Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("merve/pokemon-classifier")
model = AutoModelForImageClassification.from_pretrained("merve/pokemon-classifier")Quick Links
pokemon-classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the pokemon-classification dataset. It achieves the following results on the evaluation set:
- Loss: 5.3367
- Accuracy: 0.0109
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.7242 | 1.0 | 76 | 5.2859 | 0.0068 |
| 4.2781 | 1.99 | 152 | 5.3334 | 0.0109 |
| 4.0798 | 2.99 | 228 | 5.3367 | 0.0109 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 5
Model tree for merve/pokemon-classifier
Base model
google/vit-base-patch16-224-in21kEvaluation results
- Accuracy on pokemon-classificationtest set self-reported0.011
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="merve/pokemon-classifier") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")