Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("alkzar90/croupier-creature-classifier")
model = AutoModelForImageClassification.from_pretrained("alkzar90/croupier-creature-classifier")Quick Links
croupier-creature-classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the croupier-mtg-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.7583
- Accuracy: 0.7471
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6663 | 1.1 | 100 | 1.0179 | 0.5941 |
| 0.4924 | 2.2 | 200 | 0.7036 | 0.7529 |
| 0.4552 | 3.3 | 300 | 0.6123 | 0.7824 |
| 0.2355 | 4.4 | 400 | 0.5748 | 0.7647 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 6
Space using alkzar90/croupier-creature-classifier 1
Evaluation results
- Accuracy on croupier-mtg-datasetself-reported0.747
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="alkzar90/croupier-creature-classifier") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")