---
license: other
base_model: nvidia/mit-b0
tags:
- vision
- image-segmentation
- generated_from_trainer
model-index:
- name: segformer-b0-finetuned-segments-SixrayKnife8-19-2024
  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-SixrayKnife8-19-2024

This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the saad7489/SixraygunTest dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8400
- Mean Iou: 0.5119
- Mean Accuracy: 0.8558
- Overall Accuracy: 0.8558
- Accuracy Object1: nan
- Accuracy Object2: 0.8556
- Accuracy Object3: 0.8561
- Iou Object1: 0.0
- Iou Object2: 0.7670
- Iou Object3: 0.7687

## 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: 1e-05
- train_batch_size: 5
- eval_batch_size: 5
- 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 Object1 | Accuracy Object2 | Accuracy Object3 | Iou Object1 | Iou Object2 | Iou Object3 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:----------------:|:----------------:|:----------------:|:-----------:|:-----------:|:-----------:|
| 1.0078        | 1.4286 | 20   | 1.0664          | 0.3704   | 0.7172        | 0.7115           | nan              | 0.6051           | 0.8292           | 0.0         | 0.5243      | 0.5870      |
| 0.9646        | 2.8571 | 40   | 0.9611          | 0.4414   | 0.7944        | 0.7925           | nan              | 0.7559           | 0.8330           | 0.0         | 0.6574      | 0.6668      |
| 0.9287        | 4.2857 | 60   | 0.8994          | 0.4776   | 0.8308        | 0.8297           | nan              | 0.8085           | 0.8532           | 0.0         | 0.7157      | 0.7172      |
| 0.873         | 5.7143 | 80   | 0.8656          | 0.4944   | 0.8451        | 0.8440           | nan              | 0.8231           | 0.8671           | 0.0         | 0.7390      | 0.7442      |
| 0.8578        | 7.1429 | 100  | 0.8394          | 0.5069   | 0.8534        | 0.8532           | nan              | 0.8493           | 0.8575           | 0.0         | 0.7602      | 0.7605      |
| 0.8201        | 8.5714 | 120  | 0.8329          | 0.5102   | 0.8545        | 0.8546           | nan              | 0.8558           | 0.8531           | 0.0         | 0.7648      | 0.7657      |
| 0.8415        | 10.0   | 140  | 0.8400          | 0.5119   | 0.8558        | 0.8558           | nan              | 0.8556           | 0.8561           | 0.0         | 0.7670      | 0.7687      |


### Framework versions

- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1