---
license: other
base_model: nvidia/mit-b0
tags:
- vision
- image-segmentation
- generated_from_trainer
model-index:
- name: segformer-b0-finetuned-segments-SixrayKnife8-21-2024SAAD
  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-SixrayKnife8-21-2024SAAD

This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the ammaranasim/SixraygunTest dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4616
- Mean Iou: 0.6570
- Mean Accuracy: 0.8375
- Overall Accuracy: 0.9648
- Accuracy Bkg: 0.9748
- Accuracy Knife: 0.7634
- Accuracy Gun: 0.7742
- Iou Bkg: 0.9648
- Iou Knife: 0.5405
- Iou Gun: 0.4656

## 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: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bkg | Accuracy Knife | Accuracy Gun | Iou Bkg | Iou Knife | Iou Gun |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:--------------:|:------------:|:-------:|:---------:|:-------:|
| 0.7241        | 5.0   | 20   | 0.8184          | 0.5842   | 0.8808        | 0.9419           | 0.9469       | 0.8177         | 0.8779       | 0.9420  | 0.4548    | 0.3560  |
| 0.5542        | 10.0  | 40   | 0.5299          | 0.6345   | 0.8232        | 0.9609           | 0.9718       | 0.7379         | 0.7599       | 0.9610  | 0.5139    | 0.4287  |
| 0.5048        | 15.0  | 60   | 0.4720          | 0.6469   | 0.8313        | 0.9630           | 0.9734       | 0.7479         | 0.7725       | 0.9630  | 0.5314    | 0.4463  |
| 0.4684        | 20.0  | 80   | 0.4616          | 0.6570   | 0.8375        | 0.9648           | 0.9748       | 0.7634         | 0.7742       | 0.9648  | 0.5405    | 0.4656  |


### Framework versions

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