sachin1999-cloud / machine-learning-on-android Goto Github PK

In this project I have created a binary classifier to predict between cats and dogs using deep learning.The model is trained on around 6200 images of dataset taken from kaggle

To achieve good accuracy we have used transfer learning techniques.

I will suggest yout to use google colab gpu for model training as it is less time consuming.After training , the model is saved in tf-lite format to run on android device

This tf lite model will generate predicitons on your device

One important point-try to predict some images using your tf lite model before using it in android so that you can check whether its working fine or not.

You can download the dataset from kaggle using this link-https://www.kaggle.com/c/dogs-vs-cats/overview