{ "id": 326751, "title": " πŸ“’ Lot of sounds 🎢 - My approach - 3 MonthπŸš€ ", "url": "/competitions/birdclef-2022/discussion/326751", "author_name": "", "post_date": "2022-05-24T05:46:54.914874800Z", "votes": 6, "comment_count": 1, "views": 0, "content": "

Hello folks! This is my first competition in audio data lot of experience (3month)

\n

πŸ“’ Learning approach:

\n
\n

πŸ“’ First-month approach : https://www.kaggle.com/code/venkatkumar001/birdclef22-preprocessing-lstm-cnn

\n
\n
    \n
  1. Basics & Terminology
    2. \n
  2. Build model (Using TensorFlow) - LSTM, RNN
    3. \n
\n
\n

πŸ“’ Second-month approach: https://www.kaggle.com/code/venkatkumar001/audio-starter-almost-all-basic-concepts

\n
\n

I participated in another competition same audio data (Music classification data), This competition teaches more about audio data and a new fast.ai framework initiated by one of my friend @dienhoa

\n

And also I secure the Top 40% in this music competition

\n
\n

πŸ“’ Third-month approach : Back to this competition

\n
\n

This time i was augmented the audio data and get image 128*128 and build the model get predict output

\n

This time I was trying fast.ai and PytorchLighting @jirkaborovec the best deep learning framework approaches

\n

Competition ends! Audio data !😍

\n

Thanks for Introduce new frameworks @jirkaborovec & @dienhoa, Valerio youtube video series πŸ€πŸ‘ŒπŸ˜

", "messages": [ { "id": "1799589", "postDate": "05/24/2022 05:46:54", "content": "

Hello folks! This is my first competition in audio data lot of experience (3month)

\n

πŸ“’ Learning approach:

\n
\n

πŸ“’ First-month approach : https://www.kaggle.com/code/venkatkumar001/birdclef22-preprocessing-lstm-cnn

\n
\n
    \n
  1. Basics & Terminology
    2. \n
  2. Build model (Using TensorFlow) - LSTM, RNN
    3. \n
\n
\n

πŸ“’ Second-month approach: https://www.kaggle.com/code/venkatkumar001/audio-starter-almost-all-basic-concepts

\n
\n

I participated in another competition same audio data (Music classification data), This competition teaches more about audio data and a new fast.ai framework initiated by one of my friend @dienhoa

\n

And also I secure the Top 40% in this music competition

\n
\n

πŸ“’ Third-month approach : Back to this competition

\n
\n

This time i was augmented the audio data and get image 128*128 and build the model get predict output

\n

This time I was trying fast.ai and PytorchLighting @jirkaborovec the best deep learning framework approaches

\n

Competition ends! Audio data !😍

\n

Thanks for Introduce new frameworks @jirkaborovec & @dienhoa, Valerio youtube video series πŸ€πŸ‘ŒπŸ˜

", "rawMarkdown": "Hello folks! This is my first competition in audio data lot of experience (3month)\n\n πŸ“’ Learning approach: \n\n> πŸ“’ First-month approach : https://www.kaggle.com/code/venkatkumar001/birdclef22-preprocessing-lstm-cnn\n\n1. Basics & Terminology \n2. Build model (Using TensorFlow) - LSTM, RNN\n\n> πŸ“’ Second-month approach: https://www.kaggle.com/code/venkatkumar001/audio-starter-almost-all-basic-concepts\n\nI participated in another competition same audio data (Music classification data), This competition teaches more about audio data and a new fast.ai framework initiated by one of my friend @dienhoa \n\nAnd also I secure the Top 40% in this music competition \n\n> πŸ“’ Third-month approach : Back to this competition\n\nThis time i was augmented the audio data and get image 128*128 and build the model get predict output\n\nThis time I was trying fast.ai and PytorchLighting @jirkaborovec the best deep learning framework approaches\n\nCompetition ends! Audio data !😍\n\nThanks for Introduce new frameworks @jirkaborovec & @dienhoa, Valerio youtube video series πŸ€πŸ‘ŒπŸ˜", "votes": null }, { "id": "1799693", "postDate": "05/24/2022 07:46:07", "content": "

Cool, hope you like it! πŸ”₯

", "rawMarkdown": "Cool, hope you like it! πŸ”₯", "votes": null } ], "comments": [ { "id": 1799693, "author_name": "jirkaborovec", "author_url": "", "post_date": "05/24/2022 07:46:07", "content": "

Cool, hope you like it! πŸ”₯

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1799589": "Hello folks! This is my first competition in audio data lot of experience (3month)\n\n πŸ“’ Learning approach: \n\n> πŸ“’ First-month approach : https://www.kaggle.com/code/venkatkumar001/birdclef22-preprocessing-lstm-cnn\n\n1. Basics & Terminology \n2. Build model (Using TensorFlow) - LSTM, RNN\n\n> πŸ“’ Second-month approach: https://www.kaggle.com/code/venkatkumar001/audio-starter-almost-all-basic-concepts\n\nI participated in another competition same audio data (Music classification data), This competition teaches more about audio data and a new fast.ai framework initiated by one of my friend @dienhoa \n\nAnd also I secure the Top 40% in this music competition \n\n> πŸ“’ Third-month approach : Back to this competition\n\nThis time i was augmented the audio data and get image 128*128 and build the model get predict output\n\nThis time I was trying fast.ai and PytorchLighting @jirkaborovec the best deep learning framework approaches\n\nCompetition ends! Audio data !😍\n\nThanks for Introduce new frameworks @jirkaborovec & @dienhoa, Valerio youtube video series πŸ€πŸ‘ŒπŸ˜", "1799693": "Cool, hope you like it! πŸ”₯" }, "source": "meta" }