---
license: other
base_model: nvidia/mit-b0
tags:
- vision
- image-segmentation
- generated_from_trainer
model-index:
- name: segformerSAAD1
  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. -->

# segformerSAAD1

This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the saad7489/SixGUN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6923
- Mean Iou: 0.6077
- Mean Accuracy: 0.8342
- Overall Accuracy: 0.9596
- Accuracy Bkg: 0.9679
- Accuracy Knife: 0.7929
- Accuracy Gun: 0.7418
- Iou Bkg: 0.9593
- Iou Knife: 0.4467
- Iou Gun: 0.4171

## 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: 23
- eval_batch_size: 23
- 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 Bkg | Accuracy Knife | Accuracy Gun | Iou Bkg | Iou Knife | Iou Gun |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:--------------:|:------------:|:-------:|:---------:|:-------:|
| 0.819         | 20.0  | 20   | 0.9549          | 0.5466   | 0.8951        | 0.9364           | 0.9392       | 0.9027         | 0.8434       | 0.9365  | 0.3263    | 0.3771  |
| 0.6984        | 40.0  | 40   | 0.6923          | 0.6077   | 0.8342        | 0.9596           | 0.9679       | 0.7929         | 0.7418       | 0.9593  | 0.4467    | 0.4171  |


### Framework versions

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