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

Loss: 0.4238
Accuracy: 0.9345

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: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7682	1.0	125	1.0104	0.7083
0.5426	2.0	250	0.4423	0.8571
0.1598	3.0	375	0.3282	0.8810
0.0529	4.0	500	0.3018	0.9137
0.0216	5.0	625	0.2928	0.9226
0.0135	6.0	750	0.2874	0.9286
0.0135	7.0	875	0.3382	0.9137
0.0082	8.0	1000	0.3456	0.9226
0.0039	9.0	1125	0.3589	0.9256
0.0025	10.0	1250	0.3539	0.9315
0.0038	11.0	1375	0.4166	0.9196
0.004	12.0	1500	0.4284	0.9286
0.0022	13.0	1625	0.4279	0.9345
0.001	14.0	1750	0.4176	0.9345
0.0014	15.0	1875	0.4238	0.9345

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0

cvmil/swin-base-patch4-window7-224_augmented-v2_fft

swin-base-patch4-window7-224_rice-leaf-disease-augmented-v2_fft

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

cvmil/
swin-base-patch4-window7-224_augmented-v2_fft