Downloads · 30 days
6
1% of all-time downloads
vit-base-patch16-224-finetuned-algae-rgb
samitizerxu/vit-base-patch16-224-finetuned-algae-rgb
vit-base-patch16-224-finetuned-algae-rgb is a image classification model from samitizerxu. 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
581
Public
Repo size
7.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Feb 14, 2023
- Updated
- Feb 15, 2023
- SHA
- 8da08e38
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-base-patch16-224-finetuned-algae-rgb
This model is a fine-tuned version of google/vit-base-patch16-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0685
- Accuracy: 0.6174
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.981 | 1.0 | 120 | 1.0513 | 0.5698 |
| 1.0027 | 2.0 | 240 | 1.0316 | 0.5775 |
| 0.9554 | 3.0 | 360 | 0.9944 | 0.5945 |
| 0.978 | 4.0 | 480 | 0.9735 | 0.5980 |
| 0.8983 | 5.0 | 600 | 0.9690 | 0.6033 |
| 0.8561 | 6.0 | 720 | 0.9714 | 0.5968 |
| 0.8438 | 7.0 | 840 | 0.9833 | 0.6039 |
| 0.808 | 8.0 | 960 | 0.9827 | 0.6138 |
| 0.7882 | 9.0 | 1080 | 0.9971 | 0.5962 |
| 0.7422 | 10.0 | 1200 | 0.9901 | 0.6080 |
| 0.7797 | 11.0 | 1320 | 1.0096 | 0.5921 |
| 0.7167 | 12.0 | 1440 | 1.0252 | 0.6092 |
| 0.7445 | 13.0 | 1560 | 1.0364 | 0.6074 |
| 0.6641 | 14.0 | 1680 | 1.0471 | 0.6092 |
| 0.6847 | 15.0 | 1800 | 1.0693 | 0.6138 |
| 0.6418 | 16.0 | 1920 | 1.0685 | 0.6174 |
| 0.6423 | 17.0 | 2040 | 1.0683 | 0.6127 |
| 0.6432 | 18.0 | 2160 | 1.0729 | 0.6127 |
| 0.6208 | 19.0 | 2280 | 1.0801 | 0.6138 |
| 0.588 | 20.0 | 2400 | 1.0802 | 0.6103 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Feb 14, 2023
- Updated
- Feb 15, 2023