ZeeeWP/segformer-b0-finetuned-segments-satellite-terrain

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

segformer-b0-finetuned-segments-satellite-terrain

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

• —Loss: 1.7429
• —Mean Iou: 0.1997
• —Mean Accuracy: 0.3405
• —Overall Accuracy: 0.5221
• —Accuracy Unlabeled: nan
• —Accuracy Sand: 0.5941
• —Accuracy Cliff: 0.5946
• —Accuracy Bedrock flat: 0.7071
• —Accuracy Bedrock lowhill: 0.0427
• —Accuracy Bedrock highhill: 0.0
• —Accuracy Gravel low hill: 0.4448
• —Accuracy Gravel high hill: 0.0
• —Iou Unlabeled: 0.0
• —Iou Sand: 0.4244
• —Iou Cliff: 0.4248
• —Iou Bedrock flat: 0.4794
• —Iou Bedrock lowhill: 0.0361
• —Iou Bedrock highhill: 0.0
• —Iou Gravel low hill: 0.2331
• —Iou Gravel high hill: 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
• —trainbatchsize: 4
• —evalbatchsize: 4
• —seed: 42
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —num_epochs: 10

Training results

Framework versions

• —Transformers 4.46.3
• —Pytorch 2.4.1+cu121
• —Datasets 3.1.0
• —Tokenizers 0.20.3