This model is a fine-tuned version of google/vit-base-patch16-224 on the pcuenq/oxford-pets dataset. It achieves the following results on the evaluation set:

Loss: 0.2110
Accuracy: 0.9378

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: 8
seed: 42
optimizer: Use adamw_torch 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
0.3688	1.0	370	0.2936	0.9175
0.2174	2.0	740	0.2098	0.9323
0.1684	3.0	1110	0.1840	0.9459
0.1427	4.0	1480	0.1772	0.9405
0.1289	5.0	1850	0.1743	0.9378

Framework versions

Transformers 4.50.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1

🧠 Zero-Shot Classification (CLIP)

This evaluation compares the fine-tuned ViT model to a zero-shot approach using openai/clip-vit-base-patch32.
The model was evaluated on 100 samples from the Oxford-IIIT Pet dataset.

🔢 Zero-Shot Metrics

Metric	Score
Accuracy	88.00%
Precision	87.68%
Recall	88.00%

Evaluation notebook: oxford_pets_zero_shot.ipynb

LukeXOTWOD/vit-base-oxford-iiit-pets

vit-base-oxford-iiit-pets

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

🧠 Zero-Shot Classification (CLIP)

🔢 Zero-Shot Metrics

LukeXOTWOD/
vit-base-oxford-iiit-pets