metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
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: 0.9803703703703703
- name: F1
type: f1
value: 0.9801864359704018
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: 0.0601
- Accuracy: 0.9804
- F1: 0.9802
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.3306 | 1.0 | 95 | 0.1438 | 0.9563 | 0.9557 |
| 0.1922 | 2.0 | 190 | 0.0962 | 0.9704 | 0.9700 |
| 0.1749 | 3.0 | 285 | 0.0770 | 0.9752 | 0.9746 |
| 0.124 | 4.0 | 380 | 0.0646 | 0.9785 | 0.9782 |
| 0.1147 | 5.0 | 475 | 0.0601 | 0.9804 | 0.9802 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.0.0+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1