slm-segformer-080823-b1

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->

slm-segformer-080823-b1

This model is a fine-tuned version of nvidia/mit-b1 on patches from sketched boundaries during the SmartLandMaps project. It achieves the following results on the evaluation set:

• Train Loss: 0.0257
• Validation Loss: 0.0271
• Validation Mean Iou: 0.8583
• Validation Mean Accuracy: 0.9196
• Validation Overall Accuracy: 0.9888
• Validation Per Category Iou: [0.98849374 0.72800628]
• Validation Per Category Accuracy: [0.99410982 0.84499592]
• Epoch: 9

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

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Tokenizers 0.13.3