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: 0.7090909090909091
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: 0.6671
- Accuracy: 0.7091
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 |
|---|---|---|---|---|
| 1.1158 | 0.97 | 15 | 0.9997 | 0.5045 |
| 0.8261 | 2.0 | 31 | 0.9180 | 0.5909 |
| 0.7361 | 2.97 | 46 | 0.8047 | 0.65 |
| 0.6325 | 4.0 | 62 | 0.7320 | 0.6818 |
| 0.5946 | 4.97 | 77 | 0.7196 | 0.6773 |
| 0.5149 | 6.0 | 93 | 0.6827 | 0.7273 |
| 0.5083 | 6.97 | 108 | 0.6906 | 0.6955 |
| 0.4316 | 8.0 | 124 | 0.6681 | 0.7091 |
| 0.4214 | 8.97 | 139 | 0.6700 | 0.7091 |
| 0.4096 | 9.68 | 150 | 0.6671 | 0.7091 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0