---
license: other
tags:
- generated_from_trainer
model-index:
- name: segformer-b0-finetuned-segments-toolwear
  results: []
---

<!-- 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-finetuned-segments-toolwear

This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1003
- Mean Iou: 0.3700
- Mean Accuracy: 0.7400
- Overall Accuracy: 0.7400
- Accuracy Unlabeled: nan
- Accuracy Wear: 0.7400
- Iou Unlabeled: 0.0
- Iou Wear: 0.7400

## 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 Wear | Iou Unlabeled | Iou Wear |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------:|:-------------:|:--------:|
| 0.6115        | 3.33  | 20   | 0.6156          | 0.4098   | 0.8197        | 0.8197           | nan                | 0.8197        | 0.0           | 0.8197   |
| 0.3737        | 6.67  | 40   | 0.3901          | 0.4130   | 0.8261        | 0.8261           | nan                | 0.8261        | 0.0           | 0.8261   |
| 0.2937        | 10.0  | 60   | 0.2764          | 0.3966   | 0.7932        | 0.7932           | nan                | 0.7932        | 0.0           | 0.7932   |
| 0.2457        | 13.33 | 80   | 0.2804          | 0.3957   | 0.7914        | 0.7914           | nan                | 0.7914        | 0.0           | 0.7914   |
| 0.2099        | 16.67 | 100  | 0.2116          | 0.4119   | 0.8238        | 0.8238           | nan                | 0.8238        | 0.0           | 0.8238   |
| 0.1894        | 20.0  | 120  | 0.1894          | 0.3775   | 0.7549        | 0.7549           | nan                | 0.7549        | 0.0           | 0.7549   |
| 0.1551        | 23.33 | 140  | 0.1515          | 0.3809   | 0.7619        | 0.7619           | nan                | 0.7619        | 0.0           | 0.7619   |
| 0.1511        | 26.67 | 160  | 0.1347          | 0.3719   | 0.7438        | 0.7438           | nan                | 0.7438        | 0.0           | 0.7438   |
| 0.1299        | 30.0  | 180  | 0.1218          | 0.3716   | 0.7432        | 0.7432           | nan                | 0.7432        | 0.0           | 0.7432   |
| 0.1284        | 33.33 | 200  | 0.1275          | 0.3694   | 0.7389        | 0.7389           | nan                | 0.7389        | 0.0           | 0.7389   |
| 0.1415        | 36.67 | 220  | 0.1096          | 0.3919   | 0.7839        | 0.7839           | nan                | 0.7839        | 0.0           | 0.7839   |
| 0.1032        | 40.0  | 240  | 0.1030          | 0.3766   | 0.7531        | 0.7531           | nan                | 0.7531        | 0.0           | 0.7531   |
| 0.1076        | 43.33 | 260  | 0.0994          | 0.3818   | 0.7635        | 0.7635           | nan                | 0.7635        | 0.0           | 0.7635   |
| 0.1024        | 46.67 | 280  | 0.1024          | 0.3767   | 0.7534        | 0.7534           | nan                | 0.7534        | 0.0           | 0.7534   |
| 0.1038        | 50.0  | 300  | 0.1003          | 0.3700   | 0.7400        | 0.7400           | nan                | 0.7400        | 0.0           | 0.7400   |


### Framework versions

- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.13.3