YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Smart Visual Product Search Model
license: mit library_name: pytorch pipeline_tag: image-classification tags: - computer-vision - pytorch - efficientnet - image-classification - recommendation-system - retail-ai
Smart Visual Product Search - Product Classifier
This repository contains the custom trained EfficientNet-B0 product classification model used in the Smart Visual Product Search & Recommendation System.
Model Overview
The classifier predicts the product category from uploaded product images before retrieval and recommendation stages.
Architecture
- EfficientNet-B0
- Framework: PyTorch
- Training Device: Kaggle GPU
- Epochs: 30
- Input Size: 224x224
Supported Categories
- camera
- headphones
- keyboard
- laptop
- mobile
- monitor
- mouse
- printer
- speaker
- watch
AI Pipeline
The complete recommendation pipeline:
- YOLO detects and crops the product region
- EfficientNet classifier predicts product category
- CLIP generates semantic embeddings
- FAISS retrieves visually similar products
- RAG recommendation layer generates intelligent recommendations
Performance
- Validation Accuracy: 67.55%
- Lightweight architecture for fast inference
- Optimized for retail product retrieval
Files
| File | Description |
|---|---|
| best_product_classifier.pth | Trained EfficientNet model |
| labels.txt | Product category labels |
Tech Stack
- PyTorch
- EfficientNet-B0
- OpenCV
- NumPy
- Hugging Face Hub
Limitations
The current model supports selected retail product categories only.
Author
Aryan Gupta
B.Tech CSE (Cyber Security)
AI/ML & Data Analytics Enthusiast
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support