Downloads · 30 days
4
0% of all-time downloads
v2_vit-base-patch16-224-in21k-finetuned-gecko
emaeon/v2_vit-base-patch16-224-in21k-finetuned-gecko
v2_vit-base-patch16-224-in21k-finetuned-gecko is a image classification model from emaeon. 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
42.5K
Public
Repo size
7.9 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
- Dec 5, 2023
- Updated
- Dec 5, 2023
- SHA
- dbcdf009
Base models
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. -->
v2_vit-base-patch16-224-in21k-finetuned-gecko
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1464
- Accuracy: 0.9572
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: 0.0005
- 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.9727 | 1.0 | 76 | 2.7860 | 0.4906 |
| 1.8126 | 1.99 | 152 | 1.4636 | 0.6511 |
| 1.141 | 2.99 | 228 | 1.0104 | 0.7302 |
| 0.7464 | 4.0 | 305 | 0.8833 | 0.7382 |
| 0.6327 | 5.0 | 381 | 0.6328 | 0.8140 |
| 0.5424 | 5.99 | 457 | 0.6602 | 0.8103 |
| 0.4628 | 6.99 | 533 | 0.5417 | 0.8466 |
| 0.3852 | 8.0 | 610 | 0.5533 | 0.8405 |
| 0.3821 | 9.0 | 686 | 0.3930 | 0.8888 |
| 0.316 | 9.99 | 762 | 0.3375 | 0.9014 |
| 0.2907 | 10.99 | 838 | 0.3326 | 0.9088 |
| 0.2597 | 12.0 | 915 | 0.2484 | 0.9304 |
| 0.2387 | 13.0 | 991 | 0.2177 | 0.9359 |
| 0.221 | 13.99 | 1067 | 0.1708 | 0.9520 |
| 0.2017 | 14.95 | 1140 | 0.1464 | 0.9572 |
Framework versions
- Transformers 4.33.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.15.0
- Tokenizers 0.13.3
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Dec 5, 2023
- Updated
- Dec 5, 2023