Downloads · 30 days
17
16% of all-time downloads
swin-tiny-patch4-window7-224-finetuned-car-models-classification-car-parts-v003
natsu39/swin-tiny-patch4-window7-224-finetuned-car-models-classification-car-parts-v003
swin-tiny-patch4-window7-224-finetuned-car-models-classification-car-parts-v003 is a image classification model from natsu39. 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
106
Public
Parameters
27.6M
883 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors110 MB · 100%
Parameter types
How the weights are stored.
F3227.5M · 100%
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. -->
swin-tiny-patch4-window7-224-finetuned-car-models-classification-car-parts-v003
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0315
- Accuracy: 0.6
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 2 | 3.3010 | 0.2 |
| No log | 2.0 | 4 | 3.0586 | 0.2 |
| No log | 3.0 | 6 | 2.6931 | 0.4 |
| No log | 4.0 | 8 | 2.2568 | 0.6 |
| 1.6745 | 5.0 | 10 | 1.8658 | 0.4 |
| 1.6745 | 6.0 | 12 | 1.4990 | 0.4 |
| 1.6745 | 7.0 | 14 | 1.2129 | 0.6 |
| 1.6745 | 8.0 | 16 | 1.0403 | 0.6 |
| 1.6745 | 9.0 | 18 | 0.9412 | 0.2 |
| 0.6008 | 10.0 | 20 | 0.8707 | 0.6 |
| 0.6008 | 11.0 | 22 | 0.7957 | 0.6 |
| 0.6008 | 12.0 | 24 | 0.7709 | 0.6 |
| 0.6008 | 13.0 | 26 | 0.7686 | 0.6 |
| 0.6008 | 14.0 | 28 | 0.7594 | 0.6 |
| 0.3026 | 15.0 | 30 | 0.7892 | 0.6 |
| 0.3026 | 16.0 | 32 | 0.8406 | 0.6 |
| 0.3026 | 17.0 | 34 | 0.9704 | 0.6 |
| 0.3026 | 18.0 | 36 | 1.0912 | 0.6 |
| 0.3026 | 19.0 | 38 | 1.1079 | 0.6 |
| 0.1993 | 20.0 | 40 | 1.1272 | 0.6 |
| 0.1993 | 21.0 | 42 | 1.1378 | 0.6 |
| 0.1993 | 22.0 | 44 | 1.1386 | 0.6 |
| 0.1993 | 23.0 | 46 | 1.1138 | 0.6 |
| 0.1993 | 24.0 | 48 | 1.0729 | 0.6 |
| 0.1889 | 25.0 | 50 | 1.0470 | 0.6 |
| 0.1889 | 26.0 | 52 | 1.0453 | 0.6 |
| 0.1889 | 27.0 | 54 | 1.0442 | 0.6 |
| 0.1889 | 28.0 | 56 | 1.0360 | 0.6 |
| 0.1889 | 29.0 | 58 | 1.0286 | 0.6 |
| 0.1326 | 30.0 | 60 | 1.0315 | 0.6 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4
- Task
- Image Classification
- Library
- transformers
- Type
- swin
- License
- apache-2.0
- Created
- Aug 28, 2025
- Updated
- Aug 28, 2025