You can deploy this model and start earning money today!

aalonso-developer/
vit-base-patch16-224-in21k-euroSat

Name: vit-base-patch16-224-in21k-euroSat
Availability: InStock

generated_from_keras_callback

apache-2.0

autotrain_compatible

endpoints_compatible

Views

No views yet

aalonso-developer/vit-base-patch16-224-in21k-euroSat

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.0212
Train Accuracy: 0.9992
Train Top-3-accuracy: 1.0000
Validation Loss: 0.0613
Validation Accuracy: 0.9864
Validation Top-3-accuracy: 0.9998
Epoch: 4

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 3590, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
training_precision: mixed_float16

Training results

Train Loss	Train Accuracy	Train Top-3-accuracy	Validation Loss	Validation Accuracy	Validation Top-3-accuracy	Epoch
0.4737	0.9429	0.9862	0.1568	0.9788	0.9993	0
0.0998	0.9878	0.9996	0.1010	0.9805	0.9993	1
0.0503	0.9946	0.9999	0.0720	0.9857	0.9998	2
0.0297	0.9978	1.0000	0.0606	0.9881	0.9995	3
0.0212	0.9992	1.0000	0.0613	0.9864	0.9998	4

Framework versions

Transformers 4.29.1
TensorFlow 2.11.0
Datasets 2.12.0
Tokenizers 0.13.3