Hugging Face's logo

nguyenb2240
/
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
nguyenb2240's picture
nguyenb2240
End of training
2cd161b verified
preview code
|
raw
history blame contribute delete
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: 1.1574
  • Mean Iou: 0.1657
  • Mean Accuracy: 0.2143
  • Overall Accuracy: 0.7508
  • Accuracy Unlabeled: nan
  • Accuracy Flat-road: 0.8145
  • Accuracy Flat-sidewalk: 0.9504
  • Accuracy Flat-crosswalk: 0.0
  • Accuracy Flat-cyclinglane: 0.5828
  • Accuracy Flat-parkingdriveway: 0.0118
  • Accuracy Flat-railtrack: nan
  • Accuracy Flat-curb: 0.0001
  • Accuracy Human-person: 0.0
  • Accuracy Human-rider: 0.0
  • Accuracy Vehicle-car: 0.8895
  • 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: 0.8937
  • Accuracy Construction-door: 0.0
  • Accuracy Construction-wall: 0.0389
  • 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: 0.9244
  • Accuracy Nature-terrain: 0.8287
  • Accuracy Sky: 0.9224
  • 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: 0.5381
  • Iou Flat-sidewalk: 0.7939
  • Iou Flat-crosswalk: 0.0
  • Iou Flat-cyclinglane: 0.5124
  • Iou Flat-parkingdriveway: 0.0117
  • Iou Flat-railtrack: nan
  • Iou Flat-curb: 0.0001
  • Iou Human-person: 0.0
  • Iou Human-rider: 0.0
  • Iou Vehicle-car: 0.6117
  • 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: 0.5570
  • Iou Construction-door: 0.0
  • Iou Construction-wall: 0.0365
  • 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: 0.7504
  • Iou Nature-terrain: 0.6347
  • Iou Sky: 0.8566
  • 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: 10
  • eval_batch_size: 10
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

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
2.6835 0.25 20 2.9300 0.0679 0.1189 0.5663 nan 0.0864 0.9582 0.0005 0.0171 0.0000 nan 0.0049 0.0042 0.0 0.8284 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.7913 0.0 0.0535 0.0 0.0 nan 0.0029 0.0 0.0 0.0 0.9260 0.0016 0.1138 0.0168 0.0 0.0 0.0 0.0 0.0824 0.5815 0.0005 0.0168 0.0000 0.0 0.0045 0.0040 0.0 0.5349 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4154 0.0 0.0414 0.0 0.0 0.0 0.0006 0.0 0.0 0.0 0.5765 0.0016 0.1137 0.0025 0.0 0.0 0.0
2.3707 0.5 40 2.1968 0.0875 0.1387 0.6231 nan 0.5613 0.9361 0.0 0.0210 0.0003 nan 0.0019 0.0 0.0 0.7965 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8356 0.0 0.0281 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9513 0.0032 0.3006 0.0011 0.0 0.0 0.0 nan 0.3878 0.6646 0.0 0.0208 0.0003 0.0 0.0019 0.0 0.0 0.5587 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4439 0.0 0.0249 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5675 0.0032 0.3003 0.0009 0.0 0.0 0.0
2.0797 0.75 60 1.9742 0.1106 0.1579 0.6543 nan 0.7248 0.9240 0.0 0.0036 0.0008 nan 0.0000 0.0 0.0 0.8368 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8428 0.0 0.0254 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9498 0.0444 0.7003 0.0 0.0 0.0 0.0 nan 0.4154 0.7036 0.0 0.0036 0.0008 nan 0.0000 0.0 0.0 0.5498 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.4939 0.0 0.0240 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6151 0.0426 0.6908 0.0 0.0 0.0 0.0
1.9067 1.0 80 1.7288 0.1234 0.1699 0.6749 nan 0.7502 0.9269 0.0 0.0766 0.0014 nan 0.0000 0.0 0.0 0.8214 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8719 0.0 0.0111 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9451 0.2194 0.8139 0.0 0.0 0.0 0.0 nan 0.4498 0.7152 0.0 0.0761 0.0013 nan 0.0000 0.0 0.0 0.5696 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5007 0.0 0.0108 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6444 0.1954 0.7863 0.0 0.0 0.0 0.0
1.6673 1.25 100 1.6680 0.1258 0.1752 0.6789 nan 0.8230 0.9033 0.0 0.0493 0.0022 nan 0.0000 0.0 0.0 0.8676 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8389 0.0 0.0075 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9609 0.2915 0.8618 0.0 0.0 0.0 0.0 nan 0.4254 0.7481 0.0 0.0488 0.0022 nan 0.0000 0.0 0.0 0.5539 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5266 0.0 0.0074 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6400 0.2581 0.8161 0.0 0.0 0.0 0.0
1.7134 1.5 120 1.5470 0.1376 0.1870 0.6997 nan 0.7864 0.9287 0.0 0.1234 0.0027 nan 0.0000 0.0 0.0 0.8766 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8540 0.0 0.0060 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9433 0.5618 0.9008 0.0 0.0 0.0 0.0 nan 0.4735 0.7320 0.0 0.1216 0.0027 nan 0.0000 0.0 0.0 0.5599 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5319 0.0 0.0059 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6897 0.4601 0.8255 0.0 0.0 0.0 0.0
1.4384 1.75 140 1.4997 0.1458 0.1931 0.7143 nan 0.7973 0.9446 0.0 0.2050 0.0025 nan 0.0 0.0 0.0 0.8691 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8695 0.0 0.0025 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9304 0.6705 0.8889 0.0 0.0 0.0 0.0 nan 0.4842 0.7479 0.0 0.1960 0.0025 nan 0.0 0.0 0.0 0.5860 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5294 0.0 0.0025 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7244 0.5600 0.8314 0.0 0.0 0.0 0.0
1.4101 2.0 160 1.4325 0.1485 0.1990 0.7167 nan 0.8247 0.9212 0.0 0.2410 0.0032 nan 0.0 0.0 0.0 0.8787 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8896 0.0 0.0042 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9131 0.7902 0.9017 0.0 0.0 0.0 0.0 nan 0.4675 0.7648 0.0 0.2283 0.0032 nan 0.0 0.0 0.0 0.5777 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5259 0.0 0.0041 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7388 0.6051 0.8352 0.0 0.0 0.0 0.0
1.4613 2.25 180 1.3689 0.1522 0.2012 0.7248 nan 0.7783 0.9430 0.0 0.3362 0.0037 nan 0.0 0.0 0.0 0.8668 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8788 0.0 0.0033 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9201 0.7933 0.9142 0.0 0.0 0.0 0.0 nan 0.4951 0.7564 0.0 0.3089 0.0037 nan 0.0 0.0 0.0 0.5926 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5366 0.0 0.0033 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7330 0.6059 0.8348 0.0 0.0 0.0 0.0
1.1652 2.5 200 1.3458 0.1566 0.2036 0.7323 nan 0.7605 0.9551 0.0 0.4259 0.0038 nan 0.0 0.0 0.0 0.8580 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8902 0.0 0.0066 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9193 0.7943 0.9027 0.0 0.0 0.0 0.0 nan 0.5290 0.7548 0.0 0.3710 0.0038 nan 0.0 0.0 0.0 0.6064 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5270 0.0 0.0065 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7467 0.6256 0.8409 0.0 0.0 0.0 0.0
1.3201 2.75 220 1.2652 0.1572 0.2057 0.7353 nan 0.7825 0.9559 0.0 0.4231 0.0056 nan 0.0000 0.0 0.0 0.8904 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8834 0.0 0.0122 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9104 0.8184 0.9014 0.0 0.0 0.0 0.0 nan 0.5340 0.7600 0.0 0.3872 0.0056 nan 0.0000 0.0 0.0 0.5909 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5480 0.0 0.0120 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7383 0.6066 0.8463 0.0 0.0 0.0 0.0
1.2234 3.0 240 1.2746 0.1594 0.2088 0.7376 nan 0.8409 0.9292 0.0 0.4723 0.0054 nan 0.0 0.0 0.0 0.8857 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8767 0.0 0.0206 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9318 0.7948 0.9251 0.0 0.0 0.0 0.0 nan 0.4920 0.7916 0.0 0.4224 0.0053 nan 0.0 0.0 0.0 0.6083 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5504 0.0 0.0199 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7396 0.6269 0.8444 0.0 0.0 0.0 0.0
1.4557 3.25 260 1.2698 0.1584 0.2075 0.7313 nan 0.8659 0.9053 0.0 0.4557 0.0059 nan 0.0 0.0 0.0 0.8611 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8783 0.0 0.0141 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9394 0.7982 0.9172 0.0 0.0 0.0 0.0 nan 0.4660 0.7939 0.0 0.4017 0.0059 nan 0.0 0.0 0.0 0.6271 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5439 0.0 0.0137 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7346 0.6333 0.8478 0.0 0.0 0.0 0.0
1.2238 3.5 280 1.2213 0.1610 0.2090 0.7427 nan 0.8092 0.9490 0.0 0.4971 0.0087 nan 0.0 0.0 0.0 0.8902 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8860 0.0 0.0207 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9339 0.7840 0.9103 0.0 0.0 0.0 0.0 nan 0.5269 0.7830 0.0 0.4531 0.0086 nan 0.0 0.0 0.0 0.5897 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5528 0.0 0.0200 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7379 0.6292 0.8511 0.0 0.0 0.0 0.0
1.066 3.75 300 1.1935 0.1624 0.2109 0.7442 nan 0.8253 0.9479 0.0 0.5012 0.0083 nan 0.0 0.0 0.0 0.8755 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8923 0.0 0.0307 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9137 0.8313 0.9234 0.0 0.0 0.0 0.0 nan 0.5267 0.7849 0.0 0.4499 0.0082 nan 0.0 0.0 0.0 0.6217 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5554 0.0 0.0294 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7463 0.6202 0.8525 0.0 0.0 0.0 0.0
1.1549 4.0 320 1.1899 0.1632 0.2118 0.7464 nan 0.8334 0.9423 0.0 0.5290 0.0073 nan 0.0000 0.0 0.0 0.8857 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8956 0.0 0.0194 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9280 0.8115 0.9247 0.0 0.0 0.0 0.0 nan 0.5215 0.7940 0.0 0.4730 0.0073 nan 0.0000 0.0 0.0 0.6143 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5530 0.0 0.0188 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7488 0.6382 0.8541 0.0 0.0 0.0 0.0
1.0461 4.25 340 1.1746 0.1643 0.2127 0.7482 nan 0.8171 0.9549 0.0 0.5455 0.0078 nan 0.0 0.0 0.0 0.8974 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8812 0.0 0.0387 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9161 0.8302 0.9174 0.0 0.0 0.0 0.0 nan 0.5322 0.7872 0.0 0.4917 0.0077 nan 0.0 0.0 0.0 0.6076 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5651 0.0 0.0366 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7456 0.6282 0.8553 0.0 0.0 0.0 0.0
1.0398 4.5 360 1.1687 0.1652 0.2128 0.7494 nan 0.8254 0.9501 0.0 0.5507 0.0094 nan 0.0000 0.0 0.0 0.8755 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8972 0.0 0.0341 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9253 0.8186 0.9232 0.0 0.0 0.0 0.0 nan 0.5323 0.7930 0.0 0.4922 0.0093 nan 0.0000 0.0 0.0 0.6277 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5531 0.0 0.0323 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7518 0.6382 0.8553 0.0 0.0 0.0 0.0
1.0538 4.75 380 1.1675 0.1655 0.2135 0.7499 nan 0.8351 0.9458 0.0 0.5657 0.0087 nan 0.0000 0.0 0.0 0.8830 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8980 0.0 0.0322 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9244 0.8123 0.9262 0.0 0.0 0.0 0.0 nan 0.5260 0.7971 0.0 0.5002 0.0086 nan 0.0000 0.0 0.0 0.6214 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5537 0.0 0.0305 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7554 0.6472 0.8564 0.0 0.0 0.0 0.0
1.0232 5.0 400 1.1574 0.1657 0.2143 0.7508 nan 0.8145 0.9504 0.0 0.5828 0.0118 nan 0.0001 0.0 0.0 0.8895 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8937 0.0 0.0389 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9244 0.8287 0.9224 0.0 0.0 0.0 0.0 nan 0.5381 0.7939 0.0 0.5124 0.0117 nan 0.0001 0.0 0.0 0.6117 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5570 0.0 0.0365 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7504 0.6347 0.8566 0.0 0.0 0.0 0.0

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1