segformer-b0-finetuned-ade20k-manggarai_rivergate

This model is a fine-tuned version of nvidia/segformer-b0-finetuned-ade-512-512 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0566
• Mean Iou: 0.0
• Mean Accuracy: nan
• Overall Accuracy: nan
• Accuracy Not water: nan
• Accuracy Waters: nan
• Iou Not water: 0.0
• Iou Waters: 0.0

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: 6e-05
• train_batch_size: 8
• eval_batch_size: 8
• 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
• num_epochs: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Not water	Accuracy Waters	Iou Not water	Iou Waters
0.1903	0.0229	20	0.1300	0.0	nan	nan	nan	nan	0.0	0.0
0.0799	0.0457	40	0.0794	0.0	nan	nan	nan	nan	0.0	0.0
0.061	0.0686	60	0.0576	0.0	nan	nan	nan	nan	0.0	0.0
0.045	0.0914	80	0.0566	0.0	nan	nan	nan	nan	0.0	0.0

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cpu
• Datasets 3.1.0
• Tokenizers 0.21.0