https://github.com/lucashoeft/intelligent-data-analysis-2-project
Multiclass image classification of the EuroSAT satellite image dataset with convolutional neural network (CNN) and a pre-trained residual network (ResNet50) using transfer learning
https://github.com/lucashoeft/intelligent-data-analysis-2-project
cnn eurosat keras resnet sklearn tensorflow
Last synced: about 1 month ago
JSON representation
Multiclass image classification of the EuroSAT satellite image dataset with convolutional neural network (CNN) and a pre-trained residual network (ResNet50) using transfer learning
- Host: GitHub
- URL: https://github.com/lucashoeft/intelligent-data-analysis-2-project
- Owner: lucashoeft
- Created: 2023-01-07T13:06:52.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-01-20T14:40:12.000Z (5 months ago)
- Last Synced: 2025-05-07T08:57:10.470Z (about 1 month ago)
- Topics: cnn, eurosat, keras, resnet, sklearn, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 156 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Intelligent-Data-Analysis-2-Project
The final project for the course 'Intelligent Data Analysis & Machine Learning II' at the University of Potsdam. The given task was to apply learned methods from the course on a self-chosen data set from kaggle. I chose a data set of Sentinel-2 satellite imagery of 10 classes with a total of 27k labeled images. The goal was to predict the right class labels for the given input images.
For prediction of the classes, I used a simple and an advanced convolutional neural network (CNN) and the ResNet50 with transfer learning. As a result the pre-trained ResNet50 outperforms all other models by far.
## Dataset
EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification (Vol. 12, Number 7, pp. 2217–2226). Zenodo. [https://doi.org/10.5281/zenodo.7711810](https://doi.org/10.5281/zenodo.7711810)