metadata
license: other
tags:
- vision
- image-segmentation
- generated_from_trainer
model-index:
- name: segformer-b0-finetuned-busigt2
results: []
segformer-b0-finetuned-busigt2
This model is a fine-tuned version of nvidia/mit-b0 on the kasumi222/busigt5 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9345
- Mean Iou: 0.2296
- Mean Accuracy: 0.3908
- Overall Accuracy: 0.3978
- Per Category Iou: [0.0, 0.3674785422564665, 0.32138792265751265]
- Per Category Accuracy: [nan, 0.43273323064546193, 0.34877217945992856]
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: 0.00013
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
|---|---|---|---|---|---|---|---|---|
| 0.813 | 0.61 | 20 | 0.9345 | 0.2296 | 0.3908 | 0.3978 | [0.0, 0.3674785422564665, 0.32138792265751265] | [nan, 0.43273323064546193, 0.34877217945992856] |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1