Downloads · 30 days
26
2% of all-time downloads
swin-tiny-patch4-window7-224-finetuned-agrivision
valadhi/swin-tiny-patch4-window7-224-finetuned-agrivision
swin-tiny-patch4-window7-224-finetuned-agrivision is a image classification model from valadhi. 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
1.4K
Public
Repo size
23.1 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
- Sep 8, 2022
- Updated
- Sep 15, 2022
- SHA
- 01911303
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-agrivision
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: 0.3605
- Accuracy: 0.9203
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5913 | 1.0 | 31 | 0.7046 | 0.7175 |
| 0.1409 | 2.0 | 62 | 0.8423 | 0.6788 |
| 0.0825 | 3.0 | 93 | 0.6224 | 0.7654 |
| 0.0509 | 4.0 | 124 | 0.4379 | 0.8360 |
| 0.0439 | 5.0 | 155 | 0.1706 | 0.9317 |
| 0.0107 | 6.0 | 186 | 0.1914 | 0.9362 |
| 0.0134 | 7.0 | 217 | 0.2491 | 0.9089 |
| 0.0338 | 8.0 | 248 | 0.2119 | 0.9362 |
| 0.0306 | 9.0 | 279 | 0.4502 | 0.8610 |
| 0.0054 | 10.0 | 310 | 0.4990 | 0.8747 |
| 0.0033 | 11.0 | 341 | 0.2746 | 0.9112 |
| 0.0021 | 12.0 | 372 | 0.2501 | 0.9317 |
| 0.0068 | 13.0 | 403 | 0.1883 | 0.9522 |
| 0.0038 | 14.0 | 434 | 0.3672 | 0.9134 |
| 0.0006 | 15.0 | 465 | 0.2275 | 0.9408 |
| 0.0011 | 16.0 | 496 | 0.3349 | 0.9134 |
| 0.0017 | 17.0 | 527 | 0.3329 | 0.9157 |
| 0.0007 | 18.0 | 558 | 0.2508 | 0.9317 |
| 0.0023 | 19.0 | 589 | 0.2338 | 0.9385 |
| 0.0003 | 20.0 | 620 | 0.3193 | 0.9226 |
| 0.002 | 21.0 | 651 | 0.4604 | 0.9043 |
| 0.0023 | 22.0 | 682 | 0.3338 | 0.9203 |
| 0.005 | 23.0 | 713 | 0.2925 | 0.9271 |
| 0.0001 | 24.0 | 744 | 0.2022 | 0.9522 |
| 0.0002 | 25.0 | 775 | 0.2699 | 0.9339 |
| 0.0007 | 26.0 | 806 | 0.2603 | 0.9385 |
| 0.0005 | 27.0 | 837 | 0.4120 | 0.9134 |
| 0.0003 | 28.0 | 868 | 0.3550 | 0.9203 |
| 0.0008 | 29.0 | 899 | 0.3657 | 0.9203 |
| 0.0 | 30.0 | 930 | 0.3605 | 0.9203 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1
- Datasets 2.4.0
- Tokenizers 0.12.1
- Task
- Image Classification
- Library
- transformers
- Type
- swin
- License
- apache-2.0
- Created
- Sep 8, 2022
- Updated
- Sep 15, 2022