| { |
| "model_name": "PrithviEO", |
| "model_type": "prithvi_eo", |
| "architectures": ["PrithviEO2", "CoordinateEncoder", "Transformer"], |
| "framework": "PyTorch", |
| "domain": "earth-observation", |
| "task": "multi-temporal-remote-sensing-representation-learning", |
| "implementation": { |
| "entry_point": "model/prithvi_eo.py", |
| "scope": "engineering reproduction of the Prithvi-EO-2.0 temporal-location masked autoencoder", |
| "train_script": "scripts/train.py", |
| "inference_script": "scripts/inference.py", |
| "evaluation_script": "scripts/result.py", |
| "synthetic_data_script": "scripts/fake_data.py" |
| }, |
| "architecture": { |
| "family": "three-dimensional vision-transformer masked autoencoder", |
| "input_size": [4, 224, 224], |
| "patch_size": [1, 16, 16], |
| "in_channels": 6, |
| "mask_ratio": 0.75, |
| "encoder_dim": 96, |
| "encoder_depth": 2, |
| "encoder_heads": 4, |
| "decoder_dim": 64, |
| "decoder_depth": 1, |
| "decoder_heads": 4, |
| "metadata": ["year", "day_of_year", "latitude", "longitude"], |
| "outputs": ["loss", "embedding", "patch_embeddings", "reconstruction", "mask"] |
| }, |
| "data": { |
| "datasets": ["Harmonized Landsat Sentinel-2"], |
| "protocol": "prithvi_eo_2_synthetic_engineering_v1", |
| "format": "NPZ", |
| "train_file": "data/train.npz", |
| "test_file": "data/test.npz", |
| "input_shape": ["N", 6, 4, 224, 224], |
| "temporal_shape": ["N", 4, 2], |
| "location_shape": ["N", 2], |
| "bands": ["B02", "B03", "B04", "B8A", "B11", "B12"], |
| "required_metadata": ["format_version", "data_source", "temporal_coords", "location_coords"] |
| }, |
| "configuration_sources": ["conf/config.yaml", "model/prithvi_eo.py", "scripts/fake_data.py", "scripts/train.py", "scripts/inference.py", "scripts/result.py"] |
| } |
|
|
