---
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swinv2-tiny-patch4-window8-256-DMAE-ex
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: validation
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.45652173913043476
---

<!-- 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. -->

# swinv2-tiny-patch4-window8-256-DMAE-ex

This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1869
- Accuracy: 0.4565

## 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: 4e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 40

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 0.57  | 1    | 1.3863          | 0.1087   |
| No log        | 1.71  | 3    | 1.3825          | 0.4565   |
| No log        | 2.86  | 5    | 1.3677          | 0.4565   |
| No log        | 4.0   | 7    | 1.3405          | 0.4565   |
| No log        | 4.57  | 8    | 1.3229          | 0.4565   |
| 1.3605        | 5.71  | 10   | 1.2859          | 0.4565   |
| 1.3605        | 6.86  | 12   | 1.2580          | 0.4565   |
| 1.3605        | 8.0   | 14   | 1.2332          | 0.4565   |
| 1.3605        | 8.57  | 15   | 1.2239          | 0.4565   |
| 1.3605        | 9.71  | 17   | 1.2128          | 0.4565   |
| 1.3605        | 10.86 | 19   | 1.2086          | 0.4565   |
| 1.2105        | 12.0  | 21   | 1.2092          | 0.4565   |
| 1.2105        | 12.57 | 22   | 1.2098          | 0.4565   |
| 1.2105        | 13.71 | 24   | 1.2100          | 0.4565   |
| 1.2105        | 14.86 | 26   | 1.2062          | 0.4565   |
| 1.2105        | 16.0  | 28   | 1.2015          | 0.4565   |
| 1.2105        | 16.57 | 29   | 1.1986          | 0.4565   |
| 1.1785        | 17.71 | 31   | 1.1926          | 0.4565   |
| 1.1785        | 18.86 | 33   | 1.1902          | 0.4565   |
| 1.1785        | 20.0  | 35   | 1.1885          | 0.4565   |
| 1.1785        | 20.57 | 36   | 1.1878          | 0.4565   |
| 1.1785        | 21.71 | 38   | 1.1870          | 0.4565   |
| 1.1615        | 22.86 | 40   | 1.1869          | 0.4565   |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0