Downloads · 30 days
4
2% of all-time downloads
vit-emotions-fp16
kerwinnl/vit-emotions-fp16
vit-emotions-fp16 is a image classification model from kerwinnl. 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
229
Public
Parameters
85.8M
8.9 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
- Feb 9, 2024
- Updated
- Feb 13, 2024
- SHA
- cc10f0b4
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-emotions-fp16
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2406
- Accuracy: 0.9487
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 50 | 1.1462 | 0.605 |
| No log | 2.0 | 100 | 0.9580 | 0.7175 |
| No log | 3.0 | 150 | 0.9513 | 0.68 |
| No log | 4.0 | 200 | 0.7491 | 0.7937 |
| No log | 5.0 | 250 | 0.6535 | 0.8387 |
| No log | 6.0 | 300 | 0.5758 | 0.87 |
| No log | 7.0 | 350 | 0.5042 | 0.8688 |
| No log | 8.0 | 400 | 0.4789 | 0.8775 |
| No log | 9.0 | 450 | 0.3602 | 0.9337 |
| 0.7188 | 10.0 | 500 | 0.3826 | 0.905 |
| 0.7188 | 11.0 | 550 | 0.3889 | 0.8938 |
| 0.7188 | 12.0 | 600 | 0.3590 | 0.9137 |
| 0.7188 | 13.0 | 650 | 0.2929 | 0.92 |
| 0.7188 | 14.0 | 700 | 0.2881 | 0.9213 |
| 0.7188 | 15.0 | 750 | 0.2652 | 0.9363 |
| 0.7188 | 16.0 | 800 | 0.2611 | 0.9463 |
| 0.7188 | 17.0 | 850 | 0.2267 | 0.9537 |
| 0.7188 | 18.0 | 900 | 0.2394 | 0.95 |
| 0.7188 | 19.0 | 950 | 0.1969 | 0.9525 |
| 0.2754 | 20.0 | 1000 | 0.2419 | 0.9413 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Feb 9, 2024
- Updated
- Feb 13, 2024