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-fish
    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: 0.8333333333333334

swin-tiny-patch4-window7-224-finetuned-fish

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: 0.7059
Accuracy: 0.8333

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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	1.8803	0.5
No log	2.0	2	1.8439	0.5
No log	3.0	3	1.7572	0.5
No log	4.0	4	1.6256	0.5
No log	5.0	5	1.5082	0.5
No log	6.0	6	1.4301	0.5
No log	7.0	7	1.3379	0.5
No log	8.0	8	1.2260	0.5
No log	9.0	9	1.1071	0.6667
0.6539	10.0	10	0.9941	0.6667
0.6539	11.0	11	0.8836	0.6667
0.6539	12.0	12	0.7859	0.6667
0.6539	13.0	13	0.7059	0.8333
0.6539	14.0	14	0.6358	0.8333
0.6539	15.0	15	0.5752	0.8333
0.6539	16.0	16	0.5343	0.8333
0.6539	17.0	17	0.4994	0.8333
0.6539	18.0	18	0.4755	0.8333
0.6539	19.0	19	0.4544	0.8333
0.2777	20.0	20	0.4328	0.8333
0.2777	21.0	21	0.4171	0.8333
0.2777	22.0	22	0.4066	0.8333
0.2777	23.0	23	0.3995	0.8333
0.2777	24.0	24	0.3954	0.8333
0.2777	25.0	25	0.3933	0.8333

Framework versions

Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1