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: 2.3605
Mean Iou: 0.1012
Mean Accuracy: 0.1553
Overall Accuracy: 0.6475
Accuracy Unlabeled: nan
Accuracy Flat-road: 0.5989
Accuracy Flat-sidewalk: 0.8763
Accuracy Flat-crosswalk: 0.0000
Accuracy Flat-cyclinglane: 0.0205
Accuracy Flat-parkingdriveway: 0.0009
Accuracy Flat-railtrack: 0.0
Accuracy Flat-curb: 0.0026
Accuracy Human-person: 0.0
Accuracy Human-rider: 0.0
Accuracy Vehicle-car: 0.7978
Accuracy Vehicle-truck: 0.0
Accuracy Vehicle-bus: nan
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: 0.8528
Accuracy Construction-door: 0.0
Accuracy Construction-wall: 0.0201
Accuracy Construction-fenceguardrail: 0.0
Accuracy Construction-bridge: 0.0
Accuracy Construction-tunnel: nan
Accuracy Construction-stairs: 0.0
Accuracy Object-pole: 0.0
Accuracy Object-trafficsign: 0.0
Accuracy Object-trafficlight: 0.0
Accuracy Nature-vegetation: 0.9027
Accuracy Nature-terrain: 0.4049
Accuracy Sky: 0.4929
Accuracy Void-ground: 0.0
Accuracy Void-dynamic: 0.0
Accuracy Void-static: 0.0006
Accuracy Void-unclear: 0.0
Iou Unlabeled: 0.0
Iou Flat-road: 0.3779
Iou Flat-sidewalk: 0.6630
Iou Flat-crosswalk: 0.0000
Iou Flat-cyclinglane: 0.0196
Iou Flat-parkingdriveway: 0.0009
Iou Flat-railtrack: 0.0
Iou Flat-curb: 0.0024
Iou Human-person: 0.0
Iou Human-rider: 0.0
Iou Vehicle-car: 0.5694
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: 0.4501
Iou Construction-door: 0.0
Iou Construction-wall: 0.0186
Iou Construction-fenceguardrail: 0.0
Iou Construction-bridge: 0.0
Iou Construction-tunnel: 0.0
Iou Construction-stairs: 0.0
Iou Object-pole: 0.0
Iou Object-trafficsign: 0.0
Iou Object-trafficlight: 0.0
Iou Nature-vegetation: 0.6494
Iou Nature-terrain: 0.3108
Iou Sky: 0.4788
Iou Void-ground: 0.0
Iou Void-dynamic: 0.0
Iou Void-static: 0.0006
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: 0.2

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-curb	Accuracy Human-rider	Accuracy Vehicle-car	Accuracy Vehicle-truck	Accuracy Vehicle-bus	Accuracy Vehicle-bicycle	Accuracy Construction-building	Accuracy Construction-wall	Accuracy Construction-tunnel	Accuracy Object-pole	Accuracy Nature-vegetation	Accuracy Nature-terrain	Accuracy Sky	Accuracy Void-static	Iou Flat-road	Iou Flat-sidewalk	Iou Flat-crosswalk	Iou Flat-cyclinglane	Iou Flat-parkingdriveway	Iou Flat-curb	Iou Human-rider	Iou Vehicle-car	Iou Vehicle-truck	Iou Vehicle-bicycle	Iou Construction-building	Iou Construction-wall	Iou Object-pole	Iou Nature-vegetation	Iou Nature-terrain	Iou Sky	Iou Void-static
3.0789	0.05	20	3.2969	0.0860	0.1368	0.5740	nan	0.1836	0.9077	0.0004	0.0125	0.0001	0.0305	0.0131	0.8407	0.0000	nan	0.0040	0.5790	0.0914	nan	0.0000	0.7951	0.5523	0.3670	0.0007	0.1566	0.6044	0.0004	0.0120	0.0001	0.0132	0.0014	0.3364	0.0000	0.0019	0.4126	0.0345	0.0000	0.6545	0.4275	0.3552	0.0007
2.698	0.1	40	2.7840	0.0931	0.1461	0.6155	nan	0.2716	0.9065	0.0000	0.0145	0.0001	0.0033	0.0	0.7123	0.0	nan	0.0	0.7396	0.0291	nan	0.0	0.9204	0.6552	0.4205	0.0013	0.2097	0.6076	0.0000	0.0138	0.0001	0.0029	0.0	0.4849	0.0	0.0	0.4728	0.0233	0.0	0.6013	0.4347	0.4069	0.0012
2.3316	0.15	60	2.4747	0.1009	0.1553	0.6399	nan	0.5021	0.8787	0.0000	0.0247	0.0014	0.0016	0.0	0.7782	0.0	nan	0.0	0.8316	0.0231	nan	0.0	0.9021	0.5653	0.4592	0.0003	0.3276	0.6427	0.0000	0.0232	0.0013	0.0015	0.0	0.5663	0.0	0.0	0.4541	0.0215	0.0	0.6552	0.3860	0.4501	0.0003
2.5773	0.2	80	2.3605	0.1012	0.1553	0.6475	nan	0.5989	0.8763	0.0000	0.0205	0.0009	0.0026	0.0	0.7978	0.0	nan	0.0	0.8528	0.0201	nan	0.0	0.9027	0.4049	0.4929	0.0006	0.3779	0.6630	0.0000	0.0196	0.0009	0.0024	0.0	0.5694	0.0	0.0	0.4501	0.0186	0.0	0.6494	0.3108	0.4788	0.0006

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

miricalderonr/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

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