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-student_two_classes
    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: 0.76

swin-tiny-patch4-window7-224-finetuned-student_two_classes

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: 0.7437
Accuracy: 0.76

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3845	1.0	13	0.6475	0.7
0.3466	2.0	26	0.6201	0.74
0.3832	3.0	39	0.8068	0.82
0.5344	4.0	52	0.6340	0.81
0.4912	5.0	65	0.6880	0.8
0.5093	6.0	78	0.6999	0.73
0.4109	7.0	91	0.7295	0.83
0.4383	8.0	104	0.7048	0.84
0.4534	9.0	117	0.6094	0.82
0.4684	10.0	130	0.5789	0.74
0.3442	11.0	143	0.7297	0.82
0.3236	12.0	156	0.7688	0.79
0.4645	13.0	169	0.6687	0.76
0.3532	14.0	182	0.7880	0.84
0.3394	15.0	195	0.7216	0.79
0.3311	16.0	208	0.7209	0.79
0.3367	17.0	221	0.6827	0.71
0.3673	18.0	234	0.7472	0.76
0.3024	19.0	247	0.7761	0.79
0.3624	20.0	260	0.7437	0.76

Framework versions

Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1