segformer-b0-finetuned-segments-sidewalk-2

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

• eval_loss: 0.9118
• eval_mean_iou: 0.1726
• eval_mean_accuracy: 0.2154
• eval_overall_accuracy: 0.7733
• eval_accuracy_unlabeled: nan
• eval_accuracy_flat-road: 0.8295
• eval_accuracy_flat-sidewalk: 0.9526
• eval_accuracy_flat-crosswalk: 0.0
• eval_accuracy_flat-cyclinglane: 0.5332
• eval_accuracy_flat-parkingdriveway: 0.0181
• eval_accuracy_flat-railtrack: nan
• eval_accuracy_flat-curb: 0.0398
• eval_accuracy_human-person: 0.0
• eval_accuracy_human-rider: 0.0
• eval_accuracy_vehicle-car: 0.8847
• eval_accuracy_vehicle-truck: 0.0
• eval_accuracy_vehicle-bus: 0.0
• eval_accuracy_vehicle-tramtrain: 0.0
• eval_accuracy_vehicle-motorcycle: 0.0
• eval_accuracy_vehicle-bicycle: 0.0
• eval_accuracy_vehicle-caravan: 0.0
• eval_accuracy_vehicle-cartrailer: 0.0
• eval_accuracy_construction-building: 0.9105
• eval_accuracy_construction-door: 0.0
• eval_accuracy_construction-wall: 0.0135
• eval_accuracy_construction-fenceguardrail: 0.0
• eval_accuracy_construction-bridge: 0.0
• eval_accuracy_construction-tunnel: nan
• eval_accuracy_construction-stairs: 0.0
• eval_accuracy_object-pole: 0.0
• eval_accuracy_object-trafficsign: 0.0
• eval_accuracy_object-trafficlight: 0.0
• eval_accuracy_nature-vegetation: 0.9103
• eval_accuracy_nature-terrain: 0.8654
• eval_accuracy_sky: 0.9359
• eval_accuracy_void-ground: 0.0
• eval_accuracy_void-dynamic: 0.0
• eval_accuracy_void-static: 0.0000
• eval_accuracy_void-unclear: 0.0
• eval_iou_unlabeled: nan
• eval_iou_flat-road: 0.5508
• eval_iou_flat-sidewalk: 0.7999
• eval_iou_flat-crosswalk: 0.0
• eval_iou_flat-cyclinglane: 0.4793
• eval_iou_flat-parkingdriveway: 0.0178
• eval_iou_flat-railtrack: nan
• eval_iou_flat-curb: 0.0379
• eval_iou_human-person: 0.0
• eval_iou_human-rider: 0.0
• eval_iou_vehicle-car: 0.6617
• eval_iou_vehicle-truck: 0.0
• eval_iou_vehicle-bus: 0.0
• eval_iou_vehicle-tramtrain: 0.0
• eval_iou_vehicle-motorcycle: 0.0
• eval_iou_vehicle-bicycle: 0.0
• eval_iou_vehicle-caravan: 0.0
• eval_iou_vehicle-cartrailer: 0.0
• eval_iou_construction-building: 0.6156
• eval_iou_construction-door: 0.0
• eval_iou_construction-wall: 0.0135
• eval_iou_construction-fenceguardrail: 0.0
• eval_iou_construction-bridge: 0.0
• eval_iou_construction-tunnel: nan
• eval_iou_construction-stairs: 0.0
• eval_iou_object-pole: 0.0
• eval_iou_object-trafficsign: 0.0
• eval_iou_object-trafficlight: 0.0
• eval_iou_nature-vegetation: 0.7728
• eval_iou_nature-terrain: 0.7000
• eval_iou_sky: 0.8753
• eval_iou_void-ground: 0.0
• eval_iou_void-dynamic: 0.0
• eval_iou_void-static: 0.0000
• eval_iou_void-unclear: 0.0
• eval_runtime: 13.7353
• eval_samples_per_second: 14.561
• eval_steps_per_second: 7.28
• epoch: 1.3
• step: 520

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
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0