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-blank_img
    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: 0.9448669201520913

swin-tiny-patch4-window7-224-blank_img

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: 0.1727
Accuracy: 0.9449

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
0.2646	1.0	74	0.1974	0.9392
0.2287	2.0	148	0.1979	0.9354
0.198	3.0	222	0.1727	0.9449
0.1889	4.0	296	0.1747	0.9430
0.223	5.0	370	0.1711	0.9449
0.1771	6.0	444	0.1697	0.9382
0.1864	7.0	518	0.1672	0.9392
0.1716	8.0	592	0.1801	0.9430
0.192	9.0	666	0.1754	0.9411
0.1886	10.0	740	0.1766	0.9420

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0