---
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: 1.6895
- 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: 0.002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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        | 0.86  | 3    | 7.5017          | 0.1087   |
| No log        | 2.0   | 7    | 1.6895          | 0.4565   |
| 4.88          | 2.86  | 10   | 4.1382          | 0.1087   |
| 4.88          | 4.0   | 14   | 1.5189          | 0.4565   |
| 4.88          | 4.86  | 17   | 1.4064          | 0.3261   |
| 1.7482        | 6.0   | 21   | 1.3558          | 0.4565   |
| 1.7482        | 6.86  | 24   | 1.3180          | 0.3261   |
| 1.7482        | 8.0   | 28   | 1.2378          | 0.3261   |
| 1.3281        | 8.86  | 31   | 1.3390          | 0.4565   |
| 1.3281        | 10.0  | 35   | 1.2144          | 0.4565   |
| 1.3281        | 10.86 | 38   | 1.2492          | 0.3261   |
| 1.2367        | 12.0  | 42   | 1.2685          | 0.4565   |
| 1.2367        | 12.86 | 45   | 1.2390          | 0.4565   |
| 1.2367        | 14.0  | 49   | 1.2648          | 0.3261   |
| 1.2707        | 14.86 | 52   | 1.2209          | 0.4565   |
| 1.2707        | 16.0  | 56   | 1.2628          | 0.4565   |
| 1.2707        | 16.86 | 59   | 1.2173          | 0.4565   |
| 1.2699        | 18.0  | 63   | 1.2145          | 0.4565   |
| 1.2699        | 18.86 | 66   | 1.2334          | 0.4348   |
| 1.2509        | 20.0  | 70   | 1.2693          | 0.4565   |
| 1.2509        | 20.86 | 73   | 1.2041          | 0.4565   |
| 1.2509        | 22.0  | 77   | 1.2307          | 0.3696   |
| 1.1936        | 22.86 | 80   | 1.2172          | 0.4565   |
| 1.1936        | 24.0  | 84   | 1.2109          | 0.4565   |
| 1.1936        | 24.86 | 87   | 1.2051          | 0.4565   |
| 1.1629        | 26.0  | 91   | 1.2084          | 0.4565   |
| 1.1629        | 26.86 | 94   | 1.2218          | 0.4565   |
| 1.1629        | 28.0  | 98   | 1.2294          | 0.4565   |
| 1.1606        | 28.86 | 101  | 1.2060          | 0.4565   |
| 1.1606        | 30.0  | 105  | 1.2063          | 0.4130   |
| 1.1606        | 30.86 | 108  | 1.2119          | 0.4130   |
| 1.1525        | 32.0  | 112  | 1.2073          | 0.4565   |
| 1.1525        | 32.86 | 115  | 1.1995          | 0.4565   |
| 1.1525        | 34.0  | 119  | 1.1954          | 0.4565   |
| 1.1326        | 34.29 | 120  | 1.1950          | 0.4565   |


### Framework versions

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