gianlab's picture
Update README.md
688fb1a verified
|
raw
history blame
2.6 kB
metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-finetuned-ecg-classification
    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: 1

swin-tiny-patch4-window7-224-finetuned-ecg-classification

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: 0.0000
  • Accuracy: 1.0

Model description

This model was created by importing the dataset of the photos of ECG image into Google Colab from kaggle here: https://www.kaggle.com/datasets/erhmrai/ecg-image-data/data . 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/1KC6twirtsc7N1kmlwY3IQKVUmSuK7zlh?usp=sharing

The possible classified data are:

  • N: Normal beat
  • S: Supraventricular premature beat
  • V: Premature ventricular contraction
  • F: Fusion of ventricular and normal beat
  • Q: Unclassifiable beat
  • M: myocardial infarction

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
0.0476 1.0 697 0.0000 1.0

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0