Image Segmentation
Transformers
Safetensors
actu
feature-extraction
climate
geospatial
remote-sensing
spatiotemporal
multi-modal
earth-observation
time-series
hydrology
custom_code
Instructions to use DarthReca/actu-change-detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DarthReca/actu-change-detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="DarthReca/actu-change-detection", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DarthReca/actu-change-detection", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "act_layer": "identity", | |
| "architectures": [ | |
| "ACTUForImageSegmentation" | |
| ], | |
| "backbone": "convnextv2_base", | |
| "batch_first": true, | |
| "bias": true, | |
| "bidirectional": false, | |
| "climate": false, | |
| "climate_input_dim": 6, | |
| "climate_seq_len": 5, | |
| "dem": false, | |
| "feature_dim": 512, | |
| "hidden_channels": 64, | |
| "in_channels": 6, | |
| "kernel_size": 3, | |
| "lr": 5e-06, | |
| "lstm_hidden_dim": 128, | |
| "model_type": "actu", | |
| "n_classes": 2, | |
| "num_lstm_layers": 1, | |
| "original_resolution": [ | |
| 256, | |
| 256 | |
| ], | |
| "padding": 1, | |
| "skip_connections": true, | |
| "stride": 1, | |
| "target_length": 1, | |
| "task": "segmentation", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.53.2", | |
| "use_climate_branch": false, | |
| "use_dem_input": false, | |
| "auto_map": { | |
| "AutoModel": "modeling_actu.ACTUForImageSegmentation", | |
| "AutoConfig": "modeling_actu.ACTUConfig" | |
| } | |
| } | |