Inspiration

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

What we learned

What's next for Cat Dog Classifier

Cat-Dog Classifier is a deep learning project that uses Python, PyTorch, and EfficientNet-B0 to classify images as cats or dogs. I developed the machine learning pipeline, including dataset preparation, model training, evaluation, and image prediction. I also created scripts to detect duplicate images and help reduce data leakage. The model achieved 99.88% accuracy on the test set. This project strengthened my practical understanding of deep learning, computer vision, and model evaluation.

Built With

python

Submitted to

Build, Ship, Shape: Amazon Developer Hackathon

Created by

Contributed to project documentation, PowerPoint presentation, and software testing. Helped verify functionality, identify issues, document workflows, and present the project clearly.

ANKUSH KUMAR
My contribution was focused on backend development for the Cat vs Dog image classification project. I worked on implementing the backend logic, handling image inputs, and connecting the machine learning model with the application. I also helped ensure that images were processed correctly and predictions were returned to the frontend.

Dev Kumar
Tested the Cat-Dog Classifier to verify its functionality and prediction results. Created a YouTube demo video showcasing the project, its workflow, and model performance.

Mayank Kunwar
Machine Learning Developer | Cat-Dog Classifier
- Developed and trained an EfficientNet-B0 deep learning model using PyTorch for binary image classification.
- Built dataset inspection and cleaning workflows to identify duplicate and near-duplicate images.
- Implemented model evaluation using accuracy, precision, recall, F1-score, and a confusion matrix.
- Developed an image prediction pipeline for classifying new images.
- Achieved 99.88% test-set accuracy on the evaluated dataset.

Yashaswi Sce
I Contributor Role: Model Fine-Tuning & Evaluation

- Fine-tuned the Cat vs. Dog image classification model to improve classification performance.
- Evaluated model accuracy on the validation or test dataset to assess prediction quality.
- Analyzed model predictions to identify misclassifications and areas for improvement.

Key Responsibilities: Model fine-tuning, accuracy evaluation, performance analysis, and classification validation.

Kunal Kumar

Updates

Dev Kumar posted an update — Oct 23, 2026 01:56 PM EDT

Cat Dog Classifier – Project Update

I contributed to the backend development of our Cat Dog Classifier project. My work focused on backend logic, image processing, and connecting the machine learning model with the application.

This project helped me improve my understanding of backend development, model integration, and the overall workflow of an AI/ML application.

Looking forward to improving the project further!

Dev Kumar posted an update — Oct 23, 2026 01:55 PM EDT