library_name: keras
Model description
Autoencoder model trained to compress information from sentinel-2 satellite images using Resnet50 V2 as decoder backbone to extract features. The latent space of the model is given by 1024 neurons which can be used to generate embeddings from the sentinel-2 satellite images.
The model was trained using bands 2, 3 and 4 of the Sentinel-2 satellites and for the full Colombia dataset.
The input shape of the model is 224, 224, 3. To extract features you should remove the last layer.
Intended uses & limitations
The model was trained with images of 81 different cities in Colombia, however it may require fine tuning or retraining to learn from other contexts such as countries and other continents.
Training and evaluation data
The model was trained with satellite images of 81 different cities in Colombia extracted from sentinel-2.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
| Hyperparameters | Value |
|---|---|
| name | Adam |
| learning_rate | 0.0010000000474974513 |
| decay | 0.0 |
| beta_1 | 0.8999999761581421 |
| beta_2 | 0.9990000128746033 |
| epsilon | 1e-07 |
| amsgrad | False |
| training_precision | float32 |