metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-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: 0.9705882352941176
swin-tiny-patch4-window7-224-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: 0.0516
- Accuracy: 0.9706
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 | 0.6377 | 0.6275 |
| No log | 1.87 | 7 | 0.5076 | 0.6569 |
| 0.5789 | 2.93 | 11 | 0.3113 | 0.9510 |
| 0.5789 | 4.0 | 15 | 0.2111 | 0.9706 |
| 0.5789 | 4.8 | 18 | 0.1718 | 0.9706 |
| 0.251 | 5.87 | 22 | 0.0943 | 0.9608 |
| 0.251 | 6.93 | 26 | 0.0896 | 0.9608 |
| 0.0853 | 8.0 | 30 | 0.0535 | 0.9804 |
| 0.0853 | 8.8 | 33 | 0.0604 | 0.9608 |
| 0.0853 | 9.87 | 37 | 0.0982 | 0.9608 |
| 0.0461 | 10.93 | 41 | 0.0631 | 0.9608 |
| 0.0461 | 12.0 | 45 | 0.0516 | 0.9706 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2