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: 0.4110
Accuracy: 0.9091

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.8891	0.3636
No log	2.0	3	0.5901	0.6364
No log	3.0	5	0.5270	0.6364
No log	4.0	6	0.4946	0.7273
No log	5.0	7	0.4724	0.8182
No log	6.0	9	0.4406	0.8182
0.3043	7.0	11	0.4110	0.9091
0.3043	8.0	12	0.4048	0.9091

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3

skohli01/finetuned-parkinson-classification

swin-tiny-patch4-window7-224-finetuned-parkinson-classification

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

skohli01/
finetuned-parkinson-classification