Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("rdsmaia/pokemon_class_model")
model = AutoModelForImageClassification.from_pretrained("rdsmaia/pokemon_class_model")Quick Links
pokemon_class_model
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: 2.7799
- Accuracy: 0.8439
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.871 | 1.0 | 61 | 4.8286 | 0.1129 |
| 4.4362 | 2.0 | 122 | 4.3949 | 0.5626 |
| 3.9543 | 3.0 | 183 | 3.9551 | 0.7238 |
| 3.5859 | 4.0 | 244 | 3.6081 | 0.7772 |
| 3.2793 | 5.0 | 305 | 3.3454 | 0.8049 |
| 3.0146 | 6.0 | 366 | 3.1411 | 0.8152 |
| 2.8492 | 7.0 | 427 | 2.9854 | 0.8347 |
| 2.6706 | 8.0 | 488 | 2.8625 | 0.8501 |
| 2.5676 | 9.0 | 549 | 2.8014 | 0.8337 |
| 2.6059 | 10.0 | 610 | 2.7799 | 0.8439 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 4
Model tree for rdsmaia/pokemon_class_model
Base model
google/vit-base-patch16-224-in21kEvaluation results
- Accuracy on pokemon-classificationself-reported0.844
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="rdsmaia/pokemon_class_model") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")