PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Mini Project
Image Recognition with Pretrained CNNs in PyTorch
Fine-tunes ResNet and MobileNet to classify your own image categories
1-2 weeks build
Overview
A clear introduction to transfer learning. ImageNet-pretrained ResNet-18 and MobileNetV2 are loaded from torchvision, their final layers replaced and fine-tuned on a small labelled folder of images. The kit compares feature extraction against full fine-tuning and serves the trained model through a Streamlit page that shows the top-three predictions.
What makes it stand up
- 01Works on any ImageFolder-style dataset, CIFAR-10 included as a default
- 02Side-by-side comparison of frozen features and full fine-tuning
- 03Learning-rate scheduling and early stopping built in
- 04Grad-CAM heatmaps showing where the network looked
- 05Streamlit demo with top-three predictions and confidence bars
Module breakdown
- 01
Data loading
torchvision transforms, train/validation split and class balancing.
- 02
Model zoo
Pretrained ResNet-18 and MobileNetV2 with swapped classifier heads.
- 03
Training loop
Plain PyTorch loop with checkpointing and a scheduler.
- 04
Explainability
Grad-CAM overlays for correct and incorrect predictions.
- 05
Demo app
Streamlit upload page that runs inference on the saved model.
After this, you will be able to
- Explain what transfer learning reuses and why it needs less data
- Compare freezing layers against fine-tuning them with evidence
- Demo classification on images the examiner brings
Technology stack
- Python
- PyTorch
- torchvision
- Streamlit
- Matplotlib
- Level
- Mini Project
- Domain
- Artificial Intelligence
- Build time
- 1-2 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support