Skip to content

Kaizen0AI/mini-MobileNet-v2

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

Mini MobileNetV2

A simplified MobileNetV2 implementation built from scratch in TensorFlow for CIFAR-10 classification.

Concepts Implemented

  • Depthwise Separable Convolutions
  • Inverted Residual Blocks
  • Linear Bottlenecks
  • Residual Connections
  • Batch Normalization
  • Data Augmentation

Dataset

  • CIFAR-10
  • 10 classes
  • 32x32 RGB images

Results

Experiment Test Accuracy
Baseline 65.5%
+ Data Augmentation 66.8%

Future Improvements

  • Dropout
  • Learning Rate Scheduling
  • Transfer Learning with MobileNetV2

Project Status

✅ Completed

This project was built to implement and understand the core ideas behind MobileNetV2 from scratch on CIFAR-10.

Key learnings:

  • Depthwise separable convolutions
  • Inverted residual bottlenecks
  • Residual connections
  • Data augmentation
  • Bias-variance analysis

Future work:

  • Transfer learning with pretrained MobileNetV2

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors