# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("thenewsupercell/DF_Image_VIT_V1")
model = AutoModelForImageClassification.from_pretrained("thenewsupercell/DF_Image_VIT_V1")Quick Links
DF_Image_VIT_V1
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- F1: 0.6780
- Loss: 0.0492
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 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | F1 | Validation Loss |
|---|---|---|---|---|
| 0.0462 | 1.0 | 4604 | 0.4793 | 0.0570 |
| 0.0006 | 2.0 | 9208 | 0.4261 | 0.0783 |
| 0.0006 | 3.0 | 13812 | 0.6780 | 0.0492 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 2
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="thenewsupercell/DF_Image_VIT_V1") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")