelopers manually read and triage bugs\n\nLarge teams receive hundreds of screenshots daily\n\nBug categorization becomes slow, error-prone, and inconsistent\n\n❌ Manual triaging\n❌ Delayed debugging\n❌ No visibility into recurring bug patterns\n\nBugVision AI solves this by automating bug classification using computer vision.\n\n\n💡 The Solution\n\n🧠 What BugVision AI Does\n\n✔️ Accepts bug screenshots as input\n\n✔️ Classifies them into 6 real-world error types\n\n✔️ Generates confidence scores\n\n✔️ Explains predictions using Grad-CAM heatmaps\n\n✔️ Stores prediction history\n\n✔️ Provides an analytics dashboard\n\n✔️ Runs as a full-stack deployed application\n\n\n\n🏷️ Supported Bug Categories\n\nClass\t               Description\n\nUI_Error\t         Layout issues, misaligned buttons, broken UI elements\n\nDatabase_Error\t   SQL errors, DB connection failures\n\nNetwork_Error\t   Timeouts, connectivity issues\n\nRendering_Error\t   Graphics glitches, blank screens\n\nCrash_Error  \t   App crashes, fatal error screens\n\nOther_Error\t         Unclassified or rare error types\n\n\n✨ Key Features\n\n🧠 Automated Bug Triage\n\nAutomatically categorizes bug screenshots into real-world error types, eliminating manual inspection and reducing triage time.\n\n🔍 Explainable AI for Trust \u0026 Debugging\n\nGenerates Grad-CAM heatmaps that visually explain model decisions, helping engineers verify predictions instead of blindly trusting AI.\n\n⚙️ Production-Ready Inference Pipeline\n\nImplements a complete ML inference workflow including preprocessing, prediction, confidence scoring, and result rendering — mirroring real production systems.\n\n📊 Engineering Analytics Dashboard\n\nTracks prediction history and class distributions, enabling teams to identify recurring bug patterns and systemic issues.\n\n🗃️ Persistent Prediction Logging\n\nStores inference results with timestamps, supporting auditing, debugging, and future model improvements.\n\n\n🧩 System Architecture\n\nUser Screenshot\n      ↓\nImage Preprocessing (256×256 RGB)\n      ↓\nCNN-based Deep Learning Model\n      ↓\nSoftmax Probability Distribution\n      ↓\nGrad-CAM Explainability\n      ↓\nFlask Web Application\n      ↓\nPrediction Logging + Dashboard\n\n\n\n🛠️ Tech Stack\n\nML / DL: TensorFlow, CNN, Grad-CAM\nBackend: Python, Flask\nComputer Vision: OpenCV, NumPy\nData: SQLite\n\n\n\nHOW TO RUN LOCALLY\n------------------\n1. Create virtual environment (optional but recommended)\n   python -m venv venv\n\n2. Activate environment\n   (Windows) venv\\Scripts\\activate\n   (Mac/Linux) source venv/bin/activate\n\n3. Install dependencies\n   pip install -r requirements.txt\n\n4. Run Flask server\n   python app/app.py\n\n5. Open in browser:\n   http://127.0.0.1:5000\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepvamja%2Fbug_vision_ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeepvamja%2Fbug_vision_ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepvamja%2Fbug_vision_ai/lists"}