metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-finetuned-vosap
    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: 0.5

swin-tiny-patch4-window7-224-finetuned-vosap

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: 0.5813
Accuracy: 0.5

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.6077	0.5
No log	2.0	2	0.5957	0.5
No log	3.0	3	0.6554	0.5
No log	4.0	4	0.7486	0.25
No log	5.0	5	0.8207	0.25
No log	6.0	6	0.8213	0.25
No log	7.0	7	0.7957	0.5
No log	8.0	8	0.7098	0.5
No log	9.0	9	0.6372	0.5
0.2113	10.0	10	0.5358	0.5
0.2113	11.0	11	0.4894	0.75
0.2113	12.0	12	0.4507	0.75
0.2113	13.0	13	0.4311	0.75
0.2113	14.0	14	0.4339	0.75
0.2113	15.0	15	0.4600	0.75
0.2113	16.0	16	0.4982	0.5
0.2113	17.0	17	0.5299	0.5
0.2113	18.0	18	0.5602	0.5
0.2113	19.0	19	0.5777	0.5
0.0955	20.0	20	0.5813	0.5

Framework versions

Transformers 4.21.3
Pytorch 1.12.1+cu113
Datasets 2.4.0
Tokenizers 0.12.1