README.md

---
language: en
license: mit
library_name: timm
tags:
- image-classification
- timm/vit_base_patch16_224.orig_in21k_ft_in1k
- cifar100
datasets: cifar100
metrics:
- accuracy
model-index:
- name: vit_base_patch16_224_in21k_ft_cifar100
  results:
  - task:
      type: image-classification
    dataset:
      name: CIFAR-100
      type: cifar100
    metrics:
    - type: accuracy
      value: 0.9316
---

# Model Card for Model ID

This model is a small timm/vit_base_patch16_224.orig_in21k_ft_in1k trained on cifar100.

- **Test Accuracy:** 0.9316
- **License:** MIT

## How to Get Started with the Model

Use the code below to get started with the model.

```python
import timm
import torch
from torch import nn

model = timm.create_model("timm/vit_base_patch16_224.orig_in21k_ft_in1k",
pretrained=False)
model.head = nn.Linear(model.head.in_features, 100)
model.load_state_dict(
    torch.hub.load_state_dict_from_url(
        "https://huggingface.co/edadaltocg/vit_base_patch16_224_in21k_ft_cifar100/resolve/main/pytorch_model.bin",
        map_location="cpu",
        file_name="vit_base_patch16_224_in21k_ft_cifar100.pth",
    )
)
```

## Training Data

Training data is cifar100.

## Training Hyperparameters


- **config**: `scripts/train_configs/ft_cifar100.json`

- **model**: `vit_base_patch16_224_in21k_ft_cifar100`

- **dataset**: `cifar100`

- **batch_size**: `64`

- **epochs**: `10`

- **validation_frequency**: `1`

- **seed**: `1`

- **criterion**: `CrossEntropyLoss`

- **criterion_kwargs**: `{}`

- **optimizer**: `SGD`

- **lr**: `0.01`

- **optimizer_kwargs**: `{'momentum': 0.9, 'weight_decay': 0.0}`

- **scheduler**: `CosineAnnealingLR`

- **scheduler_kwargs**: `{'T_max': 10}`

- **debug**: `False`


## Testing Data

Testing data is cifar100.

---

This model card was created by Eduardo Dadalto.