Downloads · 30 days
9
2% of all-time downloads
vit-base-patch16-224-brand
barten/vit-base-patch16-224-brand
vit-base-patch16-224-brand is a image classification model from barten. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
441
Public
Parameters
85.8M
15.4 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
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Nov 14, 2023
- Updated
- Nov 25, 2023
- SHA
- dcb71fdb
Base models
Datasets
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-patch16-224-brand
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4812
- Accuracy: 0.8496
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4669 | 1.0 | 88 | 1.3067 | 0.5612 |
| 0.8898 | 1.99 | 176 | 0.8380 | 0.7140 |
| 0.7243 | 2.99 | 264 | 0.6559 | 0.7694 |
| 0.5158 | 4.0 | 353 | 0.5982 | 0.7950 |
| 0.4605 | 5.0 | 441 | 0.5856 | 0.8083 |
| 0.332 | 5.99 | 529 | 0.5138 | 0.8355 |
| 0.3375 | 6.99 | 617 | 0.5095 | 0.8264 |
| 0.2188 | 8.0 | 706 | 0.5089 | 0.8322 |
| 0.2112 | 9.0 | 794 | 0.5126 | 0.8380 |
| 0.1895 | 9.99 | 882 | 0.5057 | 0.8364 |
| 0.1593 | 10.99 | 970 | 0.4852 | 0.8529 |
| 0.1463 | 12.0 | 1059 | 0.4934 | 0.8430 |
| 0.1565 | 13.0 | 1147 | 0.4794 | 0.8496 |
| 0.1236 | 13.99 | 1235 | 0.4863 | 0.8463 |
| 0.1407 | 14.96 | 1320 | 0.4812 | 0.8496 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Nov 14, 2023
- Updated
- Nov 25, 2023