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: 0.7818
Mean Iou: 0.1872
Mean Accuracy: 0.2343
Overall Accuracy: 0.7917
Accuracy Unlabeled: nan
Accuracy Flat-road: 0.8716
Accuracy Flat-sidewalk: 0.9457
Accuracy Flat-crosswalk: 0.0
Accuracy Flat-cyclinglane: 0.6578
Accuracy Flat-parkingdriveway: 0.2561
Accuracy Flat-railtrack: nan
Accuracy Flat-curb: 0.2287
Accuracy Human-person: 0.0
Accuracy Human-rider: 0.0
Accuracy Vehicle-car: 0.9059
Accuracy Vehicle-truck: 0.0
Accuracy Vehicle-bus: 0.0
Accuracy Vehicle-tramtrain: 0.0
Accuracy Vehicle-motorcycle: 0.0
Accuracy Vehicle-bicycle: 0.0
Accuracy Vehicle-caravan: 0.0
Accuracy Vehicle-cartrailer: 0.0
Accuracy Construction-building: 0.8667
Accuracy Construction-door: 0.0
Accuracy Construction-wall: 0.0198
Accuracy Construction-fenceguardrail: 0.0
Accuracy Construction-bridge: 0.0
Accuracy Construction-tunnel: nan
Accuracy Construction-stairs: 0.0
Accuracy Object-pole: 0.0002
Accuracy Object-trafficsign: 0.0
Accuracy Object-trafficlight: 0.0
Accuracy Nature-vegetation: 0.9476
Accuracy Nature-terrain: 0.8466
Accuracy Sky: 0.9510
Accuracy Void-ground: 0.0
Accuracy Void-dynamic: 0.0
Accuracy Void-static: 0.0001
Accuracy Void-unclear: 0.0
Iou Unlabeled: nan
Iou Flat-road: 0.6267
Iou Flat-sidewalk: 0.8545
Iou Flat-crosswalk: 0.0
Iou Flat-cyclinglane: 0.5807
Iou Flat-parkingdriveway: 0.2032
Iou Flat-railtrack: nan
Iou Flat-curb: 0.1902
Iou Human-person: 0.0
Iou Human-rider: 0.0
Iou Vehicle-car: 0.6625
Iou Vehicle-truck: 0.0
Iou Vehicle-bus: 0.0
Iou Vehicle-tramtrain: 0.0
Iou Vehicle-motorcycle: 0.0
Iou Vehicle-bicycle: 0.0
Iou Vehicle-caravan: 0.0
Iou Vehicle-cartrailer: 0.0
Iou Construction-building: 0.5368
Iou Construction-door: 0.0
Iou Construction-wall: 0.0195
Iou Construction-fenceguardrail: 0.0
Iou Construction-bridge: 0.0
Iou Construction-tunnel: nan
Iou Construction-stairs: 0.0
Iou Object-pole: 0.0002
Iou Object-trafficsign: 0.0
Iou Object-trafficlight: 0.0
Iou Nature-vegetation: 0.7879
Iou Nature-terrain: 0.6502
Iou Sky: 0.8781
Iou Void-ground: 0.0
Iou Void-dynamic: 0.0
Iou Void-static: 0.0001
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
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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Flat-road	Accuracy Flat-sidewalk	Accuracy Flat-cyclinglane	Accuracy Flat-parkingdriveway	Accuracy Flat-railtrack	Accuracy Flat-curb	Accuracy Vehicle-car	Accuracy Construction-building	Accuracy Construction-wall	Accuracy Construction-tunnel	Accuracy Object-pole	Accuracy Nature-vegetation	Accuracy Nature-terrain	Accuracy Sky	Accuracy Void-static	Iou Unlabeled	Iou Flat-road	Iou Flat-sidewalk	Iou Flat-cyclinglane	Iou Flat-parkingdriveway	Iou Flat-railtrack	Iou Flat-curb	Iou Vehicle-car	Iou Construction-building	Iou Construction-wall	Iou Construction-tunnel	Iou Object-pole	Iou Nature-vegetation	Iou Nature-terrain	Iou Sky	Iou Void-static
No log	1.0	400	1.0489	0.1563	0.2092	0.7462	nan	0.7727	0.9457	0.5203	0.0416	nan	0.0011	0.8995	0.7747	0.0	nan	0.0	0.8911	0.9117	0.9374	0.0	nan	0.5549	0.7865	0.4480	0.0400	nan	0.0011	0.5695	0.5072	0.0	nan	0.0	0.7359	0.5246	0.8336	0.0
1.4244	2.0	800	0.8409	0.1794	0.2249	0.7813	nan	0.8638	0.9504	0.5945	0.1981	nan	0.1027	0.8937	0.8568	0.0085	nan	0.0000	0.9426	0.8503	0.9368	0.0	nan	0.6014	0.8353	0.5403	0.1665	nan	0.0927	0.6676	0.5350	0.0085	nan	0.0000	0.7710	0.6442	0.8776	0.0
1.4244	3.0	1200	0.7818	0.1872	0.2343	0.7917	nan	0.8716	0.9457	0.6578	0.2561	nan	0.2287	0.9059	0.8667	0.0198	nan	0.0002	0.9476	0.8466	0.9510	0.0001	nan	0.6267	0.8545	0.5807	0.2032	nan	0.1902	0.6625	0.5368	0.0195	nan	0.0002	0.7879	0.6502	0.8781	0.0001

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1

Salmamoori/segformer-b0-finetuned-segments-sidewalk-oct-22

segformer-b0-finetuned-segments-sidewalk-oct-22

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Salmamoori/
segformer-b0-finetuned-segments-sidewalk-oct-22