Skip to content

blacckbeard4/CatsnDogs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 

Repository files navigation

🐶🐱 Cats vs Dogs - Image Classification

Welcome to my submission for the Kaggle Dogs vs. Cats Redux classification challenge!

This project demonstrates how to build progressively better deep learning models to distinguish between images of cats and dogs. The final submission predicts the probability that an image contains a dog — evaluated via log loss on Kaggle.


🎯 Objective

Develop a binary classifier that assigns a probability score to each test image, indicating whether it's a dog (1.0) or a cat (0.0).


🔍 Sample Visuals

📷 Sample Training Images

image image image image image image

🧠 Approach

🏗️ Baseline CNN (Keras)

  • Custom ConvNet trained from scratch
  • Data augmentation: horizontal flip, zoom
  • 5-epoch training with early stopping
  • Achieved ~0.25 log loss on validation

📦 Transfer Learning (EfficientNet)

  • Pretrained embeddings from EfficientNet
  • Classical neural net on top of frozen features
  • Faster convergence, better generalization

📦 Dataset

  • Source: Provided by Kaggle
  • Training images: 25,000 JPEGs in the format cat.123.jpg or dog.456.jpg
  • Test images: Unlabeled set used for leaderboard submission

🛠️ Tools & Libraries

  • Python, TensorFlow/Keras
  • EfficientNet-PyTorch
  • Matplotlib, Seaborn, OpenCV
  • Jupyter Notebooks, Kaggle Kernels

📊 Results

Model Log Loss Accuracy (Val)
Baseline CNN ~0.25 ~90%
EfficientNet Model ~0.18 ~93%

🧠 Key Learnings

  • Data augmentation helps mitigate overfitting on small image datasets.
  • Transfer learning (with EfficientNet) improves performance and training time.
  • Simple binary classification pipelines can still be highly effective with the right preprocessing.

📬 Contact

Made with ❤️ by Justin Varghese
Feel free to fork, star, or reach out if you liked this repo!

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published