{
  "id": 392802,
  "title": "KerasTuner for quick search of model hyperparameters",
  "url": "/competitions/asl-signs/discussion/392802",
  "author_name": "Andrij",
  "post_date": "2023-03-06T21:33:49.205000",
  "votes": 7,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hello Everyone! <br>\nBased on the public notebook and KerasTuner, I have prepared a basic pipeline for quickly finding model hyperparameters.<br>\nThe Keras Tuner is a library that helps you pick the optimal set of hyperparameters for your TensorFlow program. The process of selecting the right set of hyperparameters for your machine learning (ML) application is called hyperparameter tuning or hypertuning (<a href=\"https://www.tensorflow.org/tutorials/keras/keras_tuner)\" target=\"_blank\">https://www.tensorflow.org/tutorials/keras/keras_tuner)</a>.<br>\nHere is my basic notebook: <a href=\"https://www.kaggle.com/code/aikhmelnytskyy/gislr-tf-on-the-shoulders-kerastuner?scriptVersionId=121266581\" target=\"_blank\">https://www.kaggle.com/code/aikhmelnytskyy/gislr-tf-on-the-shoulders-kerastuner?scriptVersionId=121266581</a>.       In the notebook, so far, I only use the search based on the results of 10 epochs, on the one hand, this is too small for an effective search, and on the other hand, it allows you to quickly discard completely bad combinations.                                                                                                           Special thanks to the author of the original notebook.</p>",
  "messages": [
    {
      "id": 2171536,
      "postDate": "2023-03-06T21:33:49.207Z",
      "content": "<p>Hello Everyone! <br>\nBased on the public notebook and KerasTuner, I have prepared a basic pipeline for quickly finding model hyperparameters.<br>\nThe Keras Tuner is a library that helps you pick the optimal set of hyperparameters for your TensorFlow program. The process of selecting the right set of hyperparameters for your machine learning (ML) application is called hyperparameter tuning or hypertuning (<a href=\"https://www.tensorflow.org/tutorials/keras/keras_tuner)\" target=\"_blank\">https://www.tensorflow.org/tutorials/keras/keras_tuner)</a>.<br>\nHere is my basic notebook: <a href=\"https://www.kaggle.com/code/aikhmelnytskyy/gislr-tf-on-the-shoulders-kerastuner?scriptVersionId=121266581\" target=\"_blank\">https://www.kaggle.com/code/aikhmelnytskyy/gislr-tf-on-the-shoulders-kerastuner?scriptVersionId=121266581</a>.       In the notebook, so far, I only use the search based on the results of 10 epochs, on the one hand, this is too small for an effective search, and on the other hand, it allows you to quickly discard completely bad combinations.                                                                                                           Special thanks to the author of the original notebook.</p>",
      "rawMarkdown": "Hello Everyone! \nBased on the public notebook and KerasTuner, I have prepared a basic pipeline for quickly finding model hyperparameters.\nThe Keras Tuner is a library that helps you pick the optimal set of hyperparameters for your TensorFlow program. The process of selecting the right set of hyperparameters for your machine learning (ML) application is called hyperparameter tuning or hypertuning (https://www.tensorflow.org/tutorials/keras/keras_tuner).\nHere is my basic notebook: https://www.kaggle.com/code/aikhmelnytskyy/gislr-tf-on-the-shoulders-kerastuner?scriptVersionId=121266581.       In the notebook, so far, I only use the search based on the results of 10 epochs, on the one hand, this is too small for an effective search, and on the other hand, it allows you to quickly discard completely bad combinations.                                                                                                           Special thanks to the author of the original notebook.",
      "votes": 7
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2171536": "Hello Everyone! \nBased on the public notebook and KerasTuner, I have prepared a basic pipeline for quickly finding model hyperparameters.\nThe Keras Tuner is a library that helps you pick the optimal set of hyperparameters for your TensorFlow program. The process of selecting the right set of hyperparameters for your machine learning (ML) application is called hyperparameter tuning or hypertuning (https://www.tensorflow.org/tutorials/keras/keras_tuner).\nHere is my basic notebook: https://www.kaggle.com/code/aikhmelnytskyy/gislr-tf-on-the-shoulders-kerastuner?scriptVersionId=121266581.       In the notebook, so far, I only use the search based on the results of 10 epochs, on the one hand, this is too small for an effective search, and on the other hand, it allows you to quickly discard completely bad combinations.                                                                                                           Special thanks to the author of the original notebook."
  }
}