IrshadG/segformer-b0-finetuned-segments-sidewalk-123

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

segformer-b0-finetuned-segments-sidewalk-123

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:

• —eval_loss: 0.5603
• —evalmeaniou: 0.3194
• —evalmeanaccuracy: 0.3797
• —evaloverallaccuracy: 0.8649
• —evalaccuracyunlabeled: nan
• —evalaccuracyflat-road: 0.8652
• —evalaccuracyflat-sidewalk: 0.9642
• —evalaccuracyflat-crosswalk: 0.6083
• —evalaccuracyflat-cyclinglane: 0.7173
• —evalaccuracyflat-parkingdriveway: 0.5189
• —evalaccuracyflat-railtrack: 0.0
• —evalaccuracyflat-curb: 0.6089
• —evalaccuracyhuman-person: 0.8421
• —evalaccuracyhuman-rider: 0.0
• —evalaccuracyvehicle-car: 0.9347
• —evalaccuracyvehicle-truck: 0.0
• —evalaccuracyvehicle-bus: 0.0
• —evalaccuracyvehicle-tramtrain: 0.0
• —evalaccuracyvehicle-motorcycle: 0.0
• —evalaccuracyvehicle-bicycle: 0.7877
• —evalaccuracyvehicle-caravan: 0.0
• —evalaccuracyvehicle-cartrailer: 0.0
• —evalaccuracyconstruction-building: 0.9288
• —evalaccuracyconstruction-door: 0.0851
• —evalaccuracyconstruction-wall: 0.4696
• —evalaccuracyconstruction-fenceguardrail: 0.4756
• —evalaccuracyconstruction-bridge: 0.0
• —evalaccuracyconstruction-tunnel: nan
• —evalaccuracyconstruction-stairs: 0.0047
• —evalaccuracyobject-pole: 0.3599
• —evalaccuracyobject-trafficsign: 0.0028
• —evalaccuracyobject-trafficlight: 0.0
• —evalaccuracynature-vegetation: 0.9419
• —evalaccuracynature-terrain: 0.8921
• —evalaccuracysky: 0.9773
• —evalaccuracyvoid-ground: 0.0003
• —evalaccuracyvoid-dynamic: 0.1852
• —evalaccuracyvoid-static: 0.3603
• —evalaccuracyvoid-unclear: 0.0
• —evaliouunlabeled: nan
• —evaliouflat-road: 0.7774
• —evaliouflat-sidewalk: 0.8659
• —evaliouflat-crosswalk: 0.4889
• —evaliouflat-cyclinglane: 0.6488
• —evaliouflat-parkingdriveway: 0.4072
• —evaliouflat-railtrack: 0.0
• —evaliouflat-curb: 0.4944
• —evaliouhuman-person: 0.6064
• —evaliouhuman-rider: 0.0
• —evaliouvehicle-car: 0.8283
• —evaliouvehicle-truck: 0.0
• —evaliouvehicle-bus: 0.0
• —evaliouvehicle-tramtrain: 0.0
• —evaliouvehicle-motorcycle: 0.0
• —evaliouvehicle-bicycle: 0.5105
• —evaliouvehicle-caravan: 0.0
• —evaliouvehicle-cartrailer: 0.0
• —evaliouconstruction-building: 0.7458
• —evaliouconstruction-door: 0.0760
• —evaliouconstruction-wall: 0.4006
• —evaliouconstruction-fenceguardrail: 0.3288
• —evaliouconstruction-bridge: 0.0
• —evaliouconstruction-tunnel: nan
• —evaliouconstruction-stairs: 0.0047
• —evaliouobject-pole: 0.2789
• —evaliouobject-trafficsign: 0.0027
• —evaliouobject-trafficlight: 0.0
• —evaliounature-vegetation: 0.8781
• —evaliounature-terrain: 0.8170
• —evaliousky: 0.9417
• —evaliouvoid-ground: 0.0002
• —evaliouvoid-dynamic: 0.1706
• —evaliouvoid-static: 0.2686
• —evaliouvoid-unclear: 0.0
• —eval_runtime: 246.8492
• —evalsamplesper_second: 0.81
• —evalstepsper_second: 0.405
• —epoch: 15.45
• —step: 6180

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
• —trainbatchsize: 2
• —evalbatchsize: 2
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 50

Framework versions

• —Transformers 4.35.0
• —Pytorch 2.2.0+cpu
• —Datasets 2.14.6
• —Tokenizers 0.14.1