Hugging Face's logo

ichigoDifuku
/
segformer-b0-finetuned-segments-sidewalk-2

Image Segmentation
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Model card Files Metrics Community
Edit model card

segformer-b0-finetuned-segments-sidewalk-2

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: 0.5973
  • Mean Iou: 0.2741
  • Mean Accuracy: 0.3241
  • Overall Accuracy: 0.8431
  • Accuracy Unlabeled: nan
  • Accuracy Flat-road: 0.8917
  • Accuracy Flat-sidewalk: 0.9574
  • Accuracy Flat-crosswalk: 0.5943
  • Accuracy Flat-cyclinglane: 0.7718
  • Accuracy Flat-parkingdriveway: 0.4461
  • Accuracy Flat-railtrack: 0.0
  • Accuracy Flat-curb: 0.4790
  • Accuracy Human-person: 0.6275
  • Accuracy Human-rider: 0.0
  • Accuracy Vehicle-car: 0.9331
  • Accuracy Vehicle-truck: 0.0
  • Accuracy Vehicle-bus: 0.0
  • Accuracy Vehicle-tramtrain: 0.0
  • Accuracy Vehicle-motorcycle: 0.0
  • Accuracy Vehicle-bicycle: 0.3002
  • Accuracy Vehicle-caravan: 0.0
  • Accuracy Vehicle-cartrailer: 0.0
  • Accuracy Construction-building: 0.8853
  • Accuracy Construction-door: 0.0
  • Accuracy Construction-wall: 0.5059
  • Accuracy Construction-fenceguardrail: 0.1500
  • Accuracy Construction-bridge: 0.0
  • Accuracy Construction-tunnel: nan
  • Accuracy Construction-stairs: 0.0
  • Accuracy Object-pole: 0.1196
  • Accuracy Object-trafficsign: 0.0
  • Accuracy Object-trafficlight: 0.0
  • Accuracy Nature-vegetation: 0.9324
  • Accuracy Nature-terrain: 0.8845
  • Accuracy Sky: 0.9657
  • Accuracy Void-ground: 0.0
  • Accuracy Void-dynamic: 0.0
  • Accuracy Void-static: 0.2504
  • Accuracy Void-unclear: 0.0
  • Iou Unlabeled: nan
  • Iou Flat-road: 0.7433
  • Iou Flat-sidewalk: 0.8594
  • Iou Flat-crosswalk: 0.5654
  • Iou Flat-cyclinglane: 0.7149
  • Iou Flat-parkingdriveway: 0.3468
  • Iou Flat-railtrack: 0.0
  • Iou Flat-curb: 0.3889
  • Iou Human-person: 0.4411
  • Iou Human-rider: 0.0
  • Iou Vehicle-car: 0.8003
  • Iou Vehicle-truck: 0.0
  • Iou Vehicle-bus: 0.0
  • Iou Vehicle-tramtrain: 0.0
  • Iou Vehicle-motorcycle: 0.0
  • Iou Vehicle-bicycle: 0.2484
  • Iou Vehicle-caravan: 0.0
  • Iou Vehicle-cartrailer: 0.0
  • Iou Construction-building: 0.7020
  • Iou Construction-door: 0.0
  • Iou Construction-wall: 0.3589
  • Iou Construction-fenceguardrail: 0.1472
  • Iou Construction-bridge: 0.0
  • Iou Construction-tunnel: nan
  • Iou Construction-stairs: 0.0
  • Iou Object-pole: 0.1109
  • Iou Object-trafficsign: 0.0
  • Iou Object-trafficlight: 0.0
  • Iou Nature-vegetation: 0.8106
  • Iou Nature-terrain: 0.7138
  • Iou Sky: 0.8976
  • Iou Void-ground: 0.0
  • Iou Void-dynamic: 0.0
  • Iou Void-static: 0.1950
  • 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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

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
1.611 1.0 100 1.3435 0.1511 0.1998 0.7326 nan 0.8304 0.8942 0.0 0.4356 0.0015 0.0 0.0000 0.0 0.0 0.9156 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8185 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9098 0.8566 0.9324 0.0 0.0 0.0 0.0 nan 0.4820 0.7633 0.0 0.4233 0.0015 0.0 0.0000 0.0 0.0 0.5840 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5841 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7275 0.5762 0.8456 0.0 0.0 0.0 0.0
1.137 2.0 200 1.0101 0.1634 0.2060 0.7605 nan 0.8276 0.9403 0.0 0.5388 0.0501 0.0 0.0037 0.0 0.0 0.9244 0.0 0.0 0.0 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 0.9359 0.7548 0.9394 0.0 0.0 0.0 0.0 nan 0.5394 0.7902 0.0 0.5030 0.0473 0.0 0.0037 0.0 0.0 0.6562 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.5962 0.0 0.0 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7557 0.6370 0.8647 0.0 0.0 0.0 0.0
0.9072 3.0 300 0.8578 0.1838 0.2268 0.7835 nan 0.8225 0.9528 0.0 0.5973 0.2935 0.0 0.2630 0.0025 0.0 0.9198 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.8787 0.0 0.0079 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9360 0.8653 0.9461 0.0 0.0 0.0001 0.0 nan 0.6292 0.8005 0.0 0.5630 0.2090 0.0 0.2160 0.0025 0.0 0.6917 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.6191 0.0 0.0079 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7644 0.6802 0.8816 0.0 0.0 0.0001 0.0
0.8185 4.0 400 0.7882 0.1989 0.2415 0.7956 nan 0.7952 0.9597 0.0 0.7546 0.2634 0.0 0.3463 0.0840 0.0 0.9316 0.0 0.0 0.0 0.0 0.0041 0.0 0.0 0.8908 0.0 0.1958 0.0 0.0 nan 0.0 0.0022 0.0 0.0 0.9252 0.8699 0.9444 0.0 0.0 0.0031 0.0 nan 0.6240 0.8069 0.0 0.6760 0.2169 0.0 0.2836 0.0834 0.0 0.6913 0.0 0.0 0.0 0.0 0.0041 0.0 0.0 0.6411 0.0 0.1802 0.0 0.0 nan 0.0 0.0022 0.0 0.0 0.7785 0.6854 0.8880 0.0 0.0 0.0030 0.0
0.7126 5.0 500 0.6955 0.2183 0.2633 0.8120 nan 0.8911 0.9470 0.0 0.7170 0.4330 0.0 0.3882 0.3402 0.0 0.9353 0.0 0.0 0.0 0.0 0.0431 0.0 0.0 0.9055 0.0 0.3163 0.0001 0.0 nan 0.0 0.0169 0.0 0.0 0.9358 0.8452 0.9570 0.0 0.0 0.0175 0.0 nan 0.6663 0.8443 0.0 0.6712 0.3070 0.0 0.3186 0.2908 0.0 0.7295 0.0 0.0 0.0 0.0 0.0426 0.0 0.0 0.6535 0.0 0.2567 0.0001 0.0 nan 0.0 0.0168 0.0 0.0 0.7948 0.7024 0.8913 0.0 0.0 0.0169 0.0
0.6301 6.0 600 0.6489 0.2343 0.2820 0.8200 nan 0.8983 0.9516 0.0367 0.6998 0.4508 0.0 0.4324 0.4498 0.0 0.9273 0.0 0.0 0.0 0.0 0.1090 0.0 0.0 0.8946 0.0 0.4651 0.0242 0.0 nan 0.0 0.0529 0.0 0.0 0.9303 0.8783 0.9598 0.0 0.0 0.1467 0.0 nan 0.6706 0.8600 0.0366 0.6645 0.3249 0.0 0.3476 0.3571 0.0 0.7710 0.0 0.0 0.0 0.0 0.1062 0.0 0.0 0.6826 0.0 0.3357 0.0242 0.0 nan 0.0 0.0517 0.0 0.0 0.7885 0.6900 0.8949 0.0 0.0 0.1269 0.0
0.6233 7.0 700 0.6114 0.2574 0.3056 0.8362 nan 0.9201 0.9481 0.4433 0.7484 0.4279 0.0 0.4697 0.5517 0.0 0.9392 0.0 0.0 0.0 0.0 0.1717 0.0 0.0 0.9109 0.0 0.4857 0.0654 0.0 nan 0.0 0.0839 0.0 0.0 0.9306 0.8631 0.9602 0.0 0.0 0.1655 0.0 nan 0.7205 0.8672 0.4324 0.7056 0.3159 0.0 0.3665 0.4028 0.0 0.7768 0.0 0.0 0.0 0.0 0.1553 0.0 0.0 0.6845 0.0 0.3553 0.0652 0.0 nan 0.0 0.0801 0.0 0.0 0.8115 0.7151 0.8973 0.0 0.0 0.1422 0.0
0.5976 8.0 800 0.6079 0.2675 0.3160 0.8399 nan 0.8925 0.9563 0.5797 0.7454 0.4506 0.0 0.4743 0.5701 0.0 0.9310 0.0 0.0 0.0 0.0 0.2390 0.0 0.0 0.8996 0.0 0.5096 0.1015 0.0 nan 0.0 0.0911 0.0 0.0 0.9289 0.8862 0.9600 0.0 0.0 0.2112 0.0 nan 0.7371 0.8592 0.5545 0.7028 0.3314 0.0 0.3883 0.4237 0.0 0.7920 0.0 0.0 0.0 0.0 0.2045 0.0 0.0 0.6950 0.0 0.3606 0.1006 0.0 nan 0.0 0.0868 0.0 0.0 0.8094 0.7093 0.8986 0.0 0.0 0.1743 0.0
0.5346 9.0 900 0.5961 0.2715 0.3233 0.8428 nan 0.9151 0.9464 0.5468 0.7937 0.4682 0.0 0.4628 0.6180 0.0 0.9350 0.0 0.0 0.0 0.0 0.2914 0.0 0.0 0.8768 0.0 0.5235 0.1304 0.0 nan 0.0 0.1123 0.0 0.0 0.9369 0.8892 0.9621 0.0 0.0 0.2611 0.0 nan 0.7454 0.8704 0.5242 0.7242 0.3413 0.0 0.3770 0.4351 0.0 0.7947 0.0 0.0 0.0 0.0 0.2413 0.0 0.0 0.7017 0.0 0.3608 0.1287 0.0 nan 0.0 0.1054 0.0 0.0 0.8056 0.7052 0.8994 0.0 0.0 0.1976 0.0
0.5377 10.0 1000 0.5973 0.2741 0.3241 0.8431 nan 0.8917 0.9574 0.5943 0.7718 0.4461 0.0 0.4790 0.6275 0.0 0.9331 0.0 0.0 0.0 0.0 0.3002 0.0 0.0 0.8853 0.0 0.5059 0.1500 0.0 nan 0.0 0.1196 0.0 0.0 0.9324 0.8845 0.9657 0.0 0.0 0.2504 0.0 nan 0.7433 0.8594 0.5654 0.7149 0.3468 0.0 0.3889 0.4411 0.0 0.8003 0.0 0.0 0.0 0.0 0.2484 0.0 0.0 0.7020 0.0 0.3589 0.1472 0.0 nan 0.0 0.1109 0.0 0.0 0.8106 0.7138 0.8976 0.0 0.0 0.1950 0.0

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.2.1+cu118
  • Datasets 2.17.1
  • Tokenizers 0.15.2
Downloads last month
5
Safetensors
Model size
3.72M params
Tensor type
F32
·
Inference Examples
Image Segmentation
Unable to determine this model's library. Check the docs .

Model tree for ichigoDifuku/segformer-b0-finetuned-segments-sidewalk-2

Base model

nvidia/mit-b0
Finetuned
(313)
this model

Evaluation results

Metadata error: specify a dataset to view leaderboard