metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: ai_vs_real-finetuned-eurosat
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9901960784313726
ai_vs_real-finetuned-eurosat
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0432
- Accuracy: 0.9902
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: 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 |
|---|---|---|---|---|
| No log | 0.8 | 3 | 0.7072 | 0.5 |
| No log | 1.87 | 7 | 0.5099 | 0.7255 |
| 0.6036 | 2.93 | 11 | 0.3836 | 0.8529 |
| 0.6036 | 4.0 | 15 | 0.2382 | 0.9118 |
| 0.6036 | 4.8 | 18 | 0.1662 | 0.9412 |
| 0.2575 | 5.87 | 22 | 0.1505 | 0.9412 |
| 0.2575 | 6.93 | 26 | 0.0722 | 0.9804 |
| 0.0813 | 8.0 | 30 | 0.0788 | 0.9608 |
| 0.0813 | 8.8 | 33 | 0.0697 | 0.9608 |
| 0.0813 | 9.87 | 37 | 0.0596 | 0.9608 |
| 0.053 | 10.93 | 41 | 0.0437 | 0.9902 |
| 0.053 | 12.0 | 45 | 0.0432 | 0.9902 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2