---
base_model: nvidia/mit-b0
license: other
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: 0.7621
- Mean Iou: 0.4717
- Mean Accuracy: 0.8197
- Overall Accuracy: 0.8114
- Accuracy Object1: nan
- Accuracy Object2: 0.6867
- Accuracy Object3: 0.9527
- Iou Object1: 0.0
- Iou Object2: 0.6649
- Iou Object3: 0.7502

## 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 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:----------------:|:----------------:|:----------------:|:-----------:|:-----------:|:-----------:|
| 0.9327        | 1.4286 | 20   | 1.0058          | 0.3119   | 0.6386        | 0.6235           | nan              | 0.3968           | 0.8803           | 0.0         | 0.3621      | 0.5736      |
| 0.9028        | 2.8571 | 40   | 0.8719          | 0.3792   | 0.7295        | 0.7148           | nan              | 0.4933           | 0.9656           | 0.0         | 0.4796      | 0.6580      |
| 0.8514        | 4.2857 | 60   | 0.8211          | 0.4199   | 0.7734        | 0.7615           | nan              | 0.5833           | 0.9635           | 0.0         | 0.5662      | 0.6936      |
| 0.8251        | 5.7143 | 80   | 0.7680          | 0.4585   | 0.8077        | 0.7986           | nan              | 0.6613           | 0.9541           | 0.0         | 0.6389      | 0.7364      |
| 0.8048        | 7.1429 | 100  | 0.7591          | 0.4643   | 0.8141        | 0.8053           | nan              | 0.6717           | 0.9565           | 0.0         | 0.6514      | 0.7414      |
| 0.7667        | 8.5714 | 120  | 0.7591          | 0.4751   | 0.8230        | 0.8153           | nan              | 0.6997           | 0.9462           | 0.0         | 0.6737      | 0.7517      |
| 0.7748        | 10.0   | 140  | 0.7621          | 0.4717   | 0.8197        | 0.8114           | nan              | 0.6867           | 0.9527           | 0.0         | 0.6649      | 0.7502      |


### Framework versions

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