Moringa IP week 10
Practice project on classification of images using tensor flow
This week we learnt about Machine Learning, specifically: Deep learning & Neural Networks. We were tasked with learning how to use tensorflow or pytorch for text/image classification.
We will be putting what we learnt to test with this dataset on classifying images of cats and dogs
We intend to find out whether we can use the independent variables to come up with an accurate classification of whether an image contains a cat or a dog.
We intend to achieve an accuracy score of at least 80%.
- Follow us to see whether we will be able to achieve an accuracy score of at least 80% or more.
- The project is summarized in Google slides
Here are the major tools that we used for the data analysis
- Google Colab
- Tableu Public
- Python
- Git
- Tensorflow
- Special thanks to Google
- Special thanks to grepper tool
- Special thanks to Moringa School
We did this analysis with the intention of improving our skills in machine learning. However, the models used in this analysis could be used for deep learning to identify the contents of an image. With a good train dataset, the code in this can be scaled to identify different characters and contents of an image
Following our analysis, we identified some gaps in the data and would like to continue improving the dashboard and analysis in order to come up with a more accurate prediction . Some of the data that would have been nice to have are:
- More variety of animals so our code could accurately identify other animals other than cats and dogs
Similar datasets for ________ in Kenya would be interesting to work on
We would love to continue improving this analysis. Please contribute.. 😃 😃
Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch
- Commit your Changes
- Push to the Branch
- Open a Pull Request
Distributed under the MIT License. See LICENSE for more information.
- Ian Tirok - Ian - [email protected]
- John Ruoro - John - [email protected]
- Kelvin Njunge - Kelvin - [email protected]
- Beatrice Kiplagat - Beaty - [email protected]