Downloads · 30 days
15
4% of all-time downloads
deit-small-patch16-224-finetuned-HOMUS
nadimkanazi/deit-small-patch16-224-finetuned-HOMUS
deit-small-patch16-224-finetuned-HOMUS is a image classification model from nadimkanazi. 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
420
Public
Repo size
955 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin86.8 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Apr 29, 2024
- Updated
- Apr 29, 2024
- SHA
- a61d3ab6
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. -->
deit-small-patch16-224-finetuned-HOMUS
This model is a fine-tuned version of facebook/deit-small-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2130
- Accuracy: 0.9504
- Precision: 0.9509
- Recall: 0.9504
- F1 Score: 0.9504
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: 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: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
|---|---|---|---|---|---|---|---|
| 0.8475 | 1.0 | 83 | 0.6638 | 0.8224 | 0.8304 | 0.8224 | 0.8206 |
| 0.26 | 1.99 | 166 | 0.3324 | 0.8917 | 0.8996 | 0.8917 | 0.8909 |
| 0.134 | 2.99 | 249 | 0.2342 | 0.9272 | 0.9292 | 0.9272 | 0.9265 |
| 0.0807 | 4.0 | 333 | 0.2153 | 0.9307 | 0.9314 | 0.9307 | 0.9301 |
| 0.0322 | 5.0 | 416 | 0.2077 | 0.9364 | 0.9383 | 0.9364 | 0.9364 |
| 0.0162 | 5.99 | 499 | 0.2255 | 0.9377 | 0.9389 | 0.9377 | 0.9377 |
| 0.0095 | 6.99 | 582 | 0.2147 | 0.9439 | 0.9446 | 0.9439 | 0.9439 |
| 0.0022 | 8.0 | 666 | 0.2185 | 0.95 | 0.9512 | 0.95 | 0.9500 |
| 0.0017 | 9.0 | 749 | 0.2117 | 0.9504 | 0.9509 | 0.9504 | 0.9504 |
| 0.0015 | 9.97 | 830 | 0.2130 | 0.9504 | 0.9509 | 0.9504 | 0.9504 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Apr 29, 2024
- Updated
- Apr 29, 2024