https://github.com/gellanz/lego_minifigures_classification
Project to learn data augmentation honing my Tensorflow skills
https://github.com/gellanz/lego_minifigures_classification
computer-vision data-augmentation python tensorflow
Last synced: 3 months ago
JSON representation
Project to learn data augmentation honing my Tensorflow skills
- Host: GitHub
- URL: https://github.com/gellanz/lego_minifigures_classification
- Owner: gellanz
- Created: 2022-04-13T20:40:38.000Z (about 4 years ago)
- Default Branch: master
- Last Pushed: 2022-04-13T20:41:47.000Z (about 4 years ago)
- Last Synced: 2025-10-08T03:20:56.879Z (9 months ago)
- Topics: computer-vision, data-augmentation, python, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 51 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.MD
Awesome Lists containing this project
README
This project was done with the following [Kaggle dataset](https://www.kaggle.com/datasets/ihelon/lego-minifigures-classification). It consist of 37 different LEGO figures (classes) with a total of 405 images, these are quite a few for a computer vision problem, so I learned how to do data augmentation using Tensorflow.
Another thing to note is that the data from Kaggle has a different tree structure, I changed it using some Python modules like `pandas`, `os` and `shutil`, the `processing_data.ipynb` notebook show how it was done in order to have the tree structure in the `data` directory. I did it this way for Tensorflow to load more easily the images nd the belonging class.