|
--- |
|
language: en |
|
license: mit |
|
library_name: timm |
|
tags: |
|
- image-classification |
|
- timm/vit_base_patch16_224.orig_in21k_ft_in1k |
|
- cifar10 |
|
datasets: cifar10 |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vit_base_patch16_224_in21k_ft_cifar10 |
|
results: |
|
- task: |
|
type: image-classification |
|
dataset: |
|
name: CIFAR-10 |
|
type: cifar10 |
|
metrics: |
|
- type: accuracy |
|
value: 0.9896 |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
This model is a small timm/vit_base_patch16_224.orig_in21k_ft_in1k trained on cifar10. |
|
|
|
- **Test Accuracy:** 0.9896 |
|
- **License:** MIT |
|
|
|
## How to Get Started with the Model |
|
|
|
Use the code below to get started with the model. |
|
|
|
```python |
|
import detectors |
|
import timm |
|
|
|
model = timm.create_model("vit_base_patch16_224_in21k_ft_cifar10", pretrained=True) |
|
``` |
|
|
|
## Training Data |
|
|
|
Training data is cifar10. |
|
|
|
## Training Hyperparameters |
|
|
|
|
|
- **config**: `scripts/train_configs/ft_cifar10.json` |
|
|
|
- **model**: `vit_base_patch16_224_in21k_ft_cifar10` |
|
|
|
- **dataset**: `cifar10` |
|
|
|
- **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 cifar10. |
|
|
|
--- |
|
|
|
This model card was created by Eduardo Dadalto. |
