UniversalAlgorithmic/segformer-finetuned-sidewalk-10k-steps

<!-- 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-finetuned-sidewalk-10k-steps

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

• —Loss: 0.7374
• —Mean Iou: 0.2416
• —Mean Accuracy: 0.2999
• —Overall Accuracy: 0.7734
• —Accuracy Unlabeled: nan
• —Accuracy Flat-road: 0.6510
• —Accuracy Flat-sidewalk: 0.9233
• —Accuracy Flat-crosswalk: 0.2213
• —Accuracy Flat-cyclinglane: 0.7913
• —Accuracy Flat-parkingdriveway: 0.1622
• —Accuracy Flat-railtrack: nan
• —Accuracy Flat-curb: 0.2644
• —Accuracy Human-person: 0.5132
• —Accuracy Human-rider: 0.0
• —Accuracy Vehicle-car: 0.8762
• —Accuracy Vehicle-truck: 0.0
• —Accuracy Vehicle-bus: 0.0
• —Accuracy Vehicle-tramtrain: 0.0
• —Accuracy Vehicle-motorcycle: 0.0
• —Accuracy Vehicle-bicycle: 0.5599
• —Accuracy Vehicle-caravan: 0.0
• —Accuracy Vehicle-cartrailer: 0.0
• —Accuracy Construction-building: 0.8477
• —Accuracy Construction-door: 0.0
• —Accuracy Construction-wall: 0.3544
• —Accuracy Construction-fenceguardrail: 0.2162
• —Accuracy Construction-bridge: 0.0
• —Accuracy Construction-tunnel: nan
• —Accuracy Construction-stairs: 0.0
• —Accuracy Object-pole: 0.4378
• —Accuracy Object-trafficsign: 0.0
• —Accuracy Object-trafficlight: 0.0
• —Accuracy Nature-vegetation: 0.8943
• —Accuracy Nature-terrain: 0.8209
• —Accuracy Sky: 0.9377
• —Accuracy Void-ground: 0.0
• —Accuracy Void-dynamic: 0.0
• —Accuracy Void-static: 0.1252
• —Accuracy Void-unclear: 0.0
• —Iou Unlabeled: nan
• —Iou Flat-road: 0.5135
• —Iou Flat-sidewalk: 0.7767
• —Iou Flat-crosswalk: 0.2106
• —Iou Flat-cyclinglane: 0.4920
• —Iou Flat-parkingdriveway: 0.1421
• —Iou Flat-railtrack: nan
• —Iou Flat-curb: 0.1965
• —Iou Human-person: 0.4309
• —Iou Human-rider: 0.0
• —Iou Vehicle-car: 0.7003
• —Iou Vehicle-truck: 0.0
• —Iou Vehicle-bus: 0.0
• —Iou Vehicle-tramtrain: 0.0
• —Iou Vehicle-motorcycle: 0.0
• —Iou Vehicle-bicycle: 0.4517
• —Iou Vehicle-caravan: 0.0
• —Iou Vehicle-cartrailer: 0.0
• —Iou Construction-building: 0.5982
• —Iou Construction-door: 0.0
• —Iou Construction-wall: 0.2905
• —Iou Construction-fenceguardrail: 0.1754
• —Iou Construction-bridge: 0.0
• —Iou Construction-tunnel: nan
• —Iou Construction-stairs: 0.0
• —Iou Object-pole: 0.2811
• —Iou Object-trafficsign: 0.0
• —Iou Object-trafficlight: 0.0
• —Iou Nature-vegetation: 0.7988
• —Iou Nature-terrain: 0.6516
• —Iou Sky: 0.9071
• —Iou Void-ground: 0.0
• —Iou Void-dynamic: 0.0
• —Iou Void-static: 0.1129
• —Iou Void-unclear: 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: 8
• —evalbatchsize: 8
• —seed: 1337
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: polynomial
• —training_steps: 10000

Training results

Framework versions

• —Transformers 4.49.0
• —Pytorch 2.6.0+cu118
• —Datasets 3.3.1
• —Tokenizers 0.21.0