gianlab's picture
Librarian Bot: Add base_model information to model (#2)
0277b55
|
raw
history blame
2.48 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
base_model: microsoft/swin-tiny-patch4-window7-224
model-index:
  - name: swin-tiny-patch4-window7-224-finetuned-skin-cancer
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: imagefolder
          type: imagefolder
          args: default
        metrics:
          - type: accuracy
            value: 0.7275449101796407
            name: Accuracy

swin-tiny-patch4-window7-224-finetuned-skin-cancer

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: 0.7695
  • Accuracy: 0.7275

Model description

This model was created by importing the dataset of the photos of skin cancer into Google Colab from kaggle here: https://www.kaggle.com/datasets/kmader/skin-cancer-mnist-ham10000 . 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/1bMkXnAvAqjX3J2YJ8wXTNw2Z2pt5KCjy?usp=sharing

The possible classified diseases are: 'Actinic-keratoses', 'Basal-cell-carcinoma', 'Benign-keratosis-like-lesions', 'Dermatofibroma', 'Melanocytic-nevi', 'Melanoma', 'Vascular-lesions' .

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: 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
0.6911 0.99 70 0.7695 0.7275

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.11.0+cu113
  • Datasets 2.3.2
  • Tokenizers 0.12.1