|
--- |
|
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: 0.8033333333333333 |
|
- name: Precision |
|
type: precision |
|
value: 0.7988653846153846 |
|
- name: Recall |
|
type: recall |
|
value: 0.8033333333333333 |
|
--- |
|
|
|
<!-- 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: 0.4775 |
|
- Accuracy: 0.8033 |
|
- Precision: 0.7989 |
|
- Recall: 0.8033 |
|
- F1 Score: 0.7784 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:| |
|
| No log | 1.0 | 8 | 0.5941 | 0.7333 | 0.5378 | 0.7333 | 0.6205 | |
|
| 0.6385 | 2.0 | 16 | 0.5391 | 0.775 | 0.7830 | 0.775 | 0.7210 | |
|
| 0.546 | 3.0 | 24 | 0.5417 | 0.775 | 0.7658 | 0.775 | 0.7321 | |
|
| 0.481 | 4.0 | 32 | 0.5486 | 0.7833 | 0.8030 | 0.7833 | 0.7313 | |
|
| 0.3841 | 5.0 | 40 | 0.5420 | 0.7875 | 0.7825 | 0.7875 | 0.7515 | |
|
| 0.3841 | 6.0 | 48 | 0.5246 | 0.8292 | 0.8358 | 0.8292 | 0.8068 | |
|
| 0.2565 | 7.0 | 56 | 0.5763 | 0.8083 | 0.8070 | 0.8083 | 0.7821 | |
|
| 0.1605 | 8.0 | 64 | 0.5433 | 0.825 | 0.8180 | 0.825 | 0.8120 | |
|
| 0.0824 | 9.0 | 72 | 0.6010 | 0.8125 | 0.8027 | 0.8125 | 0.7994 | |
|
| 0.0489 | 10.0 | 80 | 0.6063 | 0.8125 | 0.8032 | 0.8125 | 0.7977 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
