Downloads · 30 days
5
1% of all-time downloads
vit_finedtuned_food_model
pumpitup521/vit_finedtuned_food_model
vit_finedtuned_food_model is a image classification model from pumpitup521. 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
751
Public
Parameters
85.9M
3.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin344 MB · 50%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- May 26, 2023
- Updated
- Sep 5, 2023
- SHA
- 8ba24d05
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. -->
vit_finedtuned_food_model
This model is a fine-tuned version of google/vit-base-patch16-224 on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2214
- Accuracy: 0.934
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6064 | 0.99 | 62 | 0.4593 | 0.872 |
| 0.2607 | 2.0 | 125 | 0.2649 | 0.92 |
| 0.2074 | 2.99 | 187 | 0.2421 | 0.924 |
| 0.0908 | 4.0 | 250 | 0.2442 | 0.921 |
| 0.1237 | 4.99 | 312 | 0.2353 | 0.923 |
| 0.0915 | 6.0 | 375 | 0.2402 | 0.923 |
| 0.0549 | 6.99 | 437 | 0.2053 | 0.933 |
| 0.0645 | 8.0 | 500 | 0.2190 | 0.929 |
| 0.087 | 8.99 | 562 | 0.2313 | 0.935 |
| 0.0544 | 9.92 | 620 | 0.2214 | 0.934 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- May 26, 2023
- Updated
- Sep 5, 2023