# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("tukangsanted/emotion-vit")
model = AutoModelForImageClassification.from_pretrained("tukangsanted/emotion-vit")Quick Links
emotion-vit
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.4844
- Accuracy: 0.475
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8841 | 1.0 | 40 | 1.8625 | 0.2625 |
| 1.5284 | 2.0 | 80 | 1.6332 | 0.35 |
| 1.3022 | 3.0 | 120 | 1.5466 | 0.4313 |
| 1.1572 | 4.0 | 160 | 1.4844 | 0.475 |
| 0.9867 | 5.0 | 200 | 1.4736 | 0.475 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 7
Model tree for tukangsanted/emotion-vit
Base model
google/vit-base-patch16-224-in21kEvaluation results
- Accuracy on imagefolderself-reported0.475
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="tukangsanted/emotion-vit") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")