gianlab's picture
Update README.md
ed1a09c
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-finetuned-flower-classifier
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9339263024142312

swin-tiny-patch4-window7-224-finetuned-flower-classifier

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2362
  • Accuracy: 0.9339

Model description

This model was created by importing the dataset of the photos of flowers into Google Colab from kaggle here: https://www.kaggle.com/datasets/l3llff/flowers. I then used the image classification tutorial here: https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb

obtaining the following notebook:

https://colab.research.google.com/drive/1bapCEz4vkDd16Ax9jb5oHGa85PeuyZVW?usp=sharing

The possible classified flowers are: 'common_daisy', 'rose', 'california_poppy', 'iris', 'astilbe', 'carnation', 'tulip', 'sunflower', 'coreopsis', 'magnolia', 'water_lily', 'bellflower', 'daffodil', 'calendula', 'dandelion', 'black_eyed_susan'

Flower example:

flower

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-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: 1

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.365 0.99 110 0.2362 0.9339

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.1
  • Tokenizers 0.13.2