---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Action_all_10_class
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: Action_small_dataset
      type: imagefolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8699386503067484
---

<!-- 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. -->

# Action_all_10_class

This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the Action_small_dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4618
- Accuracy: 0.8699

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.1996        | 0.35  | 100  | 1.0635          | 0.7730   |
| 1.0335        | 0.69  | 200  | 0.8392          | 0.7718   |
| 0.6279        | 1.04  | 300  | 0.6463          | 0.8294   |
| 0.8633        | 1.38  | 400  | 0.7172          | 0.7926   |
| 0.5851        | 1.73  | 500  | 0.5858          | 0.8380   |
| 0.5305        | 2.08  | 600  | 0.5780          | 0.8356   |
| 0.5511        | 2.42  | 700  | 0.5313          | 0.8393   |
| 0.4657        | 2.77  | 800  | 0.5443          | 0.8368   |
| 0.3615        | 3.11  | 900  | 0.5038          | 0.8429   |
| 0.5301        | 3.46  | 1000 | 0.5101          | 0.8503   |
| 0.4108        | 3.81  | 1100 | 0.5212          | 0.8479   |
| 0.4223        | 4.15  | 1200 | 0.5328          | 0.8429   |
| 0.3877        | 4.5   | 1300 | 0.5815          | 0.8294   |
| 0.3879        | 4.84  | 1400 | 0.5151          | 0.8503   |
| 0.2797        | 5.19  | 1500 | 0.5160          | 0.8564   |
| 0.2628        | 5.54  | 1600 | 0.4618          | 0.8699   |
| 0.3404        | 5.88  | 1700 | 0.4903          | 0.8675   |
| 0.3033        | 6.23  | 1800 | 0.4861          | 0.8663   |
| 0.214         | 6.57  | 1900 | 0.4853          | 0.8687   |
| 0.2763        | 6.92  | 2000 | 0.4705          | 0.8736   |
| 0.3009        | 7.27  | 2100 | 0.4723          | 0.8626   |
| 0.1543        | 7.61  | 2200 | 0.4983          | 0.8638   |
| 0.2407        | 7.96  | 2300 | 0.4742          | 0.8650   |
| 0.2679        | 8.3   | 2400 | 0.4935          | 0.8724   |
| 0.1508        | 8.65  | 2500 | 0.4826          | 0.8675   |
| 0.2129        | 9.0   | 2600 | 0.4981          | 0.8712   |
| 0.1131        | 9.34  | 2700 | 0.4718          | 0.8712   |
| 0.2144        | 9.69  | 2800 | 0.4745          | 0.8712   |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2