Segments / README.md
JennnDexter's picture
End of training
5efb9ac
|
raw
history blame
3.41 kB
metadata
license: other
base_model: nvidia/mit-b0
tags:
  - image-segmentation
  - vision
  - generated_from_trainer
model-index:
  - name: Segments
    results: []

Segments

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: 0.9830
  • Mean Iou: 0.1931
  • Mean Accuracy: 0.2401
  • Overall Accuracy: 0.7586
  • Accuracy Unlabeled: nan
  • Accuracy Flat-road: 0.7259
  • Accuracy Flat-sidewalk: 0.9518
  • Accuracy Flat-crosswalk: 0.5588
  • Accuracy Flat-cyclinglane: 0.5550
  • Accuracy Flat-parkingdriveway: 0.1159
  • Accuracy Flat-railtrack: nan
  • Accuracy Flat-curb: 0.1277
  • Accuracy Human-person: 0.0990
  • Accuracy Human-rider: 0.0
  • Accuracy Vehicle-car: 0.9049
  • Accuracy Vehicle-truck: 0.0
  • Accuracy Vehicle-bus: 0.0
  • Accuracy Vehicle-tramtrain: nan
  • Accuracy Vehicle-motorcycle: 0.0
  • Accuracy Vehicle-bicycle: 0.0
  • Accuracy Vehicle-caravan: 0.0
  • Accuracy Vehicle-cartrailer: 0.0
  • Accuracy Construction-building: 0.8590
  • Accuracy Construction-door: 0.0
  • Accuracy Construction-wall: 0.0013
  • Accuracy Construction-fenceguardrail: 0.0
  • Accuracy Construction-bridge: 0.0
  • Accuracy Construction-tunnel: nan
  • Accuracy Construction-stairs: 0.0
  • Accuracy Object-pole: 0.0088
  • Accuracy Object-trafficsign: 0.0
  • Accuracy Object-trafficlight: 0.0
  • Accuracy Nature-vegetation: 0.9206
  • Accuracy Nature-terrain: 0.7756
  • Accuracy Sky: 0.8391
  • 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: 0.5951
  • Iou Flat-sidewalk: 0.7822
  • Iou Flat-crosswalk: 0.5498
  • Iou Flat-cyclinglane: 0.4666
  • Iou Flat-parkingdriveway: 0.1001
  • Iou Flat-railtrack: nan
  • Iou Flat-curb: 0.1078
  • Iou Human-person: 0.0979
  • Iou Human-rider: 0.0
  • Iou Vehicle-car: 0.6265
  • Iou Vehicle-truck: 0.0
  • Iou Vehicle-bus: 0.0
  • Iou Vehicle-tramtrain: nan
  • Iou Vehicle-motorcycle: 0.0
  • Iou Vehicle-bicycle: 0.0
  • Iou Vehicle-caravan: 0.0
  • Iou Vehicle-cartrailer: 0.0
  • Iou Construction-building: 0.4997
  • Iou Construction-door: 0.0
  • Iou Construction-wall: 0.0013
  • Iou Construction-fenceguardrail: 0.0
  • Iou Construction-bridge: 0.0
  • Iou Construction-tunnel: nan
  • Iou Construction-stairs: 0.0
  • Iou Object-pole: 0.0088
  • Iou Object-trafficsign: 0.0
  • Iou Object-trafficlight: 0.0
  • Iou Nature-vegetation: 0.7405
  • Iou Nature-terrain: 0.6034
  • Iou Sky: 0.8052
  • 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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Framework versions

  • Transformers 4.33.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3