Hugging Face's logo

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

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
segformer-b0-finetuned-segments-sidewalk-oct-22 / README.md
Salmamoori's picture
Salmamoori
End of training
c5230a7 verified
preview code
|
raw
history blame
42.7 kB
metadata
license: other
base_model: nvidia/mit-b0
tags:
  - vision
  - image-segmentation
  - generated_from_trainer
model-index:
  - name: segformer-b0-finetuned-segments-sidewalk-oct-22
    results: []

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

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: 1.2519
  • Mean Iou: 0.1522
  • Mean Accuracy: 0.2003
  • Overall Accuracy: 0.7240
  • Accuracy Unlabeled: nan
  • Accuracy Flat-road: 0.7728
  • Accuracy Flat-sidewalk: 0.9359
  • Accuracy Flat-crosswalk: 0.0
  • Accuracy Flat-cyclinglane: 0.3852
  • Accuracy Flat-parkingdriveway: 0.0097
  • Accuracy Flat-railtrack: nan
  • Accuracy Flat-curb: 0.0
  • Accuracy Human-person: 0.0
  • Accuracy Human-rider: 0.0
  • Accuracy Vehicle-car: 0.8668
  • 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: 0.8650
  • Accuracy Construction-door: 0.0
  • Accuracy Construction-wall: 0.0000
  • 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: 0.9477
  • Accuracy Nature-terrain: 0.7234
  • Accuracy Sky: 0.9033
  • 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: 0.5016
  • Iou Flat-sidewalk: 0.7469
  • Iou Flat-crosswalk: 0.0
  • Iou Flat-cyclinglane: 0.3601
  • Iou Flat-parkingdriveway: 0.0096
  • Iou Flat-railtrack: nan
  • Iou Flat-curb: 0.0
  • Iou Human-person: 0.0
  • Iou Human-rider: 0.0
  • Iou Vehicle-car: 0.5774
  • 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: 0.5352
  • Iou Construction-door: 0.0
  • Iou Construction-wall: 0.0000
  • Iou Construction-fenceguardrail: 0.0
  • Iou Construction-bridge: 0.0
  • Iou Construction-tunnel: nan
  • Iou Construction-stairs: 0.0
  • Iou Object-pole: 0.0
  • Iou Object-trafficsign: 0.0
  • Iou Object-trafficlight: 0.0
  • Iou Nature-vegetation: 0.7277
  • Iou Nature-terrain: 0.5775
  • Iou Sky: 0.8350
  • 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: 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: 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
2.4782 0.05 20 2.4249 0.0836 0.1376 0.6010 nan 0.6155 0.8719 0.0 0.0011 0.0002 nan 0.0003 0.0 0.0 0.8951 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.7118 0.0 0.0001 0.0016 0.0 nan 0.0 0.0072 0.0 0.0 0.9631 0.0000 0.3367 0.0 0.0 0.0 0.0 nan 0.3522 0.6415 0.0 0.0011 0.0002 0.0 0.0003 0.0 0.0 0.4197 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4674 0.0 0.0001 0.0015 0.0 nan 0.0 0.0065 0.0 0.0 0.5431 0.0000 0.3265 0.0 0.0 0.0 0.0
1.7849 0.1 40 2.0726 0.0987 0.1471 0.6229 nan 0.5815 0.8992 0.0 0.0002 0.0003 nan 0.0007 0.0 0.0 0.8199 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.7954 0.0 0.0000 0.0 0.0 nan 0.0 0.0001 0.0 0.0 0.9628 0.0000 0.6476 0.0 0.0 0.0 0.0 nan 0.3595 0.6501 0.0 0.0002 0.0003 nan 0.0007 0.0 0.0 0.4671 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4738 0.0 0.0000 0.0 0.0 nan 0.0 0.0001 0.0 0.0 0.5760 0.0000 0.6303 0.0 0.0 0.0 0.0
1.7025 0.15 60 1.8102 0.1062 0.1576 0.6393 nan 0.6636 0.8973 0.0 0.0002 0.0003 nan 0.0000 0.0 0.0 0.9012 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8097 0.0 0.0020 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.9416 0.0000 0.8286 0.0 0.0 0.0 0.0 nan 0.3808 0.6706 0.0 0.0002 0.0003 nan 0.0000 0.0 0.0 0.4459 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4857 0.0 0.0020 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.6293 0.0000 0.7845 0.0 0.0 0.0 0.0
1.7812 0.2 80 1.8452 0.1090 0.1569 0.6450 nan 0.7383 0.8884 0.0 0.0005 0.0001 nan 0.0 0.0 0.0 0.8010 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8358 0.0 0.0008 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9661 0.0067 0.7820 0.0 0.0 0.0 0.0 nan 0.3851 0.6991 0.0 0.0005 0.0001 nan 0.0 0.0 0.0 0.5586 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4803 0.0 0.0008 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6058 0.0067 0.7522 0.0 0.0 0.0 0.0
1.9004 0.25 100 1.6849 0.1120 0.1600 0.6526 nan 0.7163 0.9044 0.0 0.0257 0.0001 nan 0.0 0.0 0.0 0.8225 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8449 0.0 0.0010 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9620 0.0294 0.8139 0.0 0.0 0.0 0.0 nan 0.3964 0.6985 0.0 0.0257 0.0001 nan 0.0 0.0 0.0 0.5494 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4895 0.0 0.0010 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6192 0.0292 0.7757 0.0 0.0 0.0 0.0
1.6287 0.3 120 1.6376 0.1174 0.1684 0.6591 nan 0.7113 0.9101 0.0 0.0529 0.0002 nan 0.0 0.0 0.0 0.9426 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.7552 0.0 0.0012 0.0 0.0 nan 0.0 0.0002 0.0 0.0 0.9463 0.2590 0.8098 0.0 0.0 0.0 0.0 nan 0.3969 0.6959 0.0 0.0527 0.0002 nan 0.0 0.0 0.0 0.4075 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5041 0.0 0.0012 0.0 0.0 nan 0.0 0.0002 0.0 0.0 0.6711 0.2464 0.7814 0.0 0.0 0.0 0.0
1.624 0.35 140 1.5312 0.1173 0.1652 0.6629 nan 0.7561 0.9049 0.0 0.0484 0.0004 nan 0.0 0.0 0.0 0.8051 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8787 0.0 0.0003 0.0 0.0 nan 0.0 0.0002 0.0 0.0 0.9487 0.0819 0.8608 0.0 0.0 0.0 0.0 nan 0.4224 0.7010 0.0 0.0482 0.0004 nan 0.0 0.0 0.0 0.5536 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4958 0.0 0.0003 0.0 0.0 nan 0.0 0.0002 0.0 0.0 0.6442 0.0799 0.8072 0.0 0.0 0.0 0.0
1.4764 0.4 160 1.5197 0.1251 0.1754 0.6818 nan 0.7557 0.9231 0.0 0.2734 0.0010 nan 0.0 0.0 0.0 0.9198 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8331 0.0 0.0001 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.9396 0.1118 0.8534 0.0 0.0 0.0 0.0 nan 0.4637 0.7207 0.0 0.2624 0.0010 nan 0.0 0.0 0.0 0.4747 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5139 0.0 0.0001 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.6528 0.1079 0.8056 0.0 0.0 0.0 0.0
1.8363 0.45 180 1.4539 0.1238 0.1687 0.6751 nan 0.6197 0.9574 0.0 0.0978 0.0019 nan 0.0 0.0 0.0 0.8247 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8816 0.0 0.0005 0.0 0.0 nan 0.0 0.0001 0.0 0.0 0.9511 0.1872 0.8765 0.0 0.0 0.0 0.0 nan 0.4542 0.6816 0.0 0.0952 0.0019 nan 0.0 0.0 0.0 0.5643 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5131 0.0 0.0005 0.0 0.0 nan 0.0 0.0001 0.0 0.0 0.6549 0.1782 0.8178 0.0 0.0 0.0 0.0
1.4421 0.5 200 1.4241 0.1305 0.1784 0.6878 nan 0.7783 0.9214 0.0 0.1456 0.0002 nan 0.0 0.0 0.0 0.8439 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8784 0.0 0.0004 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9452 0.3053 0.8909 0.0 0.0 0.0 0.0 nan 0.4476 0.7247 0.0 0.1441 0.0002 nan 0.0 0.0 0.0 0.5630 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5109 0.0 0.0004 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6834 0.2905 0.8127 0.0 0.0 0.0 0.0
1.6741 0.55 220 1.3899 0.1406 0.1883 0.7029 nan 0.7793 0.9285 0.0 0.1706 0.0007 nan 0.0 0.0 0.0 0.8693 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8566 0.0 0.0005 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9534 0.5741 0.8910 0.0 0.0 0.0 0.0 nan 0.4558 0.7302 0.0 0.1687 0.0007 nan 0.0 0.0 0.0 0.5638 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5328 0.0 0.0005 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7112 0.5174 0.8188 0.0 0.0 0.0 0.0
1.2694 0.6 240 1.3387 0.1398 0.1881 0.7026 nan 0.7975 0.9237 0.0 0.1981 0.0015 nan 0.0 0.0 0.0 0.8648 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8666 0.0 0.0000 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.9454 0.5060 0.9148 0.0 0.0 0.0 0.0 nan 0.4599 0.7374 0.0 0.1953 0.0015 nan 0.0 0.0 0.0 0.5696 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5194 0.0 0.0000 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.7101 0.4619 0.8187 0.0 0.0 0.0 0.0
1.1338 0.65 260 1.3549 0.1450 0.1945 0.7059 nan 0.8217 0.9051 0.0 0.2198 0.0013 nan 0.0 0.0 0.0 0.8762 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8620 0.0 0.0001 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9305 0.7001 0.9073 0.0 0.0 0.0 0.0 nan 0.4430 0.7379 0.0 0.2152 0.0013 nan 0.0 0.0 0.0 0.5540 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5244 0.0 0.0001 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7440 0.5836 0.8355 0.0 0.0 0.0 0.0
1.299 0.7 280 1.3301 0.1468 0.1945 0.7151 nan 0.7655 0.9451 0.0 0.2522 0.0041 nan 0.0 0.0 0.0 0.8668 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8451 0.0 0.0004 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9439 0.7032 0.8986 0.0 0.0 0.0 0.0 nan 0.4941 0.7318 0.0 0.2427 0.0041 nan 0.0 0.0 0.0 0.5595 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5348 0.0 0.0004 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7259 0.5777 0.8278 0.0 0.0 0.0 0.0
1.4226 0.75 300 1.2990 0.1481 0.1959 0.7166 nan 0.7748 0.9338 0.0 0.3201 0.0020 nan 0.0 0.0 0.0 0.8662 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8670 0.0 0.0002 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9459 0.6570 0.9029 0.0 0.0 0.0 0.0 nan 0.4872 0.7399 0.0 0.3048 0.0020 nan 0.0 0.0 0.0 0.5583 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5267 0.0 0.0002 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7299 0.5648 0.8261 0.0 0.0 0.0 0.0
1.308 0.8 320 1.2874 0.1486 0.1980 0.7147 nan 0.8059 0.9152 0.0 0.3267 0.0028 nan 0.0 0.0 0.0 0.8786 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8693 0.0 0.0001 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9331 0.6937 0.9091 0.0 0.0 0.0 0.0 nan 0.4654 0.7461 0.0 0.3124 0.0028 nan 0.0 0.0 0.0 0.5471 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5229 0.0 0.0001 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7431 0.5876 0.8269 0.0 0.0 0.0 0.0
1.1045 0.85 340 1.2836 0.1510 0.1990 0.7184 nan 0.8022 0.9221 0.0 0.3350 0.0044 nan 0.0 0.0 0.0 0.8719 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8905 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9259 0.7122 0.9027 0.0 0.0 0.0 0.0 nan 0.4729 0.7460 0.0 0.3199 0.0044 nan 0.0 0.0 0.0 0.5769 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5252 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7464 0.5976 0.8413 0.0 0.0 0.0 0.0
1.6215 0.9 360 1.2790 0.1503 0.1992 0.7153 nan 0.8199 0.9010 0.0 0.3979 0.0064 nan 0.0 0.0 0.0 0.8586 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8304 0.0 0.0 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.9614 0.6903 0.9089 0.0 0.0 0.0 0.0 nan 0.4601 0.7518 0.0 0.3725 0.0064 nan 0.0 0.0 0.0 0.5798 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5358 0.0 0.0 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.7033 0.5644 0.8348 0.0 0.0 0.0 0.0
1.4805 0.95 380 1.2778 0.1514 0.2003 0.7215 nan 0.7928 0.9270 0.0 0.3578 0.0082 nan 0.0 0.0 0.0 0.8778 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8632 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9425 0.7324 0.9068 0.0 0.0 0.0 0.0 nan 0.4862 0.7480 0.0 0.3398 0.0082 nan 0.0 0.0 0.0 0.5700 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5359 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7341 0.5834 0.8403 0.0 0.0 0.0 0.0
1.1616 1.0 400 1.2519 0.1522 0.2003 0.7240 nan 0.7728 0.9359 0.0 0.3852 0.0097 nan 0.0 0.0 0.0 0.8668 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8650 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9477 0.7234 0.9033 0.0 0.0 0.0 0.0 nan 0.5016 0.7469 0.0 0.3601 0.0096 nan 0.0 0.0 0.0 0.5774 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5352 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7277 0.5775 0.8350 0.0 0.0 0.0 0.0

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1