ANIMAL CLASSIFICATION MODEL WITH MOBILENET TRANSFER LEARNING:
This repository contains a deep learning model for classifying images of cats, dogs, elephants, and giraffes. The model, built using MobileNet transfer learning, achieved an impressive 95% training accuracy and 92% validation accuracy.
TABLE OF CONTENTS:
Dataset
Model Architecture
Results
Future Work
Contributing
Citation
DATASET
The training dataset consists of a balanced collection of images for each class: cats, deers, dogs, and horses. The dataset is split into training and validation sets to evaluate the model's performance.
MODEL ARCHITECTURE
The classification model is built on top of the MobileNet architecture, a lightweight and efficient convolutional neural network (CNN) suitable for mobile and embedded vision applications.
RESULTS
The model achieved an impressive 95% accuracy on the training set and 92% accuracy on the validation set.
FUTURE WORK
Fine-tune the model to improve performance further. Explore data augmentation techniques to enhance model generalization. Extend the dataset with more diverse images of animals.
CONTRIBUTION
Contributions are welcome! If you find any issues or have suggestions, feel free to open an issue or submit a pull request.
CITATION
J H Lee, JHyun Ahn, Sanguk Park, Seunghyun Jin. (2022). 4 animal classification. Kaggle. https://kaggle.com/competitions/4-animal-classification