license: other
tags:
- generated_from_keras_callback
model-index:
- name: nateraw/mit-b0-finetuned-sidewalks-v2
results: []
nateraw/mit-b0-finetuned-sidewalks-v2
This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.7134
- Validation Loss: 0.5660
- Validation Mean Iou: 0.2780
- Validation Mean Accuracy: 0.3320
- Validation Overall Accuracy: 0.8286
- Validation Per Category Iou: [0. 0.64791461 0.83800512 0.67301044 0.68120631 0.27361472 nan 0.26715802 0.43596999 0. 0.78649287 0.
0. 0. 0.41256964 0. 0.
0.71114766 0. 0.31646321 0.44682442 0. nan 0. 0.17132551 0. 0. 0.81845697 0.67536699 0.88940936 0. 0. 0.1304862 0. ]
- Validation Per Category Accuracy: [0. 0.85958877 0.92084269 0.82341633 0.74725972 0.33495972 nan 0.40755277 0.56591531 0. 0.90641721 0.
0. 0. 0.48144408 0. 0.
0.88294811 0. 0.46962078 0.47517397 0. nan 0. 0.20631607 0. 0. 0.90956851 0.85856042 0.94107052 0. 0. 0.16669713 0. ]
- Epoch: 2
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:
- optimizer: {'name': 'Adam', 'learning_rate': 6e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Validation Mean Iou | Validation Mean Accuracy | Validation Overall Accuracy | Validation Per Category Iou | Validation Per Category Accuracy | Epoch |
|---|---|---|---|---|---|---|---|
| 1.4089 | 0.8220 | 0.1975 | 0.2427 | 0.7701 | [0. 0.58353931 0.7655921 0.04209491 0.53135026 0.11779776 |
nan 0.07709853 0.15950712 0. 0.69634813 0.
0. 0. 0. 0. 0.
0.61456822 0. 0.24971248 0.27129675 0. nan 0. 0.07697324 0. 0. 0.78576516 0.61267064 0.84564576 0. 0. 0.08904216 0. ] | [0. 0.88026971 0.93475302 0.04216372 0.5484085 0.13285614 nan 0.08669707 0.19044773 0. 0.90089024 0. 0. 0. 0. 0. 0. 0. 0.76783975 0. 0.42102101 0.28659817 0. nan 0. 0.08671771 0. 0. 0.89590301 0.74932576 0.9434814 0. 0. 0.14245566 0. ] | 0 | | 0.8462 | 0.6135 | 0.2551 | 0.2960 | 0.8200 | [0. 0.66967645 0.80571406 0.56416239 0.66692248 0.24744912 nan 0.23994505 0.28962463 0. 0.76504783 0. 0. 0. 0. 0.14111353 0. 0. 0.6924468 0. 0.27988701 0.41876094 0. nan 0. 0.14755829 0. 0. 0.81614463 0.68429711 0.87710938 0. 0. 0.11234171 0. ] | [0. 0.83805933 0.94928385 0.59586511 0.72913519 0.30595504 nan 0.3128234 0.34805831 0. 0.87847495 0. 0. 0. 0. 0.14205167 0. 0. 0.87543619 0. 0.36001144 0.49498574 0. nan 0. 0.18179115 0. 0. 0.92867923 0.7496178 0.92220166 0. 0. 0.15398549 0. ] | 1 | | 0.7134 | 0.5660 | 0.2780 | 0.3320 | 0.8286 | [0. 0.64791461 0.83800512 0.67301044 0.68120631 0.27361472 nan 0.26715802 0.43596999 0. 0.78649287 0. 0. 0. 0. 0.41256964 0. 0. 0.71114766 0. 0.31646321 0.44682442 0. nan 0. 0.17132551 0. 0. 0.81845697 0.67536699 0.88940936 0. 0. 0.1304862 0. ] | [0. 0.85958877 0.92084269 0.82341633 0.74725972 0.33495972 nan 0.40755277 0.56591531 0. 0.90641721 0. 0. 0. 0. 0.48144408 0. 0. 0.88294811 0. 0.46962078 0.47517397 0. nan 0. 0.20631607 0. 0. 0.90956851 0.85856042 0.94107052 0. 0. 0.16669713 0. ] | 2 |
Framework versions
- Transformers 4.24.0
- TensorFlow 2.9.2
- Datasets 2.7.0
- Tokenizers 0.13.2