Downloads · 30 days
5
9% of all-time downloads
vit-google-model-30-classes
Tianmu28/vit-google-model-30-classes
vit-google-model-30-classes is a image classification model from Tianmu28. 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
57
Public
Parameters
85.8M
343 MB 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
- Oct 18, 2024
- Updated
- Oct 18, 2024
- SHA
- 24b34342
Base models
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. -->
results
This model is a fine-tuned version of google/vit-base-patch16-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0466
- Accuracy: 0.9967
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2698 | 1.0 | 57 | 0.7910 | 0.9567 |
| 0.1238 | 2.0 | 114 | 0.1673 | 0.99 |
| 0.0269 | 3.0 | 171 | 0.0869 | 0.9967 |
| 0.0096 | 4.0 | 228 | 0.0634 | 0.9967 |
| 0.0059 | 5.0 | 285 | 0.0569 | 0.9967 |
| 0.0049 | 6.0 | 342 | 0.0524 | 0.9967 |
| 0.0043 | 7.0 | 399 | 0.0495 | 0.9967 |
| 0.0036 | 8.0 | 456 | 0.0479 | 0.9967 |
| 0.0036 | 9.0 | 513 | 0.0469 | 0.9967 |
| 0.0032 | 10.0 | 570 | 0.0466 | 0.9967 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Oct 18, 2024
- Updated
- Oct 18, 2024