Downloads · 30 days
11
2% of all-time downloads
vit-base-batch-32
vuongnhathien/vit-base-batch-32
vit-base-batch-32 is a image classification model from vuongnhathien. 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
570
Public
Parameters
85.8M
3.4 GB on disk
Likes
1
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
- May 22, 2024
- Updated
- May 22, 2024
- SHA
- 9669ea8c
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-batch-32
This model is a fine-tuned version of google/vit-base-patch16-224 on the vuongnhathien/30VNFoods dataset. It achieves the following results on the evaluation set:
- Loss: 0.6201
- Accuracy: 0.8756
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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6735 | 1.0 | 550 | 0.8003 | 0.7583 |
| 0.4048 | 2.0 | 1100 | 0.6471 | 0.8266 |
| 0.2506 | 3.0 | 1650 | 0.6220 | 0.8354 |
| 0.1521 | 4.0 | 2200 | 0.6406 | 0.8493 |
| 0.0812 | 5.0 | 2750 | 0.6855 | 0.8545 |
| 0.0279 | 6.0 | 3300 | 0.6767 | 0.8648 |
| 0.0094 | 7.0 | 3850 | 0.6252 | 0.8744 |
| 0.0074 | 8.0 | 4400 | 0.6064 | 0.8751 |
| 0.0056 | 9.0 | 4950 | 0.5997 | 0.8783 |
| 0.0016 | 10.0 | 5500 | 0.6009 | 0.8767 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- May 22, 2024
- Updated
- May 22, 2024