metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: vit-base-kidney-stone
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8133333333333334
- name: Precision
type: precision
value: 0.8451020337181513
- name: Recall
type: recall
value: 0.8133333333333334
- name: F1
type: f1
value: 0.8083110647337813
vit-base-kidney-stone
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6356
- Accuracy: 0.8133
- Precision: 0.8451
- Recall: 0.8133
- F1: 0.8083
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:
- learning_rate: 0.0002
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2529 | 0.33 | 100 | 0.6368 | 0.7996 | 0.8486 | 0.7996 | 0.8000 |
| 0.071 | 0.67 | 200 | 0.6456 | 0.8142 | 0.8425 | 0.8142 | 0.8020 |
| 0.032 | 1.0 | 300 | 0.6356 | 0.8133 | 0.8451 | 0.8133 | 0.8083 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.1
- Datasets 3.1.0
- Tokenizers 0.15.2