Hugging Face's logo

piecurus
/
segformer-finetuned-segments-opit

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

segformer-finetuned-segments-opit

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: 1.3483
  • Mean Iou: 0.1474
  • Mean Accuracy: 0.1958
  • Overall Accuracy: 0.7227
  • Accuracy Unlabeled: nan
  • Accuracy Flat-road: 0.7892
  • Accuracy Flat-sidewalk: 0.9075
  • Accuracy Flat-crosswalk: 0.0
  • Accuracy Flat-cyclinglane: 0.1029
  • Accuracy Flat-parkingdriveway: 0.0001
  • Accuracy Flat-railtrack: nan
  • Accuracy Flat-curb: 0.0
  • Accuracy Human-person: 0.0
  • Accuracy Human-rider: 0.0
  • Accuracy Vehicle-car: 0.8749
  • 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: 0.8943
  • Accuracy Construction-door: 0.0
  • Accuracy Construction-wall: 0.0
  • 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: 0.9118
  • Accuracy Nature-terrain: 0.6546
  • Accuracy Sky: 0.9352
  • 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: 0.4282
  • Iou Flat-sidewalk: 0.7768
  • Iou Flat-crosswalk: 0.0
  • Iou Flat-cyclinglane: 0.1021
  • Iou Flat-parkingdriveway: 0.0001
  • Iou Flat-railtrack: nan
  • Iou Flat-curb: 0.0
  • Iou Human-person: 0.0
  • Iou Human-rider: 0.0
  • Iou Vehicle-car: 0.6372
  • 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: 0.5530
  • Iou Construction-door: 0.0
  • Iou Construction-wall: 0.0
  • 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: 0.7392
  • Iou Nature-terrain: 0.5009
  • Iou Sky: 0.8328
  • 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
2.8103 0.06 25 3.0462 0.0835 0.1351 0.5790 nan 0.1892 0.9330 0.0 0.0048 0.0006 nan 0.0005 0.0002 0.0 0.5793 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8849 0.0 0.0000 0.0002 0.0 nan 0.0003 0.0009 0.0 0.0 0.6599 0.4398 0.4779 0.0004 0.0 0.0151 0.0 0.0 0.1368 0.6091 0.0 0.0046 0.0006 0.0 0.0005 0.0002 0.0 0.4916 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.3537 0.0 0.0000 0.0002 0.0 0.0 0.0003 0.0008 0.0 0.0 0.5851 0.2698 0.4572 0.0004 0.0 0.0123 0.0
2.3833 0.12 50 2.3708 0.1025 0.1539 0.6295 nan 0.6185 0.8261 0.0 0.0007 0.0003 nan 0.0000 0.0 0.0 0.7749 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9283 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8688 0.0568 0.6944 0.0 0.0 0.0016 0.0 nan 0.3347 0.6672 0.0 0.0007 0.0003 nan 0.0000 0.0 0.0 0.5428 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4369 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6274 0.0451 0.6247 0.0 0.0 0.0015 0.0
2.1946 0.19 75 1.9680 0.1145 0.1612 0.6615 nan 0.6725 0.8726 0.0 0.0011 0.0000 nan 0.0 0.0 0.0 0.7496 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9138 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9185 0.0333 0.8355 0.0 0.0 0.0000 0.0 nan 0.3738 0.7037 0.0 0.0011 0.0000 nan 0.0 0.0 0.0 0.5385 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.4836 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6493 0.0311 0.7684 0.0 0.0 0.0000 0.0
1.959 0.25 100 1.8828 0.1179 0.1636 0.6727 nan 0.6801 0.8928 0.0 0.0006 0.0001 nan 0.0 0.0 0.0 0.7736 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8784 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9482 0.0389 0.8584 0.0 0.0 0.0000 0.0 nan 0.3884 0.7151 0.0 0.0006 0.0001 nan 0.0 0.0 0.0 0.5705 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5160 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6418 0.0360 0.7878 0.0 0.0 0.0000 0.0
1.8759 0.31 125 1.7092 0.1260 0.1758 0.6862 nan 0.7247 0.8976 0.0 0.0000 0.0000 nan 0.0 0.0 0.0 0.9094 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8479 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9024 0.2625 0.9054 0.0 0.0 0.0 0.0 nan 0.3977 0.7307 0.0 0.0000 0.0000 nan 0.0 0.0 0.0 0.5237 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5329 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6911 0.2245 0.8065 0.0 0.0 0.0 0.0
2.0333 0.38 150 1.5558 0.1267 0.1751 0.6898 nan 0.7565 0.8952 0.0 0.0007 0.0000 nan 0.0 0.0 0.0 0.8792 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8874 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9104 0.1928 0.9055 0.0 0.0 0.0 0.0 nan 0.4083 0.7455 0.0 0.0007 0.0000 nan 0.0 0.0 0.0 0.5928 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5267 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6820 0.1637 0.8069 0.0 0.0 0.0 0.0
1.8985 0.44 175 1.5370 0.1277 0.1752 0.6939 nan 0.7438 0.9025 0.0 0.0068 0.0000 nan 0.0 0.0 0.0 0.8237 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8984 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9307 0.1976 0.9266 0.0 0.0 0.0 0.0 nan 0.4223 0.7553 0.0 0.0068 0.0000 nan 0.0 0.0 0.0 0.6077 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5131 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6724 0.1691 0.8133 0.0 0.0 0.0 0.0
1.7908 0.5 200 1.4854 0.1339 0.1843 0.7020 nan 0.7612 0.9068 0.0 0.0012 0.0 nan 0.0 0.0 0.0 0.9215 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8381 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9078 0.4480 0.9274 0.0 0.0 0.0 0.0 nan 0.4095 0.7591 0.0 0.0012 0.0 nan 0.0 0.0 0.0 0.5471 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5386 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7168 0.3673 0.8119 0.0 0.0 0.0 0.0
1.4371 0.56 225 1.4176 0.1367 0.1830 0.7079 nan 0.7035 0.9303 0.0 0.0255 0.0001 nan 0.0 0.0 0.0 0.8694 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8848 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9287 0.4230 0.9065 0.0 0.0 0.0 0.0 nan 0.4233 0.7534 0.0 0.0255 0.0001 nan 0.0 0.0 0.0 0.6246 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5331 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7049 0.3427 0.8312 0.0 0.0 0.0 0.0
1.4506 0.62 250 1.4011 0.1350 0.1827 0.7079 nan 0.6936 0.9362 0.0 0.0364 0.0000 nan 0.0 0.0 0.0 0.8955 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8612 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9299 0.3720 0.9394 0.0 0.0 0.0 0.0 nan 0.4251 0.7533 0.0 0.0363 0.0000 nan 0.0 0.0 0.0 0.5961 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5472 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6990 0.3026 0.8250 0.0 0.0 0.0 0.0
1.3095 0.69 275 1.4039 0.1398 0.1861 0.7134 nan 0.6873 0.9430 0.0 0.0260 0.0000 nan 0.0 0.0 0.0 0.8807 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8960 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9156 0.5055 0.9137 0.0 0.0 0.0 0.0 nan 0.4187 0.7531 0.0 0.0260 0.0000 nan 0.0 0.0 0.0 0.6172 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5457 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7261 0.4143 0.8343 0.0 0.0 0.0 0.0
1.4218 0.75 300 1.3735 0.1370 0.1856 0.7082 nan 0.7701 0.8980 0.0 0.0524 0.0003 nan 0.0 0.0 0.0 0.8776 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8762 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9444 0.4052 0.9279 0.0 0.0 0.0 0.0 nan 0.4267 0.7668 0.0 0.0522 0.0003 nan 0.0 0.0 0.0 0.6148 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5481 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6931 0.3263 0.8172 0.0 0.0 0.0 0.0
1.3986 0.81 325 1.3224 0.1451 0.1917 0.7223 nan 0.7354 0.9296 0.0 0.1261 0.0002 nan 0.0 0.0 0.0 0.8747 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8946 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9269 0.5292 0.9261 0.0 0.0 0.0 0.0 nan 0.4389 0.7700 0.0 0.1253 0.0002 nan 0.0 0.0 0.0 0.6395 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5541 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7200 0.4083 0.8409 0.0 0.0 0.0 0.0
1.3335 0.88 350 1.2909 0.1454 0.1921 0.7230 nan 0.7157 0.9388 0.0 0.1024 0.0003 nan 0.0 0.0 0.0 0.8896 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8932 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9207 0.5667 0.9276 0.0 0.0 0.0 0.0 nan 0.4347 0.7657 0.0 0.1020 0.0003 nan 0.0 0.0 0.0 0.6232 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5533 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7300 0.4607 0.8376 0.0 0.0 0.0 0.0
1.6376 0.94 375 1.3109 0.1476 0.1964 0.7253 nan 0.7617 0.9215 0.0 0.1225 0.0002 nan 0.0 0.0 0.0 0.9008 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8842 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9118 0.6529 0.9335 0.0 0.0 0.0 0.0 nan 0.4357 0.7750 0.0 0.1216 0.0002 nan 0.0 0.0 0.0 0.6139 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5572 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7387 0.5011 0.8333 0.0 0.0 0.0 0.0
1.4354 1.0 400 1.3483 0.1474 0.1958 0.7227 nan 0.7892 0.9075 0.0 0.1029 0.0001 nan 0.0 0.0 0.0 0.8749 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8943 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9118 0.6546 0.9352 0.0 0.0 0.0 0.0 nan 0.4282 0.7768 0.0 0.1021 0.0001 nan 0.0 0.0 0.0 0.6372 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5530 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7392 0.5009 0.8328 0.0 0.0 0.0 0.0

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
14
Safetensors
Model size
3.72M params
Tensor type
F32
·
Inference Examples
Image Segmentation
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for piecurus/segformer-finetuned-segments-opit

Base model

nvidia/mit-b0
Finetuned
(335)
this model

Evaluation results

Metadata error: specify a dataset to view leaderboard