metadata
license: other
base_model: nvidia/mit-b0
tags:
- vision
- image-segmentation
- generated_from_trainer
model-index:
- name: segformerSAADNew
results: []
segformerSAADNew
This model is a fine-tuned version of nvidia/mit-b0 on the saad7489/SixGUNNew dataset. It achieves the following results on the evaluation set:
- Loss: 0.6994
- Mean Iou: 0.4393
- Mean Accuracy: 0.9081
- Overall Accuracy: 0.9708
- Accuracy Bkg: 0.9732
- Accuracy Gun: nan
- Accuracy Knife: 0.8431
- Iou Bkg: 0.9704
- Iou Gun: 0.0
- Iou Knife: 0.3476
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: 5e-05
- train_batch_size: 30
- eval_batch_size: 30
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bkg | Accuracy Gun | Accuracy Knife | Iou Bkg | Iou Gun | Iou Knife |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.8827 | 4.0 | 20 | 0.8654 | 0.4254 | 0.8976 | 0.9662 | 0.9688 | nan | 0.8264 | 0.9657 | 0.0 | 0.3106 |
| 0.7151 | 8.0 | 40 | 0.6994 | 0.4393 | 0.9081 | 0.9708 | 0.9732 | nan | 0.8431 | 0.9704 | 0.0 | 0.3476 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1