Hugging Face's logo

rishitunu
/
ecc_segformerv1

Image Segmentation
Transformers
PyTorch
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
9
ecc_segformerv1 / README.md
rishitunu's picture
rishitunu
Model save
905d005
preview code
|
raw
history blame
14.2 kB
metadata
license: other
base_model: nvidia/mit-b5
tags:
  - generated_from_trainer
model-index:
  - name: ecc_segformerv1
    results: []

ecc_segformerv1

This model is a fine-tuned version of nvidia/mit-b5 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1935
  • Mean Iou: 0.1871
  • Mean Accuracy: 0.3741
  • Overall Accuracy: 0.3741
  • Accuracy Background: nan
  • Accuracy Crack: 0.3741
  • Iou Background: 0.0
  • Iou Crack: 0.3741

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: 1
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: polynomial
  • training_steps: 10000

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Accuracy Background Accuracy Crack Iou Background Iou Crack
0.0921 1.0 133 0.1236 0.0883 0.1766 0.1766 nan 0.1766 0.0 0.1766
0.0673 2.0 266 0.1418 0.1519 0.3038 0.3038 nan 0.3038 0.0 0.3038
0.0706 3.0 399 0.1176 0.1469 0.2939 0.2939 nan 0.2939 0.0 0.2939
0.0642 4.0 532 0.1395 0.1961 0.3922 0.3922 nan 0.3922 0.0 0.3922
0.0569 5.0 665 0.1948 0.2044 0.4088 0.4088 nan 0.4088 0.0 0.4088
0.0654 6.0 798 0.1559 0.1727 0.3455 0.3455 nan 0.3455 0.0 0.3455
0.0551 7.0 931 0.1127 0.1812 0.3624 0.3624 nan 0.3624 0.0 0.3624
0.0631 8.0 1064 0.1901 0.1949 0.3898 0.3898 nan 0.3898 0.0 0.3898
0.0521 9.0 1197 0.1428 0.2037 0.4073 0.4073 nan 0.4073 0.0 0.4073
0.0546 10.0 1330 0.1569 0.0876 0.1751 0.1751 nan 0.1751 0.0 0.1751
0.056 11.0 1463 0.1042 0.2267 0.4534 0.4534 nan 0.4534 0.0 0.4534
0.0541 12.0 1596 0.1309 0.1844 0.3688 0.3688 nan 0.3688 0.0 0.3688
0.0489 13.0 1729 0.1364 0.1746 0.3493 0.3493 nan 0.3493 0.0 0.3493
0.0531 14.0 1862 0.1058 0.1605 0.3210 0.3210 nan 0.3210 0.0 0.3210
0.0467 15.0 1995 0.0952 0.2214 0.4427 0.4427 nan 0.4427 0.0 0.4427
0.0485 16.0 2128 0.1370 0.1934 0.3868 0.3868 nan 0.3868 0.0 0.3868
0.0453 17.0 2261 0.1215 0.1664 0.3329 0.3329 nan 0.3329 0.0 0.3329
0.0486 18.0 2394 0.1058 0.2284 0.4569 0.4569 nan 0.4569 0.0 0.4569
0.048 19.0 2527 0.1253 0.2056 0.4112 0.4112 nan 0.4112 0.0 0.4112
0.0428 20.0 2660 0.1319 0.2064 0.4128 0.4128 nan 0.4128 0.0 0.4128
0.0423 21.0 2793 0.1310 0.2076 0.4151 0.4151 nan 0.4151 0.0 0.4151
0.0386 22.0 2926 0.1163 0.2077 0.4154 0.4154 nan 0.4154 0.0 0.4154
0.0412 23.0 3059 0.1065 0.1723 0.3446 0.3446 nan 0.3446 0.0 0.3446
0.0433 24.0 3192 0.1071 0.2001 0.4001 0.4001 nan 0.4001 0.0 0.4001
0.0359 25.0 3325 0.1016 0.2023 0.4045 0.4045 nan 0.4045 0.0 0.4045
0.035 26.0 3458 0.1130 0.2028 0.4055 0.4055 nan 0.4055 0.0 0.4055
0.0458 27.0 3591 0.1157 0.2216 0.4431 0.4431 nan 0.4431 0.0 0.4431
0.0347 28.0 3724 0.1115 0.2068 0.4136 0.4136 nan 0.4136 0.0 0.4136
0.0347 29.0 3857 0.1139 0.2050 0.4100 0.4100 nan 0.4100 0.0 0.4100
0.0355 30.0 3990 0.1175 0.1889 0.3778 0.3778 nan 0.3778 0.0 0.3778
0.0313 31.0 4123 0.1269 0.1859 0.3719 0.3719 nan 0.3719 0.0 0.3719
0.0348 32.0 4256 0.1143 0.1971 0.3943 0.3943 nan 0.3943 0.0 0.3943
0.0327 33.0 4389 0.1310 0.1982 0.3965 0.3965 nan 0.3965 0.0 0.3965
0.0318 34.0 4522 0.1321 0.1864 0.3728 0.3728 nan 0.3728 0.0 0.3728
0.0268 35.0 4655 0.1257 0.1803 0.3607 0.3607 nan 0.3607 0.0 0.3607
0.0323 36.0 4788 0.1344 0.1910 0.3819 0.3819 nan 0.3819 0.0 0.3819
0.0285 37.0 4921 0.1495 0.1763 0.3527 0.3527 nan 0.3527 0.0 0.3527
0.0266 38.0 5054 0.1369 0.1817 0.3634 0.3634 nan 0.3634 0.0 0.3634
0.0287 39.0 5187 0.1444 0.1754 0.3508 0.3508 nan 0.3508 0.0 0.3508
0.0295 40.0 5320 0.1579 0.1499 0.2997 0.2997 nan 0.2997 0.0 0.2997
0.0252 41.0 5453 0.1363 0.2191 0.4382 0.4382 nan 0.4382 0.0 0.4382
0.0261 42.0 5586 0.1516 0.1809 0.3617 0.3617 nan 0.3617 0.0 0.3617
0.027 43.0 5719 0.1512 0.1940 0.3881 0.3881 nan 0.3881 0.0 0.3881
0.0235 44.0 5852 0.1346 0.2012 0.4024 0.4024 nan 0.4024 0.0 0.4024
0.03 45.0 5985 0.1505 0.1995 0.3990 0.3990 nan 0.3990 0.0 0.3990
0.0252 46.0 6118 0.1621 0.1817 0.3634 0.3634 nan 0.3634 0.0 0.3634
0.0262 47.0 6251 0.1511 0.2024 0.4049 0.4049 nan 0.4049 0.0 0.4049
0.0236 48.0 6384 0.1726 0.1644 0.3289 0.3289 nan 0.3289 0.0 0.3289
0.0275 49.0 6517 0.1674 0.2094 0.4188 0.4188 nan 0.4188 0.0 0.4188
0.0243 50.0 6650 0.1556 0.1856 0.3712 0.3712 nan 0.3712 0.0 0.3712
0.0231 51.0 6783 0.1532 0.2085 0.4169 0.4169 nan 0.4169 0.0 0.4169
0.0218 52.0 6916 0.1676 0.1773 0.3547 0.3547 nan 0.3547 0.0 0.3547
0.0234 53.0 7049 0.1732 0.1883 0.3767 0.3767 nan 0.3767 0.0 0.3767
0.0222 54.0 7182 0.1648 0.1987 0.3974 0.3974 nan 0.3974 0.0 0.3974
0.0225 55.0 7315 0.1787 0.1743 0.3485 0.3485 nan 0.3485 0.0 0.3485
0.025 56.0 7448 0.1617 0.1900 0.3800 0.3800 nan 0.3800 0.0 0.3800
0.0207 57.0 7581 0.1796 0.1973 0.3945 0.3945 nan 0.3945 0.0 0.3945
0.0223 58.0 7714 0.2011 0.1814 0.3628 0.3628 nan 0.3628 0.0 0.3628
0.0223 59.0 7847 0.1752 0.1912 0.3824 0.3824 nan 0.3824 0.0 0.3824
0.0191 60.0 7980 0.1927 0.1880 0.3759 0.3759 nan 0.3759 0.0 0.3759
0.0229 61.0 8113 0.1875 0.1806 0.3612 0.3612 nan 0.3612 0.0 0.3612
0.0197 62.0 8246 0.1755 0.1869 0.3738 0.3738 nan 0.3738 0.0 0.3738
0.0243 63.0 8379 0.1804 0.1948 0.3896 0.3896 nan 0.3896 0.0 0.3896
0.0189 64.0 8512 0.1708 0.2015 0.4031 0.4031 nan 0.4031 0.0 0.4031
0.0247 65.0 8645 0.1991 0.1837 0.3673 0.3673 nan 0.3673 0.0 0.3673
0.0223 66.0 8778 0.1971 0.1879 0.3757 0.3757 nan 0.3757 0.0 0.3757
0.0221 67.0 8911 0.1901 0.1859 0.3718 0.3718 nan 0.3718 0.0 0.3718
0.0197 68.0 9044 0.1991 0.1896 0.3792 0.3792 nan 0.3792 0.0 0.3792
0.0233 69.0 9177 0.1917 0.1880 0.3759 0.3759 nan 0.3759 0.0 0.3759
0.0222 70.0 9310 0.2073 0.1825 0.3651 0.3651 nan 0.3651 0.0 0.3651
0.0209 71.0 9443 0.1894 0.1921 0.3841 0.3841 nan 0.3841 0.0 0.3841
0.0193 72.0 9576 0.2007 0.1893 0.3786 0.3786 nan 0.3786 0.0 0.3786
0.0208 73.0 9709 0.2073 0.1902 0.3804 0.3804 nan 0.3804 0.0 0.3804
0.0212 74.0 9842 0.2043 0.1887 0.3775 0.3775 nan 0.3775 0.0 0.3775
0.0199 75.0 9975 0.1971 0.1875 0.3749 0.3749 nan 0.3749 0.0 0.3749
0.02 75.19 10000 0.1935 0.1871 0.3741 0.3741 nan 0.3741 0.0 0.3741

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cpu
  • Datasets 2.14.4
  • Tokenizers 0.13.3