You can deploy this model and start earning money today!

feizhe/
vit-base-patch16-224-in21k-pheno-run5

Name: vit-base-patch16-224-in21k-pheno-run5
Availability: InStock

transformers

vit

image-classification

generated_from_keras_callback

google/vit-base-patch16-224-in21k

Views

No views yet

feizhe/vit-base-patch16-224-in21k-pheno-run5

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: 0.0782
Train Accuracy: 0.9985
Train Top-3-accuracy: 1.0
Validation Loss: 1.4406
Validation Accuracy: 0.5731
Validation Top-3-accuracy: 0.9298
Epoch: 2

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': 2e-05, 'decay_steps': 1615, '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
0.7826	0.7716	0.9705	1.1364	0.5965	0.9532	0
0.1564	0.9891	1.0	1.3742	0.5731	0.9181	1
0.0782	0.9985	1.0	1.4406	0.5731	0.9298	2

Framework versions

Transformers 4.31.0
TensorFlow 2.10.0
Datasets 2.18.0
Tokenizers 0.13.3