| | 
| 
| 
| 
# Resnet101 pretrained on BigEarthNet v2.0 using Sentinel-1 & Sentinel-2 bands
> **_NOTE:_** This version of the model has been trained with a different band order that is not compatible with the newer versions and does not match the order proposed in the technical documentation of Sentinel-2.
>
> The following bands (in the specified order) were used to train the models with version 0.1.1:
> - For models using Sentinel-1 only: Sentinel-1 bands `["VH", "VV"]`
> - For models using Sentinel-2 only: Sentinel-2 10m bands and 20m bands `["B02", "B03", "B04", "B08", "B05", "B06", "B07", "B11", "B12", "B8A"]`
> - For models using Sentinel-1 and Sentinel-2: Sentinel-2 10m bands and 20m bands and Sentinel-1 bands = `["B02", "B03", "B04", "B08", "B05", "B06", "B07", "B11", "B12", "B8A", "VH", "VV"]`
>
> Newer models are compatible with the order in the technical documentation of Sentinel-2 and were trained with the following band order:
> - For models using Sentinel-1 only: Sentinel-1 bands `["VV", "VH"]`
> - For models using Sentinel-2 only: Sentinel-2 10m bands and 20m bands `["B02", "B03", "B04", "B05", "B06", "B07", "B08", "B8A", "B11", "B12"]`
> - For models using Sentinel-1 and Sentinel-2: Sentinel-1 bands and Sentinel-2 10m bands and 20m bands `["VV", "VH", "B02", "B03", "B04", "B05", "B06", "B07", "B08", "B8A", "B11", "B12"]`
This model was trained on the BigEarthNet v2.0 (also known as reBEN) dataset using
the Sentinel-1 & 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)
- Batch size: 512
- Learning rate: 0.001
- Dropout rate: 0.15
- Drop Path rate: 0.15
- Learning rate scheduler: LinearWarmupCosineAnnealing for 1000 warmup steps
- Optimizer: AdamW
- Seed: 0
The weights published in this model card were obtained after 20 training epochs.
For more information, please visit the [official BigEarthNet v2.0 (reBEN) repository](https://git.tu-berlin.de/rsim/reben-training-scripts), where you can find the training scripts.
](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 | Macro | Micro |
|:------------------|------------------:|------------------:|
| Average Precision | 0.716136 | 0.863446 |
| F1 Score | 0.660243 | 0.768155 |
| Precision | 0.716136 | 0.863446 |
# Example
| A Sentinel-2 image (true color representation) |
|:---------------------------------------------------:|
| ](example.png) |
| Class labels | Predicted scores |
|:--------------------------------------------------------------------------|--------------------------------------------------------------------------:|
| Agro-forestry areas
Arable land
Beaches, dunes, sands
...
Urban fabric
0.000000
0.000000
0.000000
...
0.000000