vit_spectrogram

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on a dataset containing images of Mel spectrogram belonging to the classes 'Male' and 'Female'. This model is still being fine tuned and tested. It achieves the following results on the evaluation set:

• Train Loss: 0.2893
• Train Accuracy: 0.8757
• Train Top-3-accuracy: 1.0000
• Validation Loss: 0.8757
• Validation Accuracy: 0.9366
• Validation Top-3-accuracy: 1.0
• Epoch: 1

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': 3032, '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

Framework versions

• Transformers 4.18.0
• TensorFlow 2.4.0
• Datasets 2.0.0
• Tokenizers 0.11.6