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: 2.7084
Mean Iou: 0.0871
Mean Accuracy: 0.1451
Overall Accuracy: 0.6167
Accuracy Unlabeled: nan
Accuracy Flat-road: 0.5180
Accuracy Flat-sidewalk: 0.9088
Accuracy Flat-crosswalk: 0.0001
Accuracy Flat-cyclinglane: 0.0259
Accuracy Flat-parkingdriveway: 0.0
Accuracy Flat-railtrack: nan
Accuracy Flat-curb: 0.0012
Accuracy Human-person: 0.0017
Accuracy Human-rider: 0.0
Accuracy Vehicle-car: 0.9553
Accuracy Vehicle-truck: 0.0
Accuracy Vehicle-bus: 0.0
Accuracy Vehicle-tramtrain: nan
Accuracy Vehicle-motorcycle: 0.0
Accuracy Vehicle-bicycle: 0.0000
Accuracy Vehicle-caravan: 0.0
Accuracy Vehicle-cartrailer: 0.0
Accuracy Construction-building: 0.4663
Accuracy Construction-door: 0.0
Accuracy Construction-wall: 0.0670
Accuracy Construction-fenceguardrail: 0.0
Accuracy Construction-bridge: 0.0
Accuracy Construction-tunnel: nan
Accuracy Construction-stairs: 0.0
Accuracy Object-pole: 0.0064
Accuracy Object-trafficsign: 0.0
Accuracy Object-trafficlight: 0.0
Accuracy Nature-vegetation: 0.9708
Accuracy Nature-terrain: 0.0024
Accuracy Sky: 0.5740
Accuracy Void-ground: 0.0
Accuracy Void-dynamic: 0.0
Accuracy Void-static: 0.0
Accuracy Void-unclear: 0.0
Iou Unlabeled: nan
Iou Flat-road: 0.3925
Iou Flat-sidewalk: 0.6649
Iou Flat-crosswalk: 0.0001
Iou Flat-cyclinglane: 0.0249
Iou Flat-parkingdriveway: 0.0
Iou Flat-railtrack: 0.0
Iou Flat-curb: 0.0012
Iou Human-person: 0.0017
Iou Human-rider: 0.0
Iou Vehicle-car: 0.2851
Iou Vehicle-truck: 0.0
Iou Vehicle-bus: 0.0
Iou Vehicle-tramtrain: 0.0
Iou Vehicle-motorcycle: 0.0
Iou Vehicle-bicycle: 0.0000
Iou Vehicle-caravan: 0.0
Iou Vehicle-cartrailer: 0.0
Iou Construction-building: 0.3825
Iou Construction-door: 0.0
Iou Construction-wall: 0.0540
Iou Construction-fenceguardrail: 0.0
Iou Construction-bridge: 0.0
Iou Construction-tunnel: 0.0
Iou Construction-stairs: 0.0
Iou Object-pole: 0.0048
Iou Object-trafficsign: 0.0
Iou Object-trafficlight: 0.0
Iou Nature-vegetation: 0.6011
Iou Nature-terrain: 0.0024
Iou Sky: 0.5451
Iou Void-ground: 0.0
Iou Void-dynamic: 0.0
Iou Void-static: 0.0
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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Flat-road	Accuracy Flat-sidewalk	Accuracy Flat-crosswalk	Accuracy Flat-cyclinglane	Accuracy Flat-parkingdriveway	Accuracy Flat-railtrack	Accuracy Flat-curb	Accuracy Human-person	Accuracy Human-rider	Accuracy Vehicle-car	Accuracy Vehicle-truck	Accuracy Vehicle-bus	Accuracy Vehicle-tramtrain	Accuracy Vehicle-motorcycle	Accuracy Vehicle-bicycle	Accuracy Vehicle-caravan	Accuracy Vehicle-cartrailer	Accuracy Construction-building	Accuracy Construction-door	Accuracy Construction-wall	Accuracy Construction-fenceguardrail	Accuracy Construction-bridge	Accuracy Construction-tunnel	Accuracy Construction-stairs	Accuracy Object-pole	Accuracy Object-trafficsign	Accuracy Object-trafficlight	Accuracy Nature-vegetation	Accuracy Nature-terrain	Accuracy Sky	Accuracy Void-ground	Accuracy Void-dynamic	Accuracy Void-static	Accuracy Void-unclear	Iou Unlabeled	Iou Flat-road	Iou Flat-sidewalk	Iou Flat-crosswalk	Iou Flat-cyclinglane	Iou Flat-parkingdriveway	Iou Flat-railtrack	Iou Flat-curb	Iou Human-person	Iou Human-rider	Iou Vehicle-car	Iou Vehicle-truck	Iou Vehicle-bus	Iou Vehicle-tramtrain	Iou Vehicle-motorcycle	Iou Vehicle-bicycle	Iou Vehicle-caravan	Iou Vehicle-cartrailer	Iou Construction-building	Iou Construction-door	Iou Construction-wall	Iou Construction-fenceguardrail	Iou Construction-bridge	Iou Construction-tunnel	Iou Construction-stairs	Iou Object-pole	Iou Object-trafficsign	Iou Object-trafficlight	Iou Nature-vegetation	Iou Nature-terrain	Iou Sky	Iou Void-ground	Iou Void-dynamic	Iou Void-static	Iou Void-unclear
2.9796	0.4	20	3.2289	0.0664	0.1236	0.5591	nan	0.2423	0.9160	0.0000	0.0110	0.0000	nan	0.0006	0.0021	0.0	0.9292	0.0	0.0	nan	0.0	0.0000	0.0	0.0	0.2970	0.0	0.1131	0.0	0.0	nan	0.0	0.0502	0.0	0.0	0.9793	0.0015	0.2752	0.0	0.0148	0.0000	0.0	0.0	0.2077	0.6059	0.0000	0.0107	0.0000	0.0	0.0006	0.0020	0.0	0.2985	0.0	0.0	0.0	0.0	0.0000	0.0	0.0	0.2620	0.0	0.0654	0.0	0.0	0.0	0.0	0.0249	0.0	0.0	0.5724	0.0015	0.2711	0.0	0.0027	0.0000	0.0
2.6315	0.8	40	2.7084	0.0871	0.1451	0.6167	nan	0.5180	0.9088	0.0001	0.0259	0.0	nan	0.0012	0.0017	0.0	0.9553	0.0	0.0	nan	0.0	0.0000	0.0	0.0	0.4663	0.0	0.0670	0.0	0.0	nan	0.0	0.0064	0.0	0.0	0.9708	0.0024	0.5740	0.0	0.0	0.0	0.0	nan	0.3925	0.6649	0.0001	0.0249	0.0	0.0	0.0012	0.0017	0.0	0.2851	0.0	0.0	0.0	0.0	0.0000	0.0	0.0	0.3825	0.0	0.0540	0.0	0.0	0.0	0.0	0.0048	0.0	0.0	0.6011	0.0024	0.5451	0.0	0.0	0.0	0.0

Framework versions

Transformers 4.41.1
Pytorch 1.13.1
Datasets 2.19.1
Tokenizers 0.19.1

hbminsi/segformer-b0-finetuned-segments-sidewalk-2

segformer-b0-finetuned-segments-sidewalk-2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hbminsi/
segformer-b0-finetuned-segments-sidewalk-2