Downloads · 30 days
23
5% of all-time downloads
vit-base-beans-demo-v5
rshrott/vit-base-beans-demo-v5
vit-base-beans-demo-v5 is a image classification model from rshrott. 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
456
Public
Parameters
85.8M
11 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin343 MB · 50%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Jul 16, 2023
- Updated
- Mar 23, 2024
- SHA
- 27b567ab
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-beans-demo-v5
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.8460
- Accuracy: 0.6695
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0616 | 0.17 | 100 | 1.0267 | 0.5818 |
| 0.9594 | 0.34 | 200 | 0.9468 | 0.6073 |
| 1.1785 | 0.51 | 300 | 0.9976 | 0.5869 |
| 0.865 | 0.68 | 400 | 0.9288 | 0.6388 |
| 0.8494 | 0.85 | 500 | 0.8573 | 0.6516 |
| 0.8151 | 1.02 | 600 | 0.8729 | 0.6397 |
| 0.5787 | 1.19 | 700 | 0.9067 | 0.6448 |
| 0.7768 | 1.36 | 800 | 0.8996 | 0.6533 |
| 0.6098 | 1.53 | 900 | 0.8460 | 0.6695 |
| 0.6251 | 1.7 | 1000 | 0.8610 | 0.6704 |
| 0.7863 | 1.87 | 1100 | 0.8668 | 0.6431 |
| 0.2595 | 2.04 | 1200 | 0.8725 | 0.6840 |
| 0.2735 | 2.21 | 1300 | 0.9307 | 0.6746 |
| 0.2429 | 2.39 | 1400 | 1.0958 | 0.6354 |
| 0.3224 | 2.56 | 1500 | 1.0305 | 0.6687 |
| 0.1602 | 2.73 | 1600 | 1.0072 | 0.6746 |
| 0.2042 | 2.9 | 1700 | 1.0971 | 0.6789 |
| 0.0604 | 3.07 | 1800 | 1.0817 | 0.6917 |
| 0.0716 | 3.24 | 1900 | 1.1307 | 0.6925 |
| 0.0822 | 3.41 | 2000 | 1.1827 | 0.6925 |
| 0.0889 | 3.58 | 2100 | 1.2424 | 0.6934 |
| 0.0855 | 3.75 | 2200 | 1.2667 | 0.6899 |
| 0.0682 | 3.92 | 2300 | 1.2470 | 0.6951 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Jul 16, 2023
- Updated
- Mar 23, 2024