metadata

license: apache-2.0
base_model: microsoft/swin-base-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swin-base-patch4-window7-224-finetuned-piid
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: val
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8127853881278538

swin-base-patch4-window7-224-finetuned-piid

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.6630
Accuracy: 0.8128

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
1.1815	0.98	20	1.0441	0.5251
0.6548	2.0	41	0.8150	0.6393
0.6083	2.98	61	0.6395	0.6986
0.4925	4.0	82	0.6273	0.6804
0.4448	4.98	102	0.4812	0.8174
0.3387	6.0	123	0.5868	0.7945
0.2622	6.98	143	0.7868	0.7260
0.2656	8.0	164	0.4432	0.8128
0.2259	8.98	184	0.6553	0.7489
0.1997	10.0	205	0.5143	0.7854
0.1892	10.98	225	0.5657	0.7945
0.1522	12.0	246	0.7339	0.7580
0.1309	12.98	266	0.6064	0.8174
0.1482	14.0	287	0.5875	0.8128
0.1459	14.98	307	0.6443	0.7900
0.1224	16.0	328	0.6521	0.8037
0.0533	16.98	348	0.5915	0.8493
0.1133	18.0	369	0.6152	0.8265
0.0923	18.98	389	0.6819	0.7854
0.086	19.51	400	0.6630	0.8128

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1