Hugging Face's logo

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

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
generated_from_trainer
Inference Endpoints
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: 0.6854
  • Mean Iou: 0.2132
  • Mean Accuracy: 0.2587
  • Overall Accuracy: 0.8151
  • Accuracy Unlabeled: nan
  • Accuracy Flat-road: 0.8383
  • Accuracy Flat-sidewalk: 0.9497
  • Accuracy Flat-crosswalk: 0.0
  • Accuracy Flat-cyclinglane: 0.8212
  • Accuracy Flat-parkingdriveway: 0.3818
  • Accuracy Flat-railtrack: nan
  • Accuracy Flat-curb: 0.2786
  • Accuracy Human-person: 0.0
  • Accuracy Human-rider: 0.0
  • Accuracy Vehicle-car: 0.9368
  • 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: 0.9300
  • Accuracy Construction-door: 0.0
  • Accuracy Construction-wall: 0.0951
  • Accuracy Construction-fenceguardrail: 0.0012
  • Accuracy Construction-bridge: 0.0
  • Accuracy Construction-tunnel: nan
  • Accuracy Construction-stairs: 0.0
  • Accuracy Object-pole: 0.0181
  • Accuracy Object-trafficsign: 0.0
  • Accuracy Object-trafficlight: 0.0
  • Accuracy Nature-vegetation: 0.9377
  • Accuracy Nature-terrain: 0.8734
  • Accuracy Sky: 0.9576
  • Accuracy Void-ground: 0.0
  • Accuracy Void-dynamic: 0.0
  • Accuracy Void-static: 0.0002
  • Accuracy Void-unclear: 0.0
  • Iou Unlabeled: nan
  • Iou Flat-road: 0.6565
  • Iou Flat-sidewalk: 0.8602
  • Iou Flat-crosswalk: 0.0
  • Iou Flat-cyclinglane: 0.7150
  • Iou Flat-parkingdriveway: 0.2892
  • Iou Flat-railtrack: nan
  • Iou Flat-curb: 0.2447
  • Iou Human-person: 0.0
  • Iou Human-rider: 0.0
  • Iou Vehicle-car: 0.7028
  • 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: 0.6164
  • Iou Construction-door: 0.0
  • Iou Construction-wall: 0.0896
  • Iou Construction-fenceguardrail: 0.0012
  • Iou Construction-bridge: 0.0
  • Iou Construction-tunnel: nan
  • Iou Construction-stairs: 0.0
  • Iou Object-pole: 0.0180
  • Iou Object-trafficsign: 0.0
  • Iou Object-trafficlight: 0.0
  • Iou Nature-vegetation: 0.8065
  • Iou Nature-terrain: 0.7196
  • Iou Sky: 0.8903
  • Iou Void-ground: 0.0
  • Iou Void-dynamic: 0.0
  • Iou Void-static: 0.0002
  • 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
1.133 0.05 20 0.8142 0.1927 0.2365 0.7919 nan 0.8488 0.9396 0.0 0.6154 0.3232 nan 0.0870 0.0 0.0 0.9079 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9091 0.0 0.0057 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9459 0.8075 0.9417 0.0 0.0 0.0000 0.0 nan 0.5996 0.8350 0.0 0.5839 0.2497 nan 0.0824 0.0 0.0 0.6972 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5834 0.0 0.0057 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7902 0.6980 0.8488 0.0 0.0 0.0000 0.0
0.6183 0.1 40 0.7929 0.1935 0.2387 0.7946 nan 0.8424 0.9426 0.0 0.6490 0.2786 nan 0.0932 0.0 0.0 0.9013 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9355 0.0 0.0078 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9106 0.9015 0.9372 0.0 0.0 0.0000 0.0 nan 0.6021 0.8449 0.0 0.5861 0.2298 nan 0.0889 0.0 0.0 0.6913 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5851 0.0 0.0078 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.7952 0.6890 0.8787 0.0 0.0 0.0000 0.0
0.7143 0.15 60 0.7832 0.1963 0.2407 0.7970 nan 0.8115 0.9508 0.0 0.6225 0.3488 nan 0.1208 0.0 0.0 0.9286 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9124 0.0 0.0163 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.9415 0.8645 0.9439 0.0 0.0 0.0000 0.0 nan 0.6145 0.8356 0.0 0.5800 0.2642 nan 0.1131 0.0 0.0 0.6861 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6004 0.0 0.0161 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.7914 0.7056 0.8799 0.0 0.0 0.0000 0.0
0.7266 0.2 80 0.7789 0.1933 0.2380 0.7922 nan 0.8418 0.9346 0.0 0.6266 0.3044 nan 0.0522 0.0 0.0 0.9256 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9212 0.0 0.0297 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.9329 0.8752 0.9345 0.0 0.0 0.0 0.0 nan 0.5945 0.8266 0.0 0.5830 0.2447 nan 0.0506 0.0 0.0 0.6819 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6030 0.0 0.0293 0.0 0.0 nan 0.0 0.0000 0.0 0.0 0.7998 0.6952 0.8834 0.0 0.0 0.0 0.0
0.8732 0.25 100 0.7598 0.2025 0.2515 0.7986 nan 0.8657 0.9218 0.0 0.7984 0.3960 nan 0.1382 0.0 0.0 0.9323 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9264 0.0 0.0718 0.0 0.0 nan 0.0 0.0010 0.0 0.0 0.8819 0.9151 0.9484 0.0 0.0 0.0001 0.0 nan 0.6212 0.8387 0.0 0.7013 0.2830 nan 0.1285 0.0 0.0 0.6971 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6065 0.0 0.0696 0.0 0.0 nan 0.0 0.0010 0.0 0.0 0.7925 0.6575 0.8817 0.0 0.0 0.0001 0.0
1.0414 0.3 120 0.7519 0.2004 0.2426 0.8027 nan 0.7989 0.9643 0.0 0.7894 0.2927 nan 0.0920 0.0 0.0 0.9300 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9095 0.0 0.0169 0.0 0.0 nan 0.0 0.0012 0.0 0.0 0.9403 0.8354 0.9507 0.0 0.0 0.0003 0.0 nan 0.6503 0.8249 0.0 0.7135 0.2513 nan 0.0851 0.0 0.0 0.7073 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5968 0.0 0.0167 0.0 0.0 nan 0.0 0.0012 0.0 0.0 0.7986 0.6976 0.8675 0.0 0.0 0.0003 0.0
0.7812 0.35 140 0.7660 0.2004 0.2433 0.8008 nan 0.7714 0.9656 0.0 0.8225 0.2306 nan 0.1649 0.0 0.0 0.9393 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9225 0.0 0.0362 0.0 0.0 nan 0.0 0.0003 0.0 0.0 0.9328 0.8450 0.9101 0.0 0.0 0.0000 0.0 nan 0.6427 0.8220 0.0 0.7043 0.2006 nan 0.1508 0.0 0.0 0.6825 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5969 0.0 0.0354 0.0 0.0 nan 0.0 0.0003 0.0 0.0 0.8031 0.7024 0.8709 0.0 0.0 0.0000 0.0
0.6117 0.4 160 0.7395 0.2078 0.2505 0.8074 nan 0.8021 0.9599 0.0 0.7951 0.3092 nan 0.2320 0.0 0.0 0.9291 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9184 0.0 0.0807 0.0001 0.0 nan 0.0 0.0031 0.0 0.0 0.9379 0.8574 0.9416 0.0 0.0 0.0001 0.0 nan 0.6450 0.8340 0.0 0.7138 0.2435 nan 0.2008 0.0 0.0 0.7102 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6146 0.0 0.0776 0.0001 0.0 nan 0.0 0.0031 0.0 0.0 0.8047 0.7070 0.8874 0.0 0.0 0.0001 0.0
1.1176 0.45 180 0.7283 0.2088 0.2543 0.8066 nan 0.7949 0.9620 0.0 0.7781 0.3479 nan 0.2238 0.0 0.0 0.9365 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.8798 0.0 0.1794 0.0000 0.0 nan 0.0 0.0070 0.0 0.0 0.9212 0.8978 0.9546 0.0 0.0 0.0004 0.0 nan 0.6398 0.8361 0.0 0.7046 0.2608 nan 0.1909 0.0 0.0 0.6770 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6329 0.0 0.1669 0.0000 0.0 nan 0.0 0.0070 0.0 0.0 0.7940 0.6798 0.8840 0.0 0.0 0.0004 0.0
1.0874 0.5 200 0.7138 0.2074 0.2497 0.8093 nan 0.8548 0.9534 0.0 0.7502 0.3509 nan 0.2045 0.0 0.0 0.9139 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9440 0.0 0.0572 0.0 0.0 nan 0.0 0.0022 0.0 0.0 0.9277 0.8297 0.9518 0.0 0.0 0.0003 0.0 nan 0.6508 0.8521 0.0 0.6877 0.2737 nan 0.1824 0.0 0.0 0.7291 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5955 0.0 0.0551 0.0 0.0 nan 0.0 0.0022 0.0 0.0 0.8090 0.7067 0.8854 0.0 0.0 0.0003 0.0
1.1744 0.55 220 0.7095 0.2072 0.2491 0.8070 nan 0.8193 0.9577 0.0 0.7556 0.3430 nan 0.2271 0.0 0.0 0.9157 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9490 0.0 0.0440 0.0000 0.0 nan 0.0 0.0031 0.0 0.0 0.9225 0.8357 0.9500 0.0 0.0 0.0004 0.0 nan 0.6459 0.8463 0.0 0.7019 0.2733 nan 0.1944 0.0 0.0 0.7281 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5841 0.0 0.0412 0.0000 0.0 nan 0.0 0.0031 0.0 0.0 0.8140 0.7022 0.8892 0.0 0.0 0.0004 0.0
0.8371 0.6 240 0.7224 0.2081 0.2506 0.8073 nan 0.8102 0.9614 0.0 0.7220 0.3368 nan 0.2390 0.0 0.0 0.9278 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9066 0.0 0.1151 0.0001 0.0 nan 0.0 0.0039 0.0 0.0 0.9439 0.8466 0.9542 0.0 0.0 0.0005 0.0 nan 0.6394 0.8393 0.0 0.6850 0.2629 nan 0.2099 0.0 0.0 0.7123 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6215 0.0 0.1074 0.0001 0.0 nan 0.0 0.0039 0.0 0.0 0.7932 0.6883 0.8870 0.0 0.0 0.0005 0.0
1.0493 0.65 260 0.7100 0.2093 0.2505 0.8086 nan 0.8021 0.9639 0.0 0.7634 0.3138 nan 0.2254 0.0 0.0 0.9232 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9235 0.0 0.0942 0.0011 0.0 nan 0.0 0.0041 0.0 0.0 0.9356 0.8677 0.9456 0.0 0.0 0.0004 0.0 nan 0.6457 0.8343 0.0 0.7131 0.2547 nan 0.1979 0.0 0.0 0.7253 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6121 0.0 0.0881 0.0011 0.0 nan 0.0 0.0041 0.0 0.0 0.8033 0.7173 0.8899 0.0 0.0 0.0004 0.0
0.4048 0.7 280 0.7147 0.2112 0.2566 0.8087 nan 0.7952 0.9466 0.0 0.7771 0.4525 nan 0.3231 0.0 0.0 0.9329 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9329 0.0 0.0638 0.0 0.0 nan 0.0 0.0058 0.0 0.0 0.9506 0.8326 0.9420 0.0 0.0 0.0002 0.0 nan 0.6491 0.8535 0.0 0.7154 0.2954 nan 0.2641 0.0 0.0 0.7080 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.5986 0.0 0.0604 0.0 0.0 nan 0.0 0.0058 0.0 0.0 0.7988 0.7070 0.8915 0.0 0.0 0.0002 0.0
0.5975 0.75 300 0.7049 0.2116 0.2572 0.8123 nan 0.8359 0.9476 0.0 0.7908 0.4403 nan 0.2551 0.0 0.0 0.9417 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9331 0.0 0.0776 0.0008 0.0 nan 0.0 0.0070 0.0 0.0 0.9270 0.8649 0.9522 0.0 0.0 0.0002 0.0 nan 0.6454 0.8593 0.0 0.7080 0.3010 nan 0.2257 0.0 0.0 0.6990 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6080 0.0 0.0732 0.0008 0.0 nan 0.0 0.0070 0.0 0.0 0.8192 0.7197 0.8919 0.0 0.0 0.0002 0.0
0.655 0.8 320 0.6919 0.2109 0.2554 0.8130 nan 0.8424 0.9520 0.0 0.8082 0.3620 nan 0.2336 0.0 0.0 0.9297 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9246 0.0 0.0843 0.0011 0.0 nan 0.0 0.0133 0.0 0.0 0.9332 0.8843 0.9474 0.0 0.0 0.0005 0.0 nan 0.6512 0.8564 0.0 0.7108 0.2799 nan 0.2115 0.0 0.0 0.7167 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6164 0.0 0.0790 0.0011 0.0 nan 0.0 0.0132 0.0 0.0 0.8027 0.7060 0.8923 0.0 0.0 0.0005 0.0
0.766 0.85 340 0.6983 0.2094 0.2539 0.8097 nan 0.8143 0.9616 0.0 0.8042 0.3275 nan 0.2248 0.0000 0.0 0.9255 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9310 0.0 0.1054 0.0003 0.0 nan 0.0 0.0160 0.0 0.0 0.8967 0.9101 0.9536 0.0 0.0 0.0007 0.0 nan 0.6514 0.8454 0.0 0.7168 0.2643 nan 0.2028 0.0000 0.0 0.7219 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6178 0.0 0.0986 0.0003 0.0 nan 0.0 0.0159 0.0 0.0 0.7980 0.6668 0.8919 0.0 0.0 0.0007 0.0
0.4367 0.9 360 0.6955 0.2123 0.2566 0.8128 nan 0.8090 0.9580 0.0 0.8199 0.3753 nan 0.2754 0.0 0.0 0.9210 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9402 0.0 0.0790 0.0010 0.0 nan 0.0 0.0143 0.0 0.0 0.9208 0.8883 0.9510 0.0 0.0 0.0006 0.0 nan 0.6541 0.8514 0.0 0.7174 0.2862 nan 0.2401 0.0 0.0 0.7243 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6082 0.0 0.0741 0.0010 0.0 nan 0.0 0.0143 0.0 0.0 0.8106 0.7056 0.8928 0.0 0.0 0.0006 0.0
0.4969 0.95 380 0.6997 0.2123 0.2559 0.8125 nan 0.7947 0.9629 0.0 0.8125 0.3625 nan 0.2558 0.0001 0.0 0.9276 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9267 0.0 0.1071 0.0005 0.0 nan 0.0 0.0181 0.0 0.0 0.9333 0.8808 0.9485 0.0 0.0 0.0008 0.0 nan 0.6540 0.8439 0.0 0.7167 0.2790 nan 0.2245 0.0001 0.0 0.7203 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6212 0.0 0.1010 0.0005 0.0 nan 0.0 0.0180 0.0 0.0 0.8060 0.7023 0.8932 0.0 0.0 0.0008 0.0
0.7571 1.0 400 0.6854 0.2132 0.2587 0.8151 nan 0.8383 0.9497 0.0 0.8212 0.3818 nan 0.2786 0.0 0.0 0.9368 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.9300 0.0 0.0951 0.0012 0.0 nan 0.0 0.0181 0.0 0.0 0.9377 0.8734 0.9576 0.0 0.0 0.0002 0.0 nan 0.6565 0.8602 0.0 0.7150 0.2892 nan 0.2447 0.0 0.0 0.7028 0.0 0.0 nan 0.0 0.0 0.0 0.0 0.6164 0.0 0.0896 0.0012 0.0 nan 0.0 0.0180 0.0 0.0 0.8065 0.7196 0.8903 0.0 0.0 0.0002 0.0

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
2
Safetensors
Model size
3.72M params
Tensor type
F32
·

Finetuned from

Evaluation results

Metadata error: specify a dataset to view leaderboard