|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: vit-base-patch16-224 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9033333333333333 |
|
- name: Precision |
|
type: precision |
|
value: 0.892075919335706 |
|
- name: Recall |
|
type: recall |
|
value: 0.9033333333333333 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# vit-base-patch16-224 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co./google/vit-base-patch16-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2446 |
|
- Accuracy: 0.9033 |
|
- Precision: 0.8921 |
|
- Recall: 0.9033 |
|
- F1 Score: 0.8889 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:| |
|
| No log | 1.0 | 4 | 0.5037 | 0.8667 | 0.8150 | 0.8667 | 0.8224 | |
|
| No log | 2.0 | 8 | 0.3500 | 0.8708 | 0.7584 | 0.8708 | 0.8107 | |
|
| No log | 3.0 | 12 | 0.3154 | 0.8708 | 0.7584 | 0.8708 | 0.8107 | |
|
| 0.5284 | 4.0 | 16 | 0.2974 | 0.8833 | 0.8659 | 0.8833 | 0.8497 | |
|
| 0.5284 | 5.0 | 20 | 0.2954 | 0.8875 | 0.8731 | 0.8875 | 0.8768 | |
|
| 0.5284 | 6.0 | 24 | 0.2721 | 0.8958 | 0.8871 | 0.8958 | 0.8716 | |
|
| 0.5284 | 7.0 | 28 | 0.2679 | 0.8875 | 0.8817 | 0.8875 | 0.8527 | |
|
| 0.3362 | 8.0 | 32 | 0.2634 | 0.8875 | 0.8817 | 0.8875 | 0.8527 | |
|
| 0.3362 | 9.0 | 36 | 0.2507 | 0.9042 | 0.8953 | 0.9042 | 0.8879 | |
|
| 0.3362 | 10.0 | 40 | 0.2439 | 0.9083 | 0.9006 | 0.9083 | 0.8941 | |
|
| 0.3362 | 11.0 | 44 | 0.2589 | 0.8917 | 0.8861 | 0.8917 | 0.8884 | |
|
| 0.3017 | 12.0 | 48 | 0.2428 | 0.9083 | 0.9005 | 0.9083 | 0.9024 | |
|
| 0.3017 | 13.0 | 52 | 0.2543 | 0.9 | 0.8949 | 0.9 | 0.8970 | |
|
| 0.3017 | 14.0 | 56 | 0.2651 | 0.8958 | 0.8944 | 0.8958 | 0.8951 | |
|
| 0.278 | 15.0 | 60 | 0.2637 | 0.8958 | 0.8944 | 0.8958 | 0.8951 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
