Downloads · 30 days
5
1% of all-time downloads
swin-finetuned-food101
Gofaone/swin-finetuned-food101
swin-finetuned-food101 is a image classification model from Gofaone. 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
604
Public
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin348 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- swin
- Access
- Public
- Created
- Apr 25, 2023
- Updated
- Apr 26, 2023
- SHA
- 19cff92d
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-finetuned-food101
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2744
- Accuracy: 0.9236
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.548 | 1.0 | 1183 | 0.3899 | 0.8848 |
| 0.2979 | 2.0 | 2367 | 0.2940 | 0.9152 |
| 0.1004 | 3.0 | 3549 | 0.2744 | 0.9236 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Task
- Image Classification
- Library
- transformers
- Type
- swin
- License
- apache-2.0
- Created
- Apr 25, 2023
- Updated
- Apr 26, 2023