Psoriasis-500-100aug-224-swinv2-large

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

• Loss: 0.7383
• Accuracy: 0.8227

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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
1.4126	0.9840	46	0.9408	0.6882
0.3672	1.9893	93	0.6431	0.7703
0.133	2.9947	140	0.5938	0.7921
0.0624	4.0	187	0.6128	0.8035
0.0473	4.9840	233	0.6654	0.8114
0.0276	5.9893	280	0.7090	0.8166
0.0111	6.9947	327	0.7133	0.8140
0.0081	8.0	374	0.7639	0.8183
0.0039	8.9840	420	0.7387	0.8236
0.0065	9.8396	460	0.7383	0.8227

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1