cvmil/swin-base-patch4-window7-224_rice-leaf-disease-augmented_tl

Source: 🤗🏴‍☠️ Rescued by: isiliconimage-classificationapache-2.087M params348 MBsafetensors✓ 5 checksumsupdated 652d ago

Magnet 5

swin-base-patch4-window7-224_rice-leaf-disease-augmented_tl_020125

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: 0.6198
Accuracy: 0.7955

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: 0.001
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: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
1.9251	1.0	250	0.492	1.5964
1.3185	2.0	500	0.669	1.0944
1.0055	3.0	750	0.721	0.9142
0.8773	4.0	1000	0.7405	0.8254
0.8008	5.0	1250	0.7565	0.7678
0.7496	6.0	1500	0.7655	0.7288
0.7126	7.0	1750	0.7733	0.6998
0.685	8.0	2000	0.777	0.6766
0.6637	9.0	2250	0.783	0.6594
0.6488	10.0	2500	0.7865	0.6473
0.6356	11.0	2750	0.7905	0.6373
0.6268	12.0	3000	0.793	0.6296
0.6191	13.0	3250	0.7955	0.6238
0.6143	14.0	3500	0.795	0.6210
0.6115	15.0	3750	0.7955	0.6198

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0