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
d35f045
preview code
|
raw
history blame
6.79 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: 0.3547
  • Mean Iou: 0.3725
  • Mean Accuracy: 0.7265
  • Overall Accuracy: 0.8226
  • Accuracy Unlabeled: nan
  • Accuracy Tool: 0.6195
  • Accuracy Wear: 0.8334
  • Iou Unlabeled: 0.0
  • Iou Tool: 0.2973
  • Iou Wear: 0.8202

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: 50

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Accuracy Unlabeled Accuracy Tool Accuracy Wear Iou Unlabeled Iou Tool Iou Wear
0.7196 1.82 20 0.9873 0.2927 0.4996 0.6806 nan 0.2982 0.7009 0.0 0.2025 0.6757
0.6004 3.64 40 0.7373 0.3312 0.6517 0.7107 nan 0.5861 0.7173 0.0 0.2916 0.7019
0.5155 5.45 60 0.6634 0.3376 0.5621 0.6378 nan 0.4778 0.6463 0.0 0.3840 0.6289
0.4228 7.27 80 0.5380 0.3612 0.6707 0.7661 nan 0.5646 0.7768 0.0 0.3241 0.7595
0.3216 9.09 100 0.5102 0.3466 0.6845 0.7281 nan 0.6361 0.7330 0.0 0.3188 0.7209
0.3752 10.91 120 0.4615 0.3902 0.7013 0.8268 nan 0.5616 0.8409 0.0 0.3476 0.8229
0.3014 12.73 140 0.4504 0.4075 0.7007 0.8311 nan 0.5558 0.8457 0.0 0.3949 0.8275
0.2183 14.55 160 0.4241 0.3708 0.7363 0.8002 nan 0.6653 0.8073 0.0 0.3165 0.7959
0.1674 16.36 180 0.4173 0.4020 0.7433 0.8684 nan 0.6041 0.8824 0.0 0.3397 0.8664
0.2385 18.18 200 0.4716 0.3450 0.6543 0.7462 nan 0.5520 0.7566 0.0 0.2941 0.7410
0.1588 20.0 220 0.3742 0.3820 0.7108 0.8179 nan 0.5917 0.8299 0.0 0.3311 0.8149
0.1553 21.82 240 0.3677 0.3811 0.7312 0.8313 nan 0.6199 0.8426 0.0 0.3144 0.8291
0.1765 23.64 260 0.4131 0.3689 0.7032 0.8024 nan 0.5929 0.8135 0.0 0.3082 0.7985
0.2516 25.45 280 0.3632 0.4142 0.7158 0.8856 nan 0.5270 0.9047 0.0 0.3585 0.8841
0.1534 27.27 300 0.3979 0.3813 0.7191 0.8236 nan 0.6029 0.8354 0.0 0.3231 0.8209
0.1104 29.09 320 0.3787 0.3640 0.7439 0.8044 nan 0.6765 0.8112 0.0 0.2911 0.8007
0.1799 30.91 340 0.3654 0.3868 0.7217 0.8257 nan 0.6060 0.8374 0.0 0.3378 0.8227
0.1069 32.73 360 0.3928 0.3524 0.7171 0.7606 nan 0.6687 0.7655 0.0 0.3018 0.7554
0.1178 34.55 380 0.3703 0.3622 0.7259 0.8079 nan 0.6345 0.8172 0.0 0.2814 0.8052
0.1191 36.36 400 0.3636 0.3766 0.7396 0.8264 nan 0.6431 0.8361 0.0 0.3069 0.8230
0.2008 38.18 420 0.3836 0.3685 0.7249 0.7907 nan 0.6516 0.7981 0.0 0.3194 0.7860
0.0846 40.0 440 0.3602 0.3738 0.7285 0.8244 nan 0.6218 0.8352 0.0 0.2994 0.8219
0.1178 41.82 460 0.3631 0.3751 0.7224 0.8311 nan 0.6015 0.8433 0.0 0.2964 0.8288
0.0806 43.64 480 0.3631 0.3678 0.7233 0.8074 nan 0.6297 0.8169 0.0 0.2988 0.8045
0.1102 45.45 500 0.3731 0.3686 0.7113 0.8067 nan 0.6053 0.8174 0.0 0.3025 0.8032
0.0751 47.27 520 0.3671 0.3682 0.7249 0.8117 nan 0.6283 0.8215 0.0 0.2959 0.8085
0.1272 49.09 540 0.3547 0.3725 0.7265 0.8226 nan 0.6195 0.8334 0.0 0.2973 0.8202

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3