| | 
| 
| 
| 
# Resnet18 pretained on BigEarthNet v2.0 using Sentinel-2 bands
This model was trained on the BigEarthNet v2.0 (also known as reBEN) dataset using the Sentinel-2 bands.
It was trained using the following parameters:
- Number of epochs: up to 100
- with early stopping
- after 5 epochs of no improvement
- based on validation average precision (macro)
- the weights published in this model card were obtained after 2 training epochs
- Batch size: 512
- Learning rate: 0.001
- Dropout rate: 0.375
- Drop Path rate: 0.0
- Learning rate scheduler: LinearWarmupCosineAnnealing for 10_000 warmup steps
- Optimizer: AdamW
- Seed: 42
The model was trained using the training script of the
[official BigEarthNet v2.0 (reBEN) repository](https://git.tu-berlin.de/rsim/reben-training-scripts).
See details in this repository for more information on how to train the model given the parameters above.
](https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/combined_2000_600_2020_0_wide.jpg)
The model was evaluated on the test set of the BigEarthNet v2.0 dataset with the following results:
| Metric | Value Macro | Value Micro |
|:------------------|------------------:|------------------:|
| Average Precision | 0.257880 | 0.257172 |
| F1 Score | 0.215393 | 0.388090 |
| Precision | 0.218440 | 0.267895 |
# Example
| Example Input (only RGB bands from Sentinel-2) |
|:---------------------------------------------------:|
| ](example.png) |
| Example Output - Labels | Example Output - Scores |
|:--------------------------------------------------------------------------|--------------------------------------------------------------------------:|
| Agro-forestry areas
Arable land
Beaches, dunes, sands
...
Urban fabric
0.000000
1.000000
0.004683
...
1.000000