Image Classification
Transformers
TensorBoard
Safetensors
vit
vision
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("amunchet/vit-base-beans")
model = AutoModelForImageClassification.from_pretrained("amunchet/vit-base-beans")Quick Links
vit-base-beans
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.0857
- Accuracy: 0.9850
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3152 | 1.0 | 130 | 0.2074 | 0.9774 |
| 0.2075 | 2.0 | 260 | 0.1327 | 0.9699 |
| 0.1856 | 3.0 | 390 | 0.1136 | 0.9774 |
| 0.0837 | 4.0 | 520 | 0.1014 | 0.9774 |
| 0.1271 | 5.0 | 650 | 0.0857 | 0.9850 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 4
Model tree for amunchet/vit-base-beans
Base model
google/vit-base-patch16-224-in21kDataset used to train amunchet/vit-base-beans
Evaluation results
- Accuracy on beansvalidation set self-reported0.985
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="amunchet/vit-base-beans") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")