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: 0.1929
Accuracy: 0.9364

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
0.3787	1.0	370	0.3074	0.9269
0.2072	2.0	740	0.2311	0.9337
0.1399	3.0	1110	0.2137	0.9378
0.1393	4.0	1480	0.2065	0.9418
0.1373	5.0	1850	0.2029	0.9418

Framework versions

Transformers 4.50.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1

🔍 Zero-Shot Evaluation (Week 7)

Modell: openai/clip-vit-large-patch14
Accuracy: 0.8800
Precision: 0.8768
Recall: 0.8800

Diese Werte stammen aus einer Zero-Shot-Klassifikation mit dem Modell openai/clip-vit-large-patch14 auf dem Oxford-IIIT Pet Datensatz (100 Testbilder). Ziel war es, die Performance eines Transfer-Learning-Modells mit einem Zero-Shot-Ansatz zu vergleichen.

martivic/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 Evaluation (Week 7)

martivic/
vit-base-oxford-iiit-pets