dousey/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: 0.0217
• Validation Mean Accuracy: 0.5
• Validation Overall Accuracy: 0.2545
• Validation Accuracy Background: 1.0
• Validation Accuracy Bleuet: 0.0
• Validation Accuracy Comptonie: nan
• Validation Accuracy Kalmia: nan
• Validation Iou Background: 0.0433
• Validation Iou Bleuet: 0.0
• Validation Iou Comptonie: nan
• Validation Iou Kalmia: 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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 6e-05, 'decay_steps': 76500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 Background	Validation Accuracy Bleuet	Validation Accuracy Comptonie	Validation Accuracy Kalmia	Validation Iou Background	Validation Iou Bleuet	Validation Iou Comptonie	Validation Iou Kalmia	Epoch
nan	nan	0.0217	0.5	0.2545	1.0	0.0	nan	nan	0.0433	0.0	nan	nan	0
nan	nan	0.0217	0.5	0.2545	1.0	0.0	nan	nan	0.0433	0.0	nan	nan	1

Framework versions

• Transformers 4.26.0
• TensorFlow 2.9.2
• Datasets 2.9.0
• Tokenizers 0.13.2