segformer-b0-finetuned-segments-sidewalk-2

• Loss: 2.3484
• Mean Iou: 0.1125
• Mean Accuracy: 0.4713
• Overall Accuracy: 0.7748
• Accuracy Unlabeled: nan
• Accuracy Flat-road: 0.7626
• Accuracy Flat-sidewalk: 0.0
• Accuracy Flat-crosswalk: nan
• Accuracy Flat-cyclinglane: 0.9544
• Accuracy Flat-parkingdriveway: nan
• Accuracy Flat-railtrack: 0.1682
• Accuracy Flat-curb: nan
• Accuracy Human-person: nan
• Accuracy Human-rider: nan
• Accuracy Vehicle-car: nan
• Accuracy Vehicle-truck: nan
• Accuracy Vehicle-bus: nan
• Accuracy Vehicle-tramtrain: nan
• Accuracy Vehicle-motorcycle: nan
• Accuracy Vehicle-bicycle: nan
• Accuracy Vehicle-caravan: nan
• Accuracy Vehicle-cartrailer: nan
• Accuracy Construction-building: nan
• Accuracy Construction-door: nan
• Accuracy Construction-wall: nan
• Accuracy Construction-fenceguardrail: nan
• Accuracy Construction-bridge: nan
• Accuracy Construction-tunnel: nan
• Accuracy Construction-stairs: nan
• Accuracy Object-pole: nan
• Accuracy Object-trafficsign: nan
• Accuracy Object-trafficlight: nan
• Accuracy Nature-vegetation: nan
• Accuracy Nature-terrain: nan
• Accuracy Sky: nan
• Accuracy Void-ground: nan
• Accuracy Void-dynamic: nan
• Accuracy Void-static: nan
• Accuracy Void-unclear: nan
• Iou Unlabeled: 0.0
• Iou Flat-road: 0.7426
• Iou Flat-sidewalk: 0.0
• Iou Flat-crosswalk: nan
• Iou Flat-cyclinglane: 0.4695
• Iou Flat-parkingdriveway: nan
• Iou Flat-railtrack: 0.1375
• Iou Flat-curb: 0.0
• Iou Human-person: nan
• Iou Human-rider: nan
• Iou Vehicle-car: nan
• Iou Vehicle-truck: nan
• Iou Vehicle-bus: 0.0
• Iou Vehicle-tramtrain: nan
• Iou Vehicle-motorcycle: nan
• Iou Vehicle-bicycle: nan
• Iou Vehicle-caravan: 0.0
• Iou Vehicle-cartrailer: nan
• Iou Construction-building: 0.0
• Iou Construction-door: nan
• Iou Construction-wall: nan
• Iou Construction-fenceguardrail: nan
• Iou Construction-bridge: nan
• Iou Construction-tunnel: nan
• Iou Construction-stairs: nan
• Iou Object-pole: nan
• Iou Object-trafficsign: nan
• Iou Object-trafficlight: 0.0
• Iou Nature-vegetation: 0.0
• Iou Nature-terrain: nan
• Iou Sky: nan
• Iou Void-ground: 0.0
• Iou Void-dynamic: nan
• Iou Void-static: nan
• Iou Void-unclear: nan

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 6e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cpu
• Datasets 2.21.0
• Tokenizers 0.19.1