metadata

library_name: transformers
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: swin-tiny-patch4-window7-224-image-classifier
    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: 0.748792270531401
          - name: F1
            type: f1
            value: 0.655421686746988
          - name: Precision
            type: precision
            value: 0.6267281105990783
          - name: Recall
            type: recall
            value: 0.6868686868686869

swin-tiny-patch4-window7-224-image-classifier

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: 0.4362
Accuracy: 0.7488
F1: 0.6554
Precision: 0.6267
Recall: 0.6869

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: 1e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.5982	1.0	143	0.5693	0.6711	0.4144	0.5441	0.3346
0.4391	2.0	286	0.4924	0.7295	0.4849	0.7178	0.3662
0.3658	3.0	429	0.4332	0.7501	0.6459	0.6368	0.6553
0.3404	4.0	572	0.4202	0.7694	0.6525	0.6857	0.6225
0.3188	5.0	715	0.4362	0.7488	0.6554	0.6267	0.6869

Framework versions

Transformers 4.46.0
Pytorch 2.5.0+cu121
Datasets 3.0.2
Tokenizers 0.20.1