Lit4pCol4b/segformer-b1-finetuned-ade-512-512_segformer_ADE20k_RGB_IS_v1

This model is a fine-tuned version of nvidia/segformer-b1-finetuned-ade-512-512 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: nan
• Validation Loss: nan
• Validation Mean Iou: 0.8984
• Validation Mean Accuracy: 1.0
• Validation Overall Accuracy: 1.0
• Validation Accuracy Unlabeled: 1.0
• Validation Accuracy Objeto Interes: nan
• Validation Accuracy Agua: nan
• Validation Iou Unlabeled: 0.8984
• Validation Iou Objeto Interes: nan
• Validation Iou Agua: nan
• Epoch: 1

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:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 6e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Validation Mean Iou	Validation Mean Accuracy	Validation Overall Accuracy	Validation Accuracy Unlabeled	Validation Accuracy Objeto Interes	Validation Accuracy Agua	Validation Iou Unlabeled	Validation Iou Objeto Interes	Validation Iou Agua	Epoch
nan	nan	0.8984	1.0	1.0	1.0	nan	nan	0.8984	nan	nan	0
nan	nan	0.8984	1.0	1.0	1.0	nan	nan	0.8984	nan	nan	1

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.0