Guldeniz/vit-base-patch16-224-in21k-lung_and_colon

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->

Guldeniz/vit-base-patch16-224-in21k-lungandcolon

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on Lung and Colon Histopathological Images dataset. This dataset can be reach via Kaggle. It achieves the following results on the evaluation set:

• —Train Loss: 0.0088
• —Train Accuracy: 1.0
• —Train Top-3-accuracy: 1.0
• —Validation Loss: 0.0084
• —Validation Accuracy: 0.9997
• —Validation Top-3-accuracy: 1.0
• —Epoch: 3

Model description

The vision transformer model, trained by Google, has been fine-tuned using a lung and colon cancer image dataset consisting of a total of 25,000 images across 5 labels. The obtained results are highly promising, and the model demonstrates the ability to predict the following listed labels.

• —colon_aca

• —colon_n

• —lung_aca

• —lung_n

• —lung_scc

Training hyperparameters

The following hyperparameters were used during training:

• —optimizer: {'name': 'AdamWeightDecay', 'learningrate': {'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 3e-05, 'decaysteps': 3325, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weightdecay_rate': 0.01}
• —training_precision: float32

Training results

Framework versions

• —Transformers 4.26.1
• —TensorFlow 2.12.0
• —Datasets 2.10.1
• —Tokenizers 0.13.3