code135/scene_segmentation

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

• Train Loss: nan
• Validation Loss: nan
• Validation Mean Iou: 0.0183
• Validation Mean Accuracy: 0.1667
• Validation Overall Accuracy: 0.1607
• Validation Accuracy Ciel: 1.0
• Validation Accuracy Vegetation: 0.0
• Validation Accuracy Batiment peu vitre (<50%): 0.0
• Validation Accuracy Batiment tres vitre (>50%): 0.0
• Validation Accuracy Couvert: 0.0
• Validation Accuracy Autre: 0.0
• Validation Iou Ciel: 0.1098
• Validation Iou Vegetation: 0.0
• Validation Iou Batiment peu vitre (<50%): 0.0
• Validation Iou Batiment tres vitre (>50%): 0.0
• Validation Iou Couvert: 0.0
• Validation Iou Autre: 0.0
• Epoch: 2

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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 6e-05, 'decay_steps': 120, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Validation Mean Iou	Validation Mean Accuracy	Validation Overall Accuracy	Validation Accuracy Ciel	Validation Accuracy Vegetation	Validation Accuracy Batiment peu vitre (<50%)	Validation Accuracy Batiment tres vitre (>50%)	Validation Accuracy Couvert	Validation Accuracy Autre	Validation Iou Ciel	Validation Iou Vegetation	Validation Iou Batiment peu vitre (<50%)	Validation Iou Batiment tres vitre (>50%)	Validation Iou Couvert	Validation Iou Autre	Epoch
nan	nan	0.0183	0.1667	0.1607	1.0	0.0	0.0	0.0	0.0	0.0	0.1098	0.0	0.0	0.0	0.0	0.0	0
nan	nan	0.0183	0.1667	0.1607	1.0	0.0	0.0	0.0	0.0	0.0	0.1098	0.0	0.0	0.0	0.0	0.0	1
nan	nan	0.0183	0.1667	0.1607	1.0	0.0	0.0	0.0	0.0	0.0	0.1098	0.0	0.0	0.0	0.0	0.0	2

Framework versions

• Transformers 4.46.2
• TensorFlow 2.17.1
• Datasets 3.1.0
• Tokenizers 0.20.3