---
license: apache-2.0
base_model: microsoft/cvt-21-384-22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: cvt-21-384-22k-finetuned-LeafBack
  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: 0.961038961038961
---

<!-- 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. -->

# cvt-21-384-22k-finetuned-LeafBack

This model is a fine-tuned version of [microsoft/cvt-21-384-22k](https://huggingface.co/microsoft/cvt-21-384-22k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1357
- Accuracy: 0.9610

## 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: 2e-05
- train_batch_size: 40
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 16   | 0.4915          | 0.7662   |
| No log        | 2.0   | 32   | 0.4215          | 0.7922   |
| No log        | 3.0   | 48   | 0.3265          | 0.8831   |
| No log        | 4.0   | 64   | 0.2275          | 0.8961   |
| No log        | 5.0   | 80   | 0.2464          | 0.8571   |
| No log        | 6.0   | 96   | 0.2023          | 0.9091   |
| No log        | 7.0   | 112  | 0.2282          | 0.8961   |
| No log        | 8.0   | 128  | 0.1933          | 0.9091   |
| No log        | 9.0   | 144  | 0.2563          | 0.8701   |
| No log        | 10.0  | 160  | 0.1911          | 0.9091   |
| No log        | 11.0  | 176  | 0.2113          | 0.9351   |
| No log        | 12.0  | 192  | 0.1680          | 0.9221   |
| No log        | 13.0  | 208  | 0.2042          | 0.9351   |
| No log        | 14.0  | 224  | 0.1466          | 0.9221   |
| No log        | 15.0  | 240  | 0.1277          | 0.9351   |
| No log        | 16.0  | 256  | 0.1558          | 0.9351   |
| No log        | 17.0  | 272  | 0.1407          | 0.9221   |
| No log        | 18.0  | 288  | 0.1538          | 0.9351   |
| No log        | 19.0  | 304  | 0.1735          | 0.9221   |
| No log        | 20.0  | 320  | 0.1640          | 0.9481   |
| No log        | 21.0  | 336  | 0.1774          | 0.9221   |
| No log        | 22.0  | 352  | 0.1369          | 0.9481   |
| No log        | 23.0  | 368  | 0.1503          | 0.9481   |
| No log        | 24.0  | 384  | 0.2836          | 0.9221   |
| No log        | 25.0  | 400  | 0.1777          | 0.9221   |
| No log        | 26.0  | 416  | 0.1820          | 0.9351   |
| No log        | 27.0  | 432  | 0.1260          | 0.9481   |
| No log        | 28.0  | 448  | 0.1539          | 0.9221   |
| No log        | 29.0  | 464  | 0.1622          | 0.9481   |
| No log        | 30.0  | 480  | 0.1357          | 0.9610   |


### Framework versions

- Transformers 4.38.1
- Pytorch 1.10.0+cu111
- Datasets 2.17.1
- Tokenizers 0.15.2