metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-eurosat-people
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: images
split: train
args: images
metrics:
- name: Accuracy
type: accuracy
value: 0.952
swin-tiny-patch4-window7-224-finetuned-eurosat-people
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: 0.1711
- Accuracy: 0.952
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 4 | 0.3073 | 0.912 |
| No log | 2.0 | 8 | 0.2076 | 0.92 |
| 0.4055 | 3.0 | 12 | 0.1789 | 0.928 |
| 0.4055 | 4.0 | 16 | 0.1911 | 0.928 |
| 0.3045 | 5.0 | 20 | 0.1695 | 0.928 |
| 0.3045 | 6.0 | 24 | 0.1756 | 0.944 |
| 0.3045 | 7.0 | 28 | 0.1751 | 0.944 |
| 0.2419 | 8.0 | 32 | 0.1727 | 0.944 |
| 0.2419 | 9.0 | 36 | 0.1711 | 0.952 |
| 0.2375 | 10.0 | 40 | 0.1711 | 0.952 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3