Hugging Face's logo

Akiteru
/
my-fine-tuned-model

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community

my-fine-tuned-model

This model is a fine-tuned version of nvidia/segformer-b1-finetuned-ade-512-512 on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1999
  • Mean Iou: 0.1706
  • Mean Accuracy: 0.2116
  • Overall Accuracy: 0.7740
  • Accuracy Unlabeled: nan
  • Accuracy Flat-road: 0.8915
  • Accuracy Flat-sidewalk: 0.9438
  • Accuracy Flat-crosswalk: 0.0
  • Accuracy Flat-cyclinglane: 0.5087
  • Accuracy Flat-parkingdriveway: 0.0048
  • Accuracy Flat-railtrack: nan
  • Accuracy Flat-curb: 0.0
  • Accuracy Human-person: 0.0
  • Accuracy Human-rider: 0.0
  • Accuracy Vehicle-car: 0.8715
  • 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: 0.9030
  • Accuracy Construction-door: 0.0
  • Accuracy Construction-wall: 0.0009
  • 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: 0.9444
  • Accuracy Nature-terrain: 0.7861
  • Accuracy Sky: 0.9161
  • 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: 0.5823
  • Iou Flat-sidewalk: 0.8174
  • Iou Flat-crosswalk: 0.0
  • Iou Flat-cyclinglane: 0.4884
  • Iou Flat-parkingdriveway: 0.0048
  • Iou Flat-railtrack: nan
  • Iou Flat-curb: 0.0
  • Iou Human-person: 0.0
  • Iou Human-rider: 0.0
  • Iou Vehicle-car: 0.6619
  • 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: 0.5862
  • Iou Construction-door: 0.0
  • Iou Construction-wall: 0.0009
  • 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: 0.7592
  • Iou Nature-terrain: 0.7159
  • Iou Sky: 0.8430
  • 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: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 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-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
3.0054 0.1 20 2.8502 0.0610 0.1050 0.5551 nan 0.5630 0.9504 0.0190 0.0010 0.0022 nan 0.0020 0.0004 0.1899 0.0446 0.0 0.0 0.0 0.0 0.0014 0.0 0.0 0.1945 0.0765 0.0374 0.0101 0.0 nan 0.0174 0.0025 0.0 0.0 0.9743 0.0000 0.2628 0.0 0.0081 0.0011 0.0 0.0 0.3847 0.7107 0.0132 0.0007 0.0022 0.0 0.0015 0.0004 0.0425 0.0434 0.0 0.0 0.0 0.0 0.0014 0.0 0.0 0.1626 0.0084 0.0214 0.0082 0.0 0.0 0.0130 0.0021 0.0 0.0 0.4534 0.0000 0.2590 0.0 0.0056 0.0010 0.0
2.9407 0.2 40 2.3892 0.0977 0.1428 0.6529 nan 0.7944 0.9095 0.0015 0.0004 0.0015 nan 0.0000 0.0 0.0029 0.4578 0.0 0.0 0.0 0.0 0.0004 0.0 0.0 0.6666 0.0 0.0090 0.0 0.0 nan 0.0 0.0003 0.0 0.0 0.9809 0.0001 0.7443 0.0 0.0002 0.0008 0.0 0.0 0.4524 0.7526 0.0013 0.0003 0.0015 0.0 0.0000 0.0 0.0029 0.4135 0.0 0.0 0.0 0.0 0.0004 0.0 0.0 0.4316 0.0 0.0085 0.0 0.0 nan 0.0 0.0003 0.0 0.0 0.5305 0.0001 0.7265 0.0 0.0002 0.0008 0.0
2.548 0.3 60 2.1416 0.1163 0.1564 0.6823 nan 0.7335 0.9336 0.0004 0.0009 0.0021 nan 0.0 0.0 0.0 0.6875 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8169 0.0 0.0109 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9771 0.0554 0.7873 0.0 0.0 0.0002 0.0 nan 0.4575 0.7461 0.0004 0.0009 0.0021 nan 0.0 0.0 0.0 0.5870 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5082 0.0 0.0108 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5896 0.0550 0.7637 0.0 0.0 0.0002 0.0
2.0998 0.4 80 1.9659 0.1286 0.1704 0.7058 nan 0.7787 0.9334 0.0000 0.0001 0.0012 nan 0.0 0.0 0.0 0.7274 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8594 0.0 0.0069 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9643 0.3080 0.8732 0.0 0.0 0.0000 0.0 nan 0.4742 0.7686 0.0000 0.0001 0.0012 nan 0.0 0.0 0.0 0.6040 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5211 0.0 0.0068 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6503 0.2984 0.7912 0.0 0.0 0.0000 0.0
1.9886 0.5 100 1.8620 0.1292 0.1707 0.7068 nan 0.8207 0.9258 0.0 0.0000 0.0002 nan 0.0 0.0 0.0 0.6582 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8540 0.0 0.0017 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9666 0.3605 0.8740 0.0 0.0 0.0000 0.0 nan 0.4776 0.7811 0.0 0.0000 0.0002 nan 0.0 0.0 0.0 0.5764 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5022 0.0 0.0017 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6580 0.3531 0.7829 0.0 0.0 0.0000 0.0
1.7382 0.6 120 1.7216 0.1316 0.1728 0.7127 nan 0.7315 0.9586 0.0 0.0034 0.0011 nan 0.0 0.0 0.0 0.7762 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8834 0.0 0.0023 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9507 0.3498 0.8714 0.0 0.0 0.0 0.0 nan 0.4817 0.7575 0.0 0.0034 0.0011 nan 0.0 0.0 0.0 0.6358 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5209 0.0 0.0023 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6836 0.3412 0.7841 0.0 0.0 0.0 0.0
1.796 0.7 140 1.6579 0.1395 0.1820 0.7278 nan 0.8098 0.9548 0.0 0.0015 0.0002 nan 0.0 0.0 0.0 0.8423 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8210 0.0 0.0019 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9476 0.5269 0.9178 0.0 0.0 0.0 0.0 nan 0.4949 0.7711 0.0 0.0015 0.0002 nan 0.0 0.0 0.0 0.6303 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5644 0.0 0.0019 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7109 0.5046 0.7848 0.0 0.0 0.0 0.0
1.7154 0.8 160 1.5859 0.1430 0.1852 0.7305 nan 0.8789 0.9173 0.0 0.0269 0.0000 nan 0.0 0.0 0.0 0.7923 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.9148 0.0 0.0003 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9430 0.5814 0.8701 0.0 0.0 0.0 0.0 nan 0.5088 0.7927 0.0 0.0269 0.0000 nan 0.0 0.0 0.0 0.6391 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5247 0.0 0.0003 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7262 0.5517 0.8041 0.0 0.0 0.0 0.0
1.7287 0.9 180 1.4827 0.1507 0.1914 0.7471 nan 0.8611 0.9539 0.0 0.0168 0.0013 nan 0.0 0.0 0.0 0.8329 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8750 0.0 0.0009 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9494 0.7283 0.9041 0.0 0.0 0.0 0.0 nan 0.5268 0.7957 0.0 0.0168 0.0013 nan 0.0 0.0 0.0 0.6465 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5805 0.0 0.0009 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7341 0.6741 0.8460 0.0 0.0 0.0 0.0
1.7761 1.0 200 1.4371 0.1462 0.1888 0.7395 nan 0.8871 0.9276 0.0 0.1441 0.0013 nan 0.0 0.0 0.0 0.8294 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8938 0.0 0.0001 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9572 0.4822 0.9179 0.0 0.0 0.0 0.0 nan 0.5213 0.8143 0.0 0.1435 0.0013 nan 0.0 0.0 0.0 0.6415 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5569 0.0 0.0001 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7003 0.4663 0.8340 0.0 0.0 0.0 0.0
1.3667 1.1 220 1.3822 0.1581 0.1972 0.7497 nan 0.7334 0.9680 0.0 0.3107 0.0039 nan 0.0 0.0 0.0 0.8475 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.9153 0.0 0.0003 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9467 0.6836 0.9024 0.0 0.0 0.0 0.0 nan 0.5388 0.7608 0.0 0.3052 0.0039 nan 0.0 0.0 0.0 0.6523 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5660 0.0 0.0003 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7450 0.6425 0.8458 0.0 0.0 0.0 0.0
1.4033 1.2 240 1.3556 0.1607 0.2017 0.7601 nan 0.8631 0.9523 0.0 0.2805 0.0028 nan 0.0 0.0 0.0 0.8582 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8912 0.0 0.0003 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9393 0.7424 0.9249 0.0 0.0 0.0 0.0 nan 0.5498 0.8023 0.0 0.2776 0.0028 nan 0.0 0.0 0.0 0.6621 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5761 0.0 0.0003 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7566 0.6899 0.8241 0.0 0.0 0.0 0.0
1.2975 1.3 260 1.2957 0.1662 0.2062 0.7674 nan 0.8769 0.9483 0.0 0.4108 0.0040 nan 0.0 0.0 0.0 0.8624 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8958 0.0 0.0017 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9524 0.7475 0.8975 0.0 0.0 0.0 0.0 nan 0.5783 0.8042 0.0 0.3990 0.0040 nan 0.0 0.0 0.0 0.6652 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5960 0.0 0.0017 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7384 0.6849 0.8452 0.0 0.0 0.0 0.0
1.113 1.4 280 1.2796 0.1656 0.2069 0.7657 nan 0.8637 0.9449 0.0 0.4093 0.0061 nan 0.0 0.0 0.0 0.8670 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.9138 0.0 0.0012 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9372 0.7764 0.9027 0.0 0.0 0.0 0.0 nan 0.5655 0.8067 0.0 0.3983 0.0061 nan 0.0 0.0 0.0 0.6548 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5752 0.0 0.0012 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7586 0.7044 0.8286 0.0 0.0 0.0 0.0
1.7147 1.5 300 1.2507 0.1668 0.2087 0.7667 nan 0.8655 0.9449 0.0 0.4471 0.0048 nan 0.0 0.0 0.0 0.8668 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8873 0.0 0.0014 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9354 0.8027 0.9226 0.0 0.0 0.0 0.0 nan 0.5655 0.8025 0.0 0.4325 0.0048 nan 0.0 0.0 0.0 0.6591 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5780 0.0 0.0014 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7601 0.7135 0.8216 0.0 0.0 0.0 0.0
1.1053 1.6 320 1.2350 0.1700 0.2099 0.7722 nan 0.8514 0.9543 0.0 0.5427 0.0056 nan 0.0 0.0 0.0 0.8614 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.9112 0.0 0.0009 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9497 0.7398 0.9009 0.0 0.0 0.0 0.0 nan 0.5979 0.8056 0.0 0.5147 0.0056 nan 0.0 0.0 0.0 0.6636 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5773 0.0 0.0009 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7483 0.6837 0.8413 0.0 0.0 0.0 0.0
1.3557 1.7 340 1.2256 0.1719 0.2120 0.7752 nan 0.8411 0.9606 0.0 0.5856 0.0061 nan 0.0 0.0 0.0 0.8698 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.9108 0.0 0.0005 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9414 0.7539 0.9156 0.0 0.0 0.0 0.0 nan 0.6089 0.8026 0.0 0.5413 0.0061 nan 0.0 0.0 0.0 0.6642 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5751 0.0 0.0005 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7607 0.6986 0.8415 0.0 0.0 0.0 0.0
1.3048 1.8 360 1.2099 0.1703 0.2117 0.7737 nan 0.8851 0.9445 0.0 0.5409 0.0070 nan 0.0 0.0 0.0 0.8833 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8912 0.0 0.0014 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9490 0.7532 0.9186 0.0 0.0 0.0 0.0 nan 0.5898 0.8161 0.0 0.5117 0.0070 nan 0.0 0.0 0.0 0.6544 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5863 0.0 0.0014 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7508 0.6953 0.8357 0.0 0.0 0.0 0.0
1.5497 1.9 380 1.2042 0.1706 0.2118 0.7739 nan 0.8855 0.9442 0.0 0.5205 0.0071 nan 0.0 0.0 0.0 0.8739 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8967 0.0 0.0012 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9486 0.7810 0.9176 0.0 0.0 0.0 0.0 nan 0.5865 0.8165 0.0 0.4976 0.0071 nan 0.0 0.0 0.0 0.6595 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5865 0.0 0.0012 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7524 0.7122 0.8413 0.0 0.0 0.0 0.0
1.3084 2.0 400 1.1999 0.1706 0.2116 0.7740 nan 0.8915 0.9438 0.0 0.5087 0.0048 nan 0.0 0.0 0.0 0.8715 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.9030 0.0 0.0009 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9444 0.7861 0.9161 0.0 0.0 0.0 0.0 nan 0.5823 0.8174 0.0 0.4884 0.0048 nan 0.0 0.0 0.0 0.6619 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5862 0.0 0.0009 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7592 0.7159 0.8430 0.0 0.0 0.0 0.0

Framework versions

  • Transformers 4.48.0
  • Pytorch 2.1.1+cu118
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
13
Safetensors
Model size
13.7M params
Tensor type
F32
·
Inference Providers NEW
Image Segmentation
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for Akiteru/my-fine-tuned-model

Base model

nvidia/segformer-b1-finetuned-ade-512-512
Finetuned
(26)
this model

Evaluation results

Metadata error: specify a dataset to view leaderboard