<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
segformer-b0-DeepCrack
This model is a fine-tuned version of nvidia/mit-b4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0017
- Mean Iou: 0.0
- Mean Accuracy: 0.0
- Overall Accuracy: 0.0
- Accuracy Background: nan
- Accuracy Cracked: 0.0
- Iou Background: 0.0
- Iou Cracked: 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Cracked | Iou Background | Iou Cracked |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.2923 | 0.13 | 20 | 0.2120 | 0.0200 | 0.0399 | 0.0399 | nan | 0.0399 | 0.0 | 0.0399 |
| 0.0959 | 0.27 | 40 | 0.0702 | 0.0661 | 0.1321 | 0.1321 | nan | 0.1321 | 0.0 | 0.1321 |
| 0.0316 | 0.4 | 60 | 0.0378 | 0.0193 | 0.0387 | 0.0387 | nan | 0.0387 | 0.0 | 0.0387 |
| 0.0184 | 0.53 | 80 | 0.0165 | 0.0306 | 0.0612 | 0.0612 | nan | 0.0612 | 0.0 | 0.0612 |
| 0.0119 | 0.67 | 100 | 0.0108 | 0.0277 | 0.0554 | 0.0554 | nan | 0.0554 | 0.0 | 0.0554 |
| 0.0083 | 0.8 | 120 | 0.0085 | 0.0381 | 0.0761 | 0.0761 | nan | 0.0761 | 0.0 | 0.0761 |
| 0.0085 | 0.93 | 140 | 0.0118 | 0.0112 | 0.0223 | 0.0223 | nan | 0.0223 | 0.0 | 0.0223 |
| 0.0072 | 1.07 | 160 | 0.0063 | 0.0289 | 0.0578 | 0.0578 | nan | 0.0578 | 0.0 | 0.0578 |
| 0.0072 | 1.2 | 180 | 0.0057 | 0.0004 | 0.0009 | 0.0009 | nan | 0.0009 | 0.0 | 0.0009 |
| 0.0038 | 1.33 | 200 | 0.0037 | 0.0004 | 0.0009 | 0.0009 | nan | 0.0009 | 0.0 | 0.0009 |
| 0.0038 | 1.47 | 220 | 0.0035 | 0.0024 | 0.0048 | 0.0048 | nan | 0.0048 | 0.0 | 0.0048 |
| 0.0037 | 1.6 | 240 | 0.0033 | 0.0035 | 0.0071 | 0.0071 | nan | 0.0071 | 0.0 | 0.0071 |
| 0.004 | 1.73 | 260 | 0.0029 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0027 | 1.87 | 280 | 0.0027 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
| 0.0029 | 2.0 | 300 | 0.0025 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0032 | 2.13 | 320 | 0.0026 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0024 | 2.27 | 340 | 0.0023 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0021 | 2.4 | 360 | 0.0024 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0021 | 2.53 | 380 | 0.0021 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0026 | 2.67 | 400 | 0.0020 | 0.0000 | 0.0001 | 0.0001 | nan | 0.0001 | 0.0 | 0.0001 |
| 0.002 | 2.8 | 420 | 0.0018 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0019 | 2.93 | 440 | 0.0020 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0023 | 3.07 | 460 | 0.0020 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
| 0.002 | 3.2 | 480 | 0.0019 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0018 | 3.33 | 500 | 0.0019 | 0.0000 | 0.0001 | 0.0001 | nan | 0.0001 | 0.0 | 0.0001 |
| 0.0018 | 3.47 | 520 | 0.0018 | 0.0000 | 0.0001 | 0.0001 | nan | 0.0001 | 0.0 | 0.0001 |
| 0.0021 | 3.6 | 540 | 0.0017 | 0.0000 | 0.0000 | 0.0000 | nan | 0.0000 | 0.0 | 0.0000 |
| 0.0018 | 3.73 | 560 | 0.0017 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
| 0.0017 | 3.87 | 580 | 0.0016 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
| 0.002 | 4.0 | 600 | 0.0017 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
