prashanth0205/vit_spectrogram

1---2license: apache-2.03tags:4- generated_from_keras_callback5model-index:6- name: vit_spectrogram7  results: []8---9 10<!-- This model card has been generated automatically according to the information Keras had access to. You should11probably proofread and complete it, then remove this comment. -->12 13# vit_spectrogram14 15This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on a dataset containing16images of Mel spectrogram belonging to the classes 'Male' and 'Female'. This model is still being fine tuned and tested.17It achieves the following results on the evaluation set:18- Train Loss: 0.2893 19- Train Accuracy: 0.8757 20- Train Top-3-accuracy: 1.000021- Validation Loss: 0.8757 22- Validation Accuracy: 0.9366 23- Validation Top-3-accuracy: 1.024- Epoch: 125 26 27## Model description28 29More information needed30 31## Intended uses & limitations32 33More information needed34 35## Training and evaluation data36 37More information needed38 39## Training procedure40 41### Training hyperparameters42 43The following hyperparameters were used during training:44- 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}45- training_precision: mixed_float1646 47### Training results48 49 50 51### Framework versions52 53- Transformers 4.18.054- TensorFlow 2.4.055- Datasets 2.0.056- Tokenizers 0.11.657