Hugging Face's logo

ArturR01
/
segformer-b0-example-pytorch-blog

Image Segmentation
Transformers
PyTorch
TensorBoard
segformer
vision
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
2
Edit model card

segformer-b0-example-pytorch-blog

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: 1.2757
  • Mean Iou: 0.1462
  • Mean Accuracy: 0.2006
  • Overall Accuracy: 0.7257
  • Accuracy Unlabeled: nan
  • Accuracy Flat-road: 0.8968
  • Accuracy Flat-sidewalk: 0.9232
  • Accuracy Flat-crosswalk: 0.0
  • Accuracy Flat-cyclinglane: 0.0013
  • Accuracy Flat-parkingdriveway: 0.0024
  • Accuracy Flat-railtrack: nan
  • Accuracy Flat-curb: 0.0
  • Accuracy Human-person: 0.0
  • Accuracy Human-rider: 0.0
  • Accuracy Vehicle-car: 0.8803
  • 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: 0.8822
  • 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: 0.8802
  • Accuracy Nature-terrain: 0.8441
  • Accuracy Sky: 0.9068
  • 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: 0.5131
  • Iou Flat-sidewalk: 0.7717
  • Iou Flat-crosswalk: 0.0
  • Iou Flat-cyclinglane: 0.0013
  • Iou Flat-parkingdriveway: 0.0024
  • Iou Flat-railtrack: nan
  • Iou Flat-curb: 0.0
  • Iou Human-person: 0.0
  • Iou Human-rider: 0.0
  • Iou Vehicle-car: 0.5983
  • 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: 0.5449
  • 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: 0.7519
  • Iou Nature-terrain: 0.5340
  • Iou Sky: 0.8151
  • 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
3.0226 0.05 20 3.2451 0.0770 0.1291 0.5814 nan 0.3392 0.9150 0.0007 0.0167 0.0052 nan 0.0281 0.0013 0.0 0.6316 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8880 0.0 0.0100 0.0 0.0 nan 0.0 0.0212 0.0 0.0 0.7776 0.2569 0.1047 0.0036 0.0021 0.0002 0.0 0.0 0.2887 0.6060 0.0006 0.0156 0.0051 0.0 0.0209 0.0011 0.0 0.4177 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.3513 0.0 0.0087 0.0 0.0 0.0 0.0 0.0109 0.0 0.0 0.6347 0.2251 0.1037 0.0027 0.0019 0.0002 0.0
2.4643 0.1 40 2.4748 0.0979 0.1462 0.6444 nan 0.6454 0.9084 0.0012 0.0002 0.0006 nan 0.0124 0.0000 0.0 0.6787 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8760 0.0 0.0119 0.0 0.0 nan 0.0 0.0038 0.0 0.0 0.9282 0.0365 0.4258 0.0016 0.0 0.0 0.0 nan 0.4331 0.6624 0.0012 0.0002 0.0006 nan 0.0114 0.0000 0.0 0.4718 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4327 0.0 0.0115 0.0 0.0 nan 0.0 0.0036 0.0 0.0 0.6481 0.0359 0.4181 0.0015 0.0 0.0 0.0
2.3866 0.15 60 2.0828 0.1129 0.1636 0.6679 nan 0.7570 0.8891 0.0000 0.0000 0.0002 nan 0.0010 0.0001 0.0 0.7980 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8425 0.0 0.0088 0.0 0.0 nan 0.0 0.0006 0.0 0.0 0.9416 0.3129 0.5187 0.0000 0.0 0.0 0.0 nan 0.4431 0.6874 0.0000 0.0000 0.0002 nan 0.0010 0.0001 0.0 0.5410 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4735 0.0 0.0087 0.0 0.0 nan 0.0 0.0006 0.0 0.0 0.6784 0.2726 0.5071 0.0000 0.0 0.0 0.0
2.4998 0.2 80 1.9122 0.1276 0.1772 0.6866 nan 0.8098 0.8856 0.0 0.0001 0.0 nan 0.0004 0.0 0.0 0.8752 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8497 0.0 0.0073 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9361 0.4185 0.7115 0.0000 0.0 0.0 0.0 nan 0.4611 0.7099 0.0 0.0001 0.0 nan 0.0004 0.0 0.0 0.5317 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5068 0.0 0.0072 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7000 0.3600 0.6771 0.0000 0.0 0.0 0.0
1.9775 0.25 100 1.7125 0.1344 0.1848 0.6979 nan 0.7868 0.9065 0.0 0.0002 0.0000 nan 0.0007 0.0 0.0 0.8211 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8331 0.0 0.0015 0.0 0.0 nan 0.0 0.0010 0.0 0.0 0.9286 0.6121 0.8377 0.0 0.0 0.0 0.0 nan 0.4865 0.7134 0.0 0.0002 0.0000 nan 0.0007 0.0 0.0 0.5603 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5044 0.0 0.0015 0.0 0.0 nan 0.0 0.0010 0.0 0.0 0.7089 0.4386 0.7511 0.0 0.0 0.0 0.0
1.6408 0.3 120 1.6293 0.1379 0.1888 0.7033 nan 0.7671 0.9293 0.0 0.0020 0.0000 nan 0.0002 0.0 0.0 0.8367 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8499 0.0 0.0005 0.0 0.0 nan 0.0 0.0001 0.0 0.0 0.8888 0.6973 0.8808 0.0 0.0 0.0 0.0 nan 0.4924 0.7106 0.0 0.0020 0.0000 nan 0.0002 0.0 0.0 0.5812 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5056 0.0 0.0005 0.0 0.0 nan 0.0 0.0001 0.0 0.0 0.7306 0.4774 0.7751 0.0 0.0 0.0 0.0
2.0971 0.35 140 1.5878 0.1392 0.1931 0.7067 nan 0.8429 0.9084 0.0 0.0003 0.0000 nan 0.0000 0.0 0.0 0.8886 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8458 0.0 0.0061 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8806 0.7458 0.8668 0.0 0.0 0.0 0.0 nan 0.4799 0.7350 0.0 0.0003 0.0000 nan 0.0000 0.0 0.0 0.5623 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5298 0.0 0.0061 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7340 0.4897 0.7783 0.0 0.0 0.0 0.0
1.5524 0.4 160 1.5210 0.1416 0.1935 0.7104 nan 0.8431 0.9047 0.0 0.0054 0.0004 nan 0.0001 0.0 0.0 0.8147 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8864 0.0 0.0011 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8979 0.7542 0.8898 0.0 0.0 0.0 0.0 nan 0.4947 0.7378 0.0 0.0054 0.0004 nan 0.0001 0.0 0.0 0.6030 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5067 0.0 0.0011 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7376 0.5122 0.7895 0.0 0.0 0.0 0.0
2.1125 0.45 180 1.4662 0.1381 0.1967 0.7038 nan 0.8346 0.9129 0.0 0.0013 0.0012 nan 0.0 0.0 0.0 0.8720 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8763 0.0 0.0004 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8097 0.8918 0.8970 0.0 0.0 0.0 0.0 nan 0.5026 0.7394 0.0 0.0013 0.0012 nan 0.0 0.0 0.0 0.5807 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5253 0.0 0.0004 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6976 0.4392 0.7937 0.0 0.0 0.0 0.0
1.7884 0.5 200 1.3982 0.1411 0.1928 0.7139 nan 0.8103 0.9245 0.0 0.0012 0.0007 nan 0.0 0.0 0.0 0.8626 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8615 0.0 0.0001 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9163 0.6946 0.9044 0.0 0.0 0.0 0.0 nan 0.5111 0.7331 0.0 0.0012 0.0007 nan 0.0 0.0 0.0 0.5772 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5245 0.0 0.0001 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7332 0.5028 0.7899 0.0 0.0 0.0 0.0
1.7399 0.55 220 1.4060 0.1429 0.1965 0.7154 nan 0.8177 0.9351 0.0 0.0000 0.0004 nan 0.0 0.0 0.0 0.8868 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8743 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8626 0.8036 0.9097 0.0 0.0 0.0 0.0 nan 0.5061 0.7372 0.0 0.0000 0.0004 nan 0.0 0.0 0.0 0.5900 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5170 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7513 0.5264 0.8019 0.0 0.0 0.0 0.0
1.6151 0.6 240 1.3772 0.1407 0.1920 0.7140 nan 0.8674 0.9061 0.0 0.0000 0.0018 nan 0.0 0.0 0.0 0.8325 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8259 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9415 0.6687 0.9074 0.0 0.0 0.0 0.0 nan 0.5026 0.7512 0.0 0.0000 0.0018 nan 0.0 0.0 0.0 0.5943 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5339 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7135 0.4782 0.7870 0.0 0.0 0.0 0.0
1.8311 0.65 260 1.3217 0.1418 0.1945 0.7189 nan 0.8499 0.9251 0.0 0.0002 0.0028 nan 0.0 0.0 0.0 0.8839 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8598 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9138 0.7105 0.8851 0.0 0.0 0.0 0.0 nan 0.5198 0.7509 0.0 0.0002 0.0028 nan 0.0 0.0 0.0 0.5533 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5311 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7431 0.4986 0.7975 0.0 0.0 0.0 0.0
1.215 0.7 280 1.3329 0.1434 0.1977 0.7195 nan 0.8756 0.9182 0.0 0.0003 0.0023 nan 0.0 0.0 0.0 0.8858 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9029 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8752 0.7868 0.8822 0.0 0.0 0.0 0.0 nan 0.5146 0.7624 0.0 0.0003 0.0023 nan 0.0 0.0 0.0 0.5919 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5143 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7533 0.5041 0.8033 0.0 0.0 0.0 0.0
1.5656 0.75 300 1.2993 0.1433 0.1973 0.7170 nan 0.8972 0.9030 0.0 0.0002 0.0016 nan 0.0 0.0 0.0 0.8611 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8344 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9037 0.8070 0.9082 0.0 0.0 0.0 0.0 nan 0.4916 0.7608 0.0 0.0002 0.0015 nan 0.0 0.0 0.0 0.5982 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5474 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7300 0.5160 0.7977 0.0 0.0 0.0 0.0
1.3712 0.8 320 1.2934 0.1445 0.1984 0.7203 nan 0.9047 0.9056 0.0 0.0004 0.0006 nan 0.0 0.0 0.0 0.8724 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8694 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8976 0.7999 0.8984 0.0 0.0 0.0 0.0 nan 0.4941 0.7696 0.0 0.0004 0.0006 nan 0.0 0.0 0.0 0.5955 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5460 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7442 0.5189 0.8093 0.0 0.0 0.0 0.0
1.1831 0.85 340 1.2771 0.1453 0.1996 0.7217 nan 0.9035 0.9105 0.0 0.0010 0.0012 nan 0.0 0.0 0.0 0.8679 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8874 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8812 0.8507 0.8838 0.0 0.0 0.0 0.0 nan 0.4996 0.7710 0.0 0.0010 0.0012 nan 0.0 0.0 0.0 0.6037 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5458 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7443 0.5249 0.8129 0.0 0.0 0.0 0.0
1.343 0.9 360 1.2465 0.1449 0.1989 0.7212 nan 0.9086 0.9032 0.0 0.0007 0.0022 nan 0.0 0.0 0.0 0.8650 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8673 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9040 0.8253 0.8911 0.0 0.0 0.0 0.0 nan 0.4947 0.7732 0.0 0.0007 0.0022 nan 0.0 0.0 0.0 0.5988 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5508 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7403 0.5220 0.8099 0.0 0.0 0.0 0.0
1.4857 0.95 380 1.2733 0.1453 0.2008 0.7241 nan 0.8789 0.9317 0.0 0.0019 0.0035 nan 0.0 0.0 0.0 0.8861 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9032 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8505 0.8620 0.9060 0.0 0.0 0.0 0.0 nan 0.5280 0.7656 0.0 0.0019 0.0035 nan 0.0 0.0 0.0 0.5952 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5299 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7500 0.5148 0.8150 0.0 0.0 0.0 0.0
1.1595 1.0 400 1.2757 0.1462 0.2006 0.7257 nan 0.8968 0.9232 0.0 0.0013 0.0024 nan 0.0 0.0 0.0 0.8803 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8822 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8802 0.8441 0.9068 0.0 0.0 0.0 0.0 nan 0.5131 0.7717 0.0 0.0013 0.0024 nan 0.0 0.0 0.0 0.5983 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5449 0.0 0.0000 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7519 0.5340 0.8151 0.0 0.0 0.0 0.0

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
3

Evaluation results

Metadata error: specify a dataset to view leaderboard