# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("PREMAADC/vit-base-ham10000")
model = AutoModelForImageClassification.from_pretrained("PREMAADC/vit-base-ham10000", device_map="auto")Quick Links
vit-base-ham10000
This model is a fine-tuned version of google/vit-base-patch16-224 on the HAM10000 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5809
- Accuracy: 0.7848
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 |
|---|---|---|---|---|
| 0.6898 | 1.0 | 501 | 0.6788 | 0.7474 |
| 0.5914 | 2.0 | 1002 | 0.6237 | 0.7664 |
| 0.6228 | 3.0 | 1503 | 0.6005 | 0.7763 |
| 0.5843 | 4.0 | 2004 | 0.5855 | 0.7848 |
| 0.5569 | 5.0 | 2505 | 0.5809 | 0.7848 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 17
Model tree for PREMAADC/vit-base-ham10000
Base model
google/vit-base-patch16-224
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="PREMAADC/vit-base-ham10000") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")