Downloads · 30 days
7
10% of all-time downloads
vit-base-patch16-224-ve-U11-b-40
Augusto777/vit-base-patch16-224-ve-U11-b-40
vit-base-patch16-224-ve-U11-b-40 is a image classification model from Augusto777. 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
73
Public
Parameters
85.8M
3.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt687 MB · 50%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Jun 12, 2024
- Updated
- Jun 12, 2024
- SHA
- 81609cbc
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-ve-U11-b-40
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: 0.6399
- Accuracy: 0.8478
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: 5.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.92 | 6 | 1.3827 | 0.3913 |
| 1.3824 | 2.0 | 13 | 1.3319 | 0.6087 |
| 1.3824 | 2.92 | 19 | 1.2476 | 0.5435 |
| 1.3034 | 4.0 | 26 | 1.1450 | 0.5217 |
| 1.1431 | 4.92 | 32 | 1.0679 | 0.5435 |
| 1.1431 | 6.0 | 39 | 1.0006 | 0.6087 |
| 1.0123 | 6.92 | 45 | 0.9617 | 0.6522 |
| 0.8798 | 8.0 | 52 | 0.8575 | 0.7609 |
| 0.8798 | 8.92 | 58 | 0.8074 | 0.6957 |
| 0.7538 | 10.0 | 65 | 0.7447 | 0.7826 |
| 0.6115 | 10.92 | 71 | 0.7204 | 0.7826 |
| 0.6115 | 12.0 | 78 | 0.6399 | 0.8478 |
| 0.5009 | 12.92 | 84 | 0.5726 | 0.8478 |
| 0.389 | 14.0 | 91 | 0.5825 | 0.8478 |
| 0.389 | 14.92 | 97 | 0.6231 | 0.7609 |
| 0.3348 | 16.0 | 104 | 0.5510 | 0.8478 |
| 0.2616 | 16.92 | 110 | 0.5070 | 0.8478 |
| 0.2616 | 18.0 | 117 | 0.5040 | 0.8261 |
| 0.2188 | 18.92 | 123 | 0.5738 | 0.7826 |
| 0.2078 | 20.0 | 130 | 0.5398 | 0.8043 |
| 0.2078 | 20.92 | 136 | 0.5334 | 0.7826 |
| 0.2165 | 22.0 | 143 | 0.6043 | 0.7826 |
| 0.2165 | 22.92 | 149 | 0.5817 | 0.8043 |
| 0.1645 | 24.0 | 156 | 0.6465 | 0.7391 |
| 0.1413 | 24.92 | 162 | 0.6638 | 0.8043 |
| 0.1413 | 26.0 | 169 | 0.5710 | 0.8261 |
| 0.141 | 26.92 | 175 | 0.6494 | 0.8043 |
| 0.1313 | 28.0 | 182 | 0.7649 | 0.6957 |
| 0.1313 | 28.92 | 188 | 0.6130 | 0.7609 |
| 0.14 | 30.0 | 195 | 0.6718 | 0.7609 |
| 0.1284 | 30.92 | 201 | 0.6660 | 0.8261 |
| 0.1284 | 32.0 | 208 | 0.6286 | 0.7826 |
| 0.1135 | 32.92 | 214 | 0.6424 | 0.8043 |
| 0.1024 | 34.0 | 221 | 0.6339 | 0.8043 |
| 0.1024 | 34.92 | 227 | 0.6132 | 0.8043 |
| 0.1108 | 36.0 | 234 | 0.5975 | 0.8478 |
| 0.0944 | 36.92 | 240 | 0.5981 | 0.8478 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Jun 12, 2024
- Updated
- Jun 12, 2024