You can deploy this model and start earning money today!

MinhLe999/
mobilenetv3-BlurryDetection-v2

Name: mobilenetv3-BlurryDetection-v2
Availability: InStock

Views

No views yet

mobilenetv3-BlurryDetection-v2

This model is a fine-tuned version of MinhLe999/mobilenetv3-HandwritingStrip-RandImg on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
0.0545	0.4405	200	0.1432	0.9715	0.9604	0.9828	0.9715	0.9941
0.0891	0.8811	400	0.0674	0.9785	0.9637	0.9939	0.9786	0.9976
0.0436	1.3216	600	0.0701	0.9795	0.9683	0.9909	0.9795	0.9980
0.0531	1.7621	800	0.0964	0.974	0.9526	0.9970	0.9743	0.9984
0.0401	2.2026	1000	0.1098	0.981	0.9675	0.9949	0.9810	0.9980
0.0269	2.6432	1200	0.0942	0.982	0.9666	0.9980	0.9821	0.9974
0.0414	3.0837	1400	0.0728	0.984	0.9723	0.9959	0.9840	0.9986
0.0116	3.5242	1600	0.0847	0.982	0.9703	0.9939	0.9820	0.9986
0.0251	3.9648	1800	0.0887	0.982	0.9694	0.9949	0.982	0.9984