Hugging Face's logo

Spaces:
BIFOLD-BigEarthNetv2-0
/
README
Running

App Files Community
1
hackelle commited on
Commit
7851bd7
•
1 Parent(s): afbf9b5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -45
README.md CHANGED
@@ -20,7 +20,7 @@ For Models using Sentinel-1 only: `["VH", "VV"]`
20
  For Models using Sentinel-2 only: 10m bands, 20m bands = `["B02", "B03", "B04", "B08", "B05", "B06", "B07", "B11", "B12", "B8A"]`
21
  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"]`
22
 
23
- The output classes are in alphabetical order:
24
  ['Agro-forestry areas', 'Arable land', 'Beaches, dunes, sands', 'Broad-leaved forest', 'Coastal wetlands',
25
  'Complex cultivation patterns', 'Coniferous forest', 'Industrial or commercial units', 'Inland waters',
26
  'Inland wetlands', 'Land principally occupied by agriculture, with significant areas of natural vegetation',
@@ -29,47 +29,12 @@ The output classes are in alphabetical order:
29
  'Urban fabric']
30
 
31
 
32
- ## ConvMixer
33
- [ConvMixer](https://arxiv.org/abs/2201.09792) was trained in the version with a hidden
34
- dimension of 768 and 32 layers (often called ConvMixer-768/32). The weights are available for the following versions:
35
- - [Sentinel-1 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-s1-v0.1.1)
36
- - [Sentinel-2 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-s2-v0.1.1)
37
- - [Sentinel-1 and Sentinel-2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-all-v0.1.1)
38
-
39
- ## ConvNextv2
40
- [ConvNext v2](https://openaccess.thecvf.com/content/CVPR2023/html/Woo_ConvNeXt_V2_Co-Designing_and_Scaling_ConvNets_With_Masked_Autoencoders_CVPR_2023_paper.html) was trained in the "base" configuration. The weights are available for the following versions:
41
- - [Sentinel-1 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convnextv2_base-s1-v0.1.1)
42
- - [Sentinel-2 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convnextv2_base-s2-v0.1.1)
43
- - [Sentinel-1 and Sentinel-2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convnextv2_base-all-v0.1.1)
44
-
45
- ## MLP-Mixer
46
- [MLP-Mixer](https://proceedings.neurips.cc/paper/2021/hash/cba0a4ee5ccd02fda0fe3f9a3e7b89fe-Abstract.html) was trained in the "base" configuration with a patch size of 16. The weights are available for the following versions:
47
- - [Sentinel-1 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mixer_b16_224-s1-v0.1.1)
48
- - [Sentinel-2 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mixer_b16_224-s2-v0.1.1)
49
- - [Sentinel-1 and Sentinel-2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mixer_b16_224-all-v0.1.1)
50
-
51
- ## MobileViT
52
- [MobileViT](https://arxiv.org/abs/2110.02178) was trained in the "small" configuration. The weights are available for the following versions:
53
- - [Sentinel-1 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mobilevit_s-s1-v0.1.1)
54
- - [Sentinel-2 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mobilevit_s-s2-v0.1.1)
55
- - [Sentinel-1 and Sentinel-2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mobilevit_s-all-v0.1.1)
56
-
57
- ## ResNet
58
- [ResNet](https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html) was trained in the "50" and "101" configurations.
59
- ### ResNet-50
60
- The weights for the "50" configuration are available for the following versions:
61
- - [Sentinel-1 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-s1-v0.1.1)
62
- - [Sentinel-2 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-s2-v0.1.1)
63
- - [Sentinel-1 and Sentinel-2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-all-v0.1.1)
64
-
65
- ### ResNet-101
66
- The weights for the "101" configuration are available for the following versions:
67
- - [Sentinel-1 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-s1-v0.1.1)
68
- - [Sentinel-2 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-s2-v0.1.1)
69
- - [Sentinel-1 and Sentinel-2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-all-v0.1.1)
70
-
71
- ### Vision Transformer
72
- [ViT](https://arxiv.org/abs/2010.11929) was trained in the "base" configuration with a patch size of 8. The weights are available for the following versions:
73
- - [Sentinel-1 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-s1-v0.1.1)
74
- - [Sentinel-2 only](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-s2-v0.1.1)
75
- - [Sentinel-1 and Sentinel-2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-all-v0.1.1)
 
20
  For Models using Sentinel-2 only: 10m bands, 20m bands = `["B02", "B03", "B04", "B08", "B05", "B06", "B07", "B11", "B12", "B8A"]`
21
  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"]`
22
 
23
+ The output classes are always in alphabetical order:
24
  ['Agro-forestry areas', 'Arable land', 'Beaches, dunes, sands', 'Broad-leaved forest', 'Coastal wetlands',
25
  'Complex cultivation patterns', 'Coniferous forest', 'Industrial or commercial units', 'Inland waters',
26
  'Inland wetlands', 'Land principally occupied by agriculture, with significant areas of natural vegetation',
 
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) |
35
+ | ConvNext v2 Base | `convnextv2_base` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convnextv2_base-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convnextv2_base-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convnextv2_base-all-v0.1.1) |
36
+ | MLP-Mixer Base | `mixer_b16_224` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mixer_b16_224-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mixer_b16_224-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mixer_b16_224-all-v0.1.1) |
37
+ | MobileViT-S | `mobilevit_s` | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mobilevit_s-s1-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mobilevit_s-s2-v0.1.1) | [link](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mobilevit_s-all-v0.1.1) |
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) |