Downloads · 30 days
145
2% of all-time downloads
vit-cifar100
nickypro/vit-cifar100
vit-cifar100 is a image classification model from nickypro. 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
7.8K
Public
Repo size
687 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin344 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Feb 22, 2024
- Updated
- Feb 22, 2024
- SHA
- 27c87df1
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-base-beans-demo-v5
Note: This model is copied from Ahmed9275/Vit-Cifar100. See below for details
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the Cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4420
- Accuracy: 0.8985
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.08 | 1.0 | 3125 | 0.6196 | 0.8262 |
| 0.3816 | 2.0 | 6250 | 0.5322 | 0.8555 |
| 0.1619 | 3.0 | 9375 | 0.4817 | 0.8765 |
| 0.0443 | 4.0 | 12500 | 0.4420 | 0.8985 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Feb 22, 2024
- Updated
- Feb 22, 2024