Downloads · 30 days
6
1% of all-time downloads
swin-tiny-patch4-window7-224-finetuned-ai-not
LukeSajkowski/swin-tiny-patch4-window7-224-finetuned-ai-not
swin-tiny-patch4-window7-224-finetuned-ai-not is a image classification model from LukeSajkowski. 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
664
Public
Repo size
1.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin110 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- swin
- Access
- Public
- Created
- Feb 15, 2023
- Updated
- Feb 17, 2023
- SHA
- cfd88054
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. -->
swin-tiny-patch4-window7-224-finetuned-ai-not
This model is a fine-tuned version of lukee/swin-tiny-patch4-window7-224-finetuned-ai-not on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0827
- Accuracy: 0.9796
- F1: 0.9794
- Log Loss: 0.7049
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 | F1 | Log Loss |
|---|---|---|---|---|---|---|
| 0.1026 | 1.0 | 131 | 0.0761 | 0.9715 | 0.9713 | 0.9831 |
| 0.1111 | 2.0 | 262 | 0.1050 | 0.9597 | 0.9591 | 1.3912 |
| 0.0736 | 3.0 | 393 | 0.0736 | 0.9748 | 0.9745 | 0.8718 |
| 0.0708 | 4.0 | 524 | 0.0888 | 0.9694 | 0.9690 | 1.0573 |
| 0.0439 | 5.0 | 655 | 0.0998 | 0.9683 | 0.9679 | 1.0944 |
| 0.0514 | 6.0 | 786 | 0.0854 | 0.9705 | 0.9701 | 1.0202 |
| 0.0361 | 7.0 | 917 | 0.0737 | 0.9780 | 0.9778 | 0.7605 |
| 0.0256 | 8.0 | 1048 | 0.0764 | 0.9801 | 0.9799 | 0.6863 |
| 0.0375 | 9.0 | 1179 | 0.0740 | 0.9785 | 0.9783 | 0.7420 |
| 0.0257 | 10.0 | 1310 | 0.0827 | 0.9796 | 0.9794 | 0.7049 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
- Task
- Image Classification
- Library
- transformers
- Type
- swin
- License
- apache-2.0
- Created
- Feb 15, 2023
- Updated
- Feb 17, 2023