Downloads · 30 days
13
2% of all-time downloads
deit-tiny-patch16-224-finetuned-papsmear
MakAIHealthLab/deit-tiny-patch16-224-finetuned-papsmear
deit-tiny-patch16-224-finetuned-papsmear is a image classification model from MakAIHealthLab. 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
665
Public
Parameters
5.5M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors22.1 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Sep 18, 2024
- Updated
- Oct 3, 2024
- SHA
- 447e6140
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. -->
deit-tiny-patch16-224-finetuned-papsmear
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4747
- Accuracy: 0.8235
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5381 | 0.9935 | 38 | 1.4222 | 0.3897 |
| 1.172 | 1.9869 | 76 | 1.1008 | 0.5882 |
| 0.8361 | 2.9804 | 114 | 0.8529 | 0.6618 |
| 0.6869 | 4.0 | 153 | 0.9582 | 0.6324 |
| 0.4995 | 4.9935 | 191 | 0.6926 | 0.7574 |
| 0.4576 | 5.9869 | 229 | 0.4967 | 0.8529 |
| 0.4187 | 6.9804 | 267 | 0.5350 | 0.8162 |
| 0.4075 | 8.0 | 306 | 0.4903 | 0.8088 |
| 0.3585 | 8.9935 | 344 | 0.5252 | 0.7868 |
| 0.3528 | 9.9869 | 382 | 0.5027 | 0.8088 |
| 0.2788 | 10.9804 | 420 | 0.4503 | 0.8456 |
| 0.2419 | 12.0 | 459 | 0.4857 | 0.8309 |
| 0.2544 | 12.9935 | 497 | 0.5543 | 0.7868 |
| 0.2591 | 13.9869 | 535 | 0.4839 | 0.8382 |
| 0.207 | 14.9020 | 570 | 0.4747 | 0.8235 |
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
- Sep 18, 2024
- Updated
- Oct 3, 2024