Downloads · 30 days
11
3% of all-time downloads
swinv2transformer-brats-artifact-classifier
lyfesan/swinv2transformer-brats-artifact-classifier
swinv2transformer-brats-artifact-classifier is a image classification model from lyfesan. 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
352
Public
Parameters
27.6M
3.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors110 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- swinv2
- Access
- Public
- Created
- Nov 20, 2025
- Updated
- Nov 22, 2025
- SHA
- 9a158213
Base models
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. -->
swinv2transformer-brats-artifact-classifier
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6292
- Accuracy: 0.9480
- Precision: 0.9536
- Recall: 0.9480
- F1: 0.9483
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 80 | 0.5925 | 0.7626 | 0.8094 | 0.7626 | 0.7546 |
| 0.6976 | 2.0 | 160 | 0.2719 | 0.8975 | 0.9048 | 0.8975 | 0.8989 |
| 0.6976 | 3.0 | 240 | 0.2157 | 0.9045 | 0.9159 | 0.9045 | 0.9044 |
| 0.138 | 4.0 | 320 | 0.3328 | 0.8919 | 0.9125 | 0.8919 | 0.8944 |
| 0.138 | 5.0 | 400 | 0.3456 | 0.8947 | 0.9052 | 0.8947 | 0.8927 |
| 0.0775 | 6.0 | 480 | 0.2108 | 0.9382 | 0.9405 | 0.9382 | 0.9381 |
| 0.0775 | 7.0 | 560 | 0.2550 | 0.9452 | 0.9493 | 0.9452 | 0.9455 |
| 0.0464 | 8.0 | 640 | 0.3084 | 0.9270 | 0.9314 | 0.9270 | 0.9270 |
| 0.0464 | 9.0 | 720 | 0.3198 | 0.9537 | 0.9539 | 0.9537 | 0.9536 |
| 0.0169 | 10.0 | 800 | 0.2893 | 0.9494 | 0.9531 | 0.9494 | 0.9492 |
| 0.0169 | 11.0 | 880 | 0.5885 | 0.9424 | 0.9461 | 0.9424 | 0.9427 |
| 0.0055 | 12.0 | 960 | 0.6292 | 0.9480 | 0.9536 | 0.9480 | 0.9483 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.21.2
- Task
- Image Classification
- Library
- transformers
- Type
- swinv2
- License
- apache-2.0
- Created
- Nov 20, 2025
- Updated
- Nov 22, 2025