View on GitHub
Background
This project was created to explore the capabilities of image classification models using TensorFlow. The goal was to train a model to identify images of Pokémon, and then use the model to classify Pokémon images that were not included in the training dataset.
Results
The model was able to achieve an accuracy of 95% on the test dataset, and was able to correctly classify images of Pokémon that were not included in the training dataset.
Tech Stack
The model was built using the following technologies:
-
TensorFlow: TensorFlow is an open-source machine learning framework that provides a simple and efficient way to build and train machine learning models.
-
Keras: Keras is a high-level API that provides an intuitive interface for building and training machine learning models. It is built on top of TensorFlow, and provides a simple way to build and train machine learning models.
-
Python: Python is a high-level programming language that is used for a wide variety of applications, including machine learning and data science.