Hugging Face's logo

HorcruxNo13
/
segformer-b0-finetuned-segments-toolwear

Transformers
PyTorch
TensorBoard
Safetensors
segformer
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
segformer-b0-finetuned-segments-toolwear / README.md
HorcruxNo13's picture
HorcruxNo13
update model card README.md
0bd5730
preview code
|
raw
history blame
9.99 kB
metadata
license: other
tags:
  - generated_from_trainer
model-index:
  - name: segformer-b0-finetuned-segments-toolwear
    results: []

segformer-b0-finetuned-segments-toolwear

This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0316
  • Mean Iou: 0.4930
  • Mean Accuracy: 0.9859
  • Overall Accuracy: 0.9859
  • Accuracy Unlabeled: nan
  • Accuracy Outline: 0.9859
  • Iou Unlabeled: 0.0
  • Iou Outline: 0.9859

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: 24
  • eval_batch_size: 24
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 40

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Accuracy Unlabeled Accuracy Outline Iou Unlabeled Iou Outline
0.1277 0.8 20 0.1795 0.4907 0.9814 0.9814 nan 0.9814 0.0 0.9814
0.1026 1.6 40 0.0920 0.4764 0.9529 0.9529 nan 0.9529 0.0 0.9529
0.0934 2.4 60 0.0782 0.4859 0.9718 0.9718 nan 0.9718 0.0 0.9718
0.0682 3.2 80 0.0656 0.4862 0.9724 0.9724 nan 0.9724 0.0 0.9724
0.054 4.0 100 0.0584 0.4885 0.9769 0.9769 nan 0.9769 0.0 0.9769
0.0529 4.8 120 0.0528 0.4894 0.9787 0.9787 nan 0.9787 0.0 0.9787
0.0586 5.6 140 0.0498 0.4885 0.9771 0.9771 nan 0.9771 0.0 0.9771
0.0538 6.4 160 0.0464 0.4878 0.9756 0.9756 nan 0.9756 0.0 0.9756
0.0422 7.2 180 0.0443 0.4926 0.9851 0.9851 nan 0.9851 0.0 0.9851
0.0517 8.0 200 0.0443 0.4914 0.9828 0.9828 nan 0.9828 0.0 0.9828
0.0439 8.8 220 0.0409 0.4912 0.9824 0.9824 nan 0.9824 0.0 0.9824
0.0357 9.6 240 0.0394 0.4899 0.9799 0.9799 nan 0.9799 0.0 0.9799
0.0381 10.4 260 0.0393 0.4901 0.9801 0.9801 nan 0.9801 0.0 0.9801
0.0362 11.2 280 0.0396 0.4931 0.9863 0.9863 nan 0.9863 0.0 0.9863
0.0317 12.0 300 0.0373 0.4922 0.9844 0.9844 nan 0.9844 0.0 0.9844
0.0342 12.8 320 0.0423 0.4950 0.9899 0.9899 nan 0.9899 0.0 0.9899
0.0341 13.6 340 0.0374 0.4925 0.9849 0.9849 nan 0.9849 0.0 0.9849
0.0347 14.4 360 0.0358 0.4921 0.9842 0.9842 nan 0.9842 0.0 0.9842
0.0351 15.2 380 0.0358 0.4928 0.9855 0.9855 nan 0.9855 0.0 0.9855
0.0589 16.0 400 0.0346 0.4908 0.9816 0.9816 nan 0.9816 0.0 0.9816
0.0354 16.8 420 0.0353 0.4945 0.9891 0.9891 nan 0.9891 0.0 0.9891
0.0349 17.6 440 0.0346 0.4899 0.9797 0.9797 nan 0.9797 0.0 0.9797
0.0357 18.4 460 0.0340 0.4927 0.9855 0.9855 nan 0.9855 0.0 0.9855
0.032 19.2 480 0.0348 0.4904 0.9808 0.9808 nan 0.9808 0.0 0.9808
0.0365 20.0 500 0.0337 0.4924 0.9849 0.9849 nan 0.9849 0.0 0.9849
0.0361 20.8 520 0.0334 0.4932 0.9863 0.9863 nan 0.9863 0.0 0.9863
0.0411 21.6 540 0.0324 0.4921 0.9843 0.9843 nan 0.9843 0.0 0.9843
0.0335 22.4 560 0.0329 0.4932 0.9864 0.9864 nan 0.9864 0.0 0.9864
0.0285 23.2 580 0.0327 0.4924 0.9847 0.9847 nan 0.9847 0.0 0.9847
0.0339 24.0 600 0.0328 0.4913 0.9827 0.9827 nan 0.9827 0.0 0.9827
0.034 24.8 620 0.0323 0.4934 0.9869 0.9869 nan 0.9869 0.0 0.9869
0.0314 25.6 640 0.0336 0.4940 0.9880 0.9880 nan 0.9880 0.0 0.9880
0.029 26.4 660 0.0324 0.4926 0.9853 0.9853 nan 0.9853 0.0 0.9853
0.0371 27.2 680 0.0324 0.4917 0.9833 0.9833 nan 0.9833 0.0 0.9833
0.0288 28.0 700 0.0322 0.4931 0.9862 0.9862 nan 0.9862 0.0 0.9862
0.0297 28.8 720 0.0320 0.4925 0.9849 0.9849 nan 0.9849 0.0 0.9849
0.0256 29.6 740 0.0321 0.4923 0.9846 0.9846 nan 0.9846 0.0 0.9846
0.033 30.4 760 0.0317 0.4926 0.9852 0.9852 nan 0.9852 0.0 0.9852
0.0251 31.2 780 0.0328 0.4943 0.9887 0.9887 nan 0.9887 0.0 0.9887
0.0286 32.0 800 0.0322 0.4938 0.9876 0.9876 nan 0.9876 0.0 0.9876
0.0273 32.8 820 0.0318 0.4930 0.9859 0.9859 nan 0.9859 0.0 0.9859
0.0289 33.6 840 0.0325 0.4937 0.9873 0.9873 nan 0.9873 0.0 0.9873
0.0279 34.4 860 0.0325 0.4937 0.9874 0.9874 nan 0.9874 0.0 0.9874
0.0284 35.2 880 0.0325 0.4940 0.9879 0.9879 nan 0.9879 0.0 0.9879
0.0229 36.0 900 0.0317 0.4931 0.9861 0.9861 nan 0.9861 0.0 0.9861
0.0256 36.8 920 0.0316 0.4927 0.9854 0.9854 nan 0.9854 0.0 0.9854
0.0278 37.6 940 0.0319 0.4933 0.9867 0.9867 nan 0.9867 0.0 0.9867
0.0301 38.4 960 0.0318 0.4932 0.9865 0.9865 nan 0.9865 0.0 0.9865
0.0233 39.2 980 0.0319 0.4934 0.9868 0.9868 nan 0.9868 0.0 0.9868
0.0256 40.0 1000 0.0316 0.4930 0.9859 0.9859 nan 0.9859 0.0 0.9859

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.13.3