GitHub - SamH135/dog-breed-image-classifier: Image classifier for dog breeds using EfficientNetB3 pre-trained model and transfer learning. The model achieves 94.8% training accuracy and 90% validation accuracy across 120 dog breeds. Features automatic pipeline for data loading, augmentation, training and evaluation using TensorFlow/Keras.

SamH135 / dog-breed-image-classifier Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Image classifier for dog breeds using EfficientNetB3 pre-trained model and transfer learning. The model achieves 94.8% training accuracy and 90% validation accuracy across 120 dog breeds. Features automatic pipeline for data loading, augmentation, training and evaluation using TensorFlow/Keras.

0 stars 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
DogBreed_Classifier.ipynb		DogBreed_Classifier.ipynb
Image Classifier Output.pdf		Image Classifier Output.pdf
README.txt		README.txt

Repository files navigation

Dataset: https://www.kaggle.com/c/dog-breed-identification

Instructions:
You can find our notebook named "DogBreed_Classifier.ipynb" which contains all the code for the model. In order to run the code, run each cell block in sequential order (in Google Colab). All the necessary files/data will be automatically downloaded off a public GitHub repository.

Output file:
The file "Image Classifier Output" contains all the output statistics/plots pertaining to the project. You can also refer to specific cell blocks within the notebook file for further analysis.

NOTE: Running the notebook file requires a lot of Google Colab tokens (if you're running it on Colab). Your run may be interrupted if you use the base version of Google Colab.