Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,10 @@ license: mit
|
|
9 |
short_description: Official Repository of Pretrained Models on BigEarthNet v2.0
|
10 |
---
|
11 |
|
|
|
|
|
|
|
|
|
12 |
# BigEarthNetv2.0 Pretrained Weights
|
13 |
We provide pretrained weights for several different models.
|
14 |
All models were trained with different seeds.
|
@@ -16,9 +20,9 @@ The weights for the best-performing model (based on Macro Average Precision on t
|
|
16 |
All models are available as versions using Sentinel-1 only, Sentinel-2 only or Sentinel-1 and Sentinel-2 data.
|
17 |
|
18 |
The order of bands is as follows:
|
19 |
-
For
|
20 |
-
For
|
21 |
-
For
|
22 |
|
23 |
The output classes are always in alphabetical order:
|
24 |
['Agro-forestry areas', 'Arable land', 'Beaches, dunes, sands', 'Broad-leaved forest', 'Coastal wetlands',
|
@@ -29,6 +33,8 @@ The output classes are always in alphabetical order:
|
|
29 |
'Urban fabric']
|
30 |
|
31 |
|
|
|
|
|
32 |
| Model | equivalent [`timm`](https://huggingface.co/docs/timm/en/index) model name | Sentinel-1 only | Sentinel-2 only | Sentinel-1 and Sentinel-2 |
|
33 |
|:-----------------|:---------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
|
34 |
| ConvMixer-768/32 | `convmixer_768_32` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-all-v0.1.1) |
|
@@ -38,3 +44,40 @@ The output classes are always in alphabetical order:
|
|
38 |
| ResNet-50 | `resnet50` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-all-v0.1.1) |
|
39 |
| ResNet-101 | `resnet101` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-all-v0.1.1) |
|
40 |
| ViT Base | `vit_base_patch8_224` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-all-v0.1.1) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
short_description: Official Repository of Pretrained Models on BigEarthNet v2.0
|
10 |
---
|
11 |
|
12 |
+
[TU Berlin](https://www.tu.berlin/) | [RSiM](https://rsim.berlin/) | [DIMA](https://www.dima.tu-berlin.de/menue/database_systems_and_information_management_group/) | [BigEarth](http://www.bigearth.eu/) | [BIFOLD](https://bifold.berlin/)
|
13 |
+
:---:|:---:|:---:|:---:|:---:
|
14 |
+
<a href="https://www.tu.berlin/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/tu-berlin-logo-long-red.svg" style="font-size: 1rem; height: 2em; width: auto" alt="TU Berlin Logo"/> | <a href="https://rsim.berlin/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/RSiM_Logo_1.png" style="font-size: 1rem; height: 2em; width: auto" alt="RSiM Logo"> | <a href="https://www.dima.tu-berlin.de/menue/database_systems_and_information_management_group/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/DIMA.png" style="font-size: 1rem; height: 2em; width: auto" alt="DIMA Logo"> | <a href="http://www.bigearth.eu/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/BigEarth.png" style="font-size: 1rem; height: 2em; width: auto" alt="BigEarth Logo"> | <a href="https://bifold.berlin/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/BIFOLD_Logo_farbig.png" style="font-size: 1rem; height: 2em; width: auto; margin-right: 1em" alt="BIFOLD Logo">
|
15 |
+
|
16 |
# BigEarthNetv2.0 Pretrained Weights
|
17 |
We provide pretrained weights for several different models.
|
18 |
All models were trained with different seeds.
|
|
|
20 |
All models are available as versions using Sentinel-1 only, Sentinel-2 only or Sentinel-1 and Sentinel-2 data.
|
21 |
|
22 |
The order of bands is as follows:
|
23 |
+
For models using Sentinel-1 only: `["VH", "VV"]`
|
24 |
+
For models using Sentinel-2 only: 10m bands, 20m bands = `["B02", "B03", "B04", "B08", "B05", "B06", "B07", "B11", "B12", "B8A"]`
|
25 |
+
For models using Sentinel-1 and Sentinel-2: 10m bands, 20m bands, S1 bands = `["B02", "B03", "B04", "B08", "B05", "B06", "B07", "B11", "B12", "B8A", "VH", "VV"]`
|
26 |
|
27 |
The output classes are always in alphabetical order:
|
28 |
['Agro-forestry areas', 'Arable land', 'Beaches, dunes, sands', 'Broad-leaved forest', 'Coastal wetlands',
|
|
|
33 |
'Urban fabric']
|
34 |
|
35 |
|
36 |
+
![[BigEarthNet](http://bigearth.net/)](https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/combined_2000_600_2020_0_wide.jpg)
|
37 |
+
|
38 |
| Model | equivalent [`timm`](https://huggingface.co/docs/timm/en/index) model name | Sentinel-1 only | Sentinel-2 only | Sentinel-1 and Sentinel-2 |
|
39 |
|:-----------------|:---------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
|
40 |
| ConvMixer-768/32 | `convmixer_768_32` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-all-v0.1.1) |
|
|
|
44 |
| ResNet-50 | `resnet50` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-all-v0.1.1) |
|
45 |
| ResNet-101 | `resnet101` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-all-v0.1.1) |
|
46 |
| ViT Base | `vit_base_patch8_224` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-all-v0.1.1) |
|
47 |
+
![[BigEarthNet](http://bigearth.net/)](https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/combined_2000_600_2020_0_wide.jpg)
|
48 |
+
|
49 |
+
To use the model, download the codes that define the model architecture from the
|
50 |
+
[official BigEarthNet v2.0 (reBEN) repository](https://git.tu-berlin.de/rsim/reben-training-scripts) and load the model
|
51 |
+
using the code below. Note that you have to install [`configilm`](https://pypi.org/project/configilm/) to use the
|
52 |
+
provided code.
|
53 |
+
|
54 |
+
```python
|
55 |
+
from reben_publication.BigEarthNetv2_0_ImageClassifier import BigEarthNetv2_0_ImageClassifier
|
56 |
+
|
57 |
+
model = BigEarthNetv2_0_ImageClassifier.from_pretrained("path_to/huggingface_model_folder")
|
58 |
+
```
|
59 |
+
|
60 |
+
e.g.
|
61 |
+
|
62 |
+
```python
|
63 |
+
from reben_publication.BigEarthNetv2_0_ImageClassifier import BigEarthNetv2_0_ImageClassifier
|
64 |
+
|
65 |
+
model = BigEarthNetv2_0_ImageClassifier.from_pretrained(
|
66 |
+
"BIFOLD-BigEarthNetv2-0/resnet50-s2-v0.1.1")
|
67 |
+
```
|
68 |
+
|
69 |
+
If you use any of these models in your research, please cite the following papers:
|
70 |
+
```bibtex
|
71 |
+
CITATION FOR DATASET PAPER
|
72 |
+
```
|
73 |
+
```bibtex
|
74 |
+
@article{hackel2024configilm,
|
75 |
+
title={ConfigILM: A general purpose configurable library for combining image and language models for visual question answering},
|
76 |
+
author={Hackel, Leonard and Clasen, Kai Norman and Demir, Beg{\"u}m},
|
77 |
+
journal={SoftwareX},
|
78 |
+
volume={26},
|
79 |
+
pages={101731},
|
80 |
+
year={2024},
|
81 |
+
publisher={Elsevier}
|
82 |
+
}
|
83 |
+
```
|