---
license: apache-2.0
tags:
- huggingpics
- image-classification
- generated_from_trainer
metrics:
- accuracy
model_index:
- name: planes-trains-automobiles
  results:
  - task:
      name: Image Classification
      type: image-classification
    metric:
      name: Accuracy
      type: accuracy
      value: 0.9850746268656716
base_model: google/vit-base-patch16-224-in21k
---

<!-- 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. -->

# planes-trains-automobiles

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 huggingpics dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0534
- Accuracy: 0.9851


## Model description

Autogenerated by HuggingPics🤗🖼️

Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb).

Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics).
## Example Images


#### automobiles

![automobiles](images/automobiles.jpg)

#### planes

![planes](images/planes.jpg)

#### trains

![trains](images/trains.jpg)


## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0283        | 1.0   | 48   | 0.0434          | 0.9851   |
| 0.0224        | 2.0   | 96   | 0.0548          | 0.9851   |
| 0.0203        | 3.0   | 144  | 0.0445          | 0.9851   |
| 0.0195        | 4.0   | 192  | 0.0534          | 0.9851   |


### Framework versions

- Transformers 4.9.2
- Pytorch 1.9.0+cu102
- Datasets 1.11.0
- Tokenizers 0.10.3