Downloads · 30 days
5
11% of all-time downloads
vit-base-patch16-224-in21k-finetuned-eurosat
MingPass/vit-base-patch16-224-in21k-finetuned-eurosat
vit-base-patch16-224-in21k-finetuned-eurosat is a image classification model from MingPass. 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
46
Public
Parameters
85.8M
343 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Feb 15, 2025
- Updated
- Feb 15, 2025
- SHA
- 58cf8bcf
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. -->
vit-base-patch16-224-in21k-finetuned-eurosat
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: 0.5799
- Accuracy: 0.8899
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 8 | 0.7453 | 0.8648 |
| 0.8416 | 2.0 | 16 | 0.6232 | 0.8773 |
| 0.6293 | 3.0 | 24 | 0.5799 | 0.8899 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Feb 15, 2025
- Updated
- Feb 15, 2025