Image Classification
Transformers
TensorBoard
ONNX
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("spolivin/food-vit-tutorial")
model = AutoModelForImageClassification.from_pretrained("spolivin/food-vit-tutorial")Quick Links
food-vit-tutorial
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on food101 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0267
- Accuracy: 0.916
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.7889 | 0.99 | 62 | 2.5577 | 0.838 |
| 1.7142 | 2.0 | 125 | 1.6126 | 0.879 |
| 1.2887 | 2.99 | 187 | 1.2513 | 0.903 |
| 1.0307 | 4.0 | 250 | 1.0673 | 0.922 |
| 1.0022 | 4.96 | 310 | 1.0267 | 0.916 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 11
Model tree for spolivin/food-vit-tutorial
Base model
google/vit-base-patch16-224-in21kDataset used to train spolivin/food-vit-tutorial
Evaluation results
- accuracy on food101self-reported0.916
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="spolivin/food-vit-tutorial") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")