Downloads · 30 days
2
4% of all-time downloads
vit-base-oxford-iiit-pets
BastianFuh/vit-base-oxford-iiit-pets
vit-base-oxford-iiit-pets is a image classification model from BastianFuh. Use it when you need a label for an image. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
49
Public
Parameters
85.8M
1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- Model type
- vit
- Access
- Public
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024
- SHA
- 39f4bb57
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
vit-base-oxford-iiit-pets
This model is a fine-tuned version of BastianFuh/vit-base-oxford-iiit-pets on the pcuenq/oxford-pets dataset. It achieves the following results on the evaluation set:
- Loss: 0.1375
- Accuracy: 0.9526
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: 8
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1971 | 1.0 | 739 | 0.1790 | 0.9364 |
| 0.1262 | 2.0 | 1478 | 0.1669 | 0.9391 |
| 0.1168 | 3.0 | 2217 | 0.1676 | 0.9378 |
| 0.1125 | 4.0 | 2956 | 0.1615 | 0.9378 |
| 0.1097 | 5.0 | 3695 | 0.1622 | 0.9391 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024