Feature Extraction
Transformers
Safetensors
English
remote-sensing
earth-observation
self-supervised-learning
sentinel-2
sentinel-1
multispectral
sar
vision
ssl4eo
mae
moco
dino
data2vec
vit
resnet
Instructions to use BiliSakura/SSL4EO-S12-transformers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BiliSakura/SSL4EO-S12-transformers with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="BiliSakura/SSL4EO-S12-transformers")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BiliSakura/SSL4EO-S12-transformers", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SSL4EOData2VecModel" | |
| ], | |
| "drop_path_rate": 0.0, | |
| "dtype": "float32", | |
| "hidden_size": 384, | |
| "id2label": {}, | |
| "image_size": 224, | |
| "init_values": 0.1, | |
| "label2id": {}, | |
| "layer_norm_eps": 1e-06, | |
| "mlp_ratio": 4.0, | |
| "modality": "s2c", | |
| "model_type": "ssl4eo_data2vec", | |
| "num_attention_heads": 6, | |
| "num_channels": 13, | |
| "num_hidden_layers": 12, | |
| "patch_size": 16, | |
| "qkv_bias": true, | |
| "ssl_method": "data2vec", | |
| "transformers_version": "5.0.0", | |
| "use_abs_pos_emb": false, | |
| "use_mean_pooling": true, | |
| "use_shared_rel_pos_bias": true | |
| } | |