metadata

library_name: transformers
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - precision
  - recall
  - 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: 0.8327974276527331
          - name: Precision
            type: precision
            value: 0.860997154156041
          - name: Recall
            type: recall
            value: 0.8327974276527331
          - name: F1
            type: f1
            value: 0.8137864007121186

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: 0.3277
Accuracy: 0.8328
Precision: 0.8610
Recall: 0.8328
F1: 0.8138

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	Precision	Recall	F1
0.5603	1.0	22	0.5610	0.6817	0.7833	0.6817	0.5559
0.3934	2.0	44	0.3976	0.7910	0.7879	0.7910	0.7768
0.2992	3.0	66	0.3036	0.8071	0.8044	0.8071	0.7965
0.2746	4.0	88	0.3538	0.7878	0.7812	0.7878	0.7799
0.2573	5.0	110	0.2242	0.8521	0.8561	0.8521	0.8535
0.2724	6.0	132	0.3801	0.7749	0.8145	0.7749	0.7347
0.2344	7.0	154	0.3327	0.8232	0.8544	0.8232	0.8011
0.2225	8.0	176	0.3736	0.8392	0.8655	0.8392	0.8221
0.225	9.0	198	0.3479	0.8328	0.8610	0.8328	0.8138
0.2308	10.0	220	0.3277	0.8328	0.8610	0.8328	0.8138

Framework versions

Transformers 4.44.2
Pytorch 2.5.0+cu121
Datasets 3.0.2
Tokenizers 0.19.1