오디오 딥러닝 마스터 되기
김채현 | 박지현 | 김용희 |
---|---|---|
Date | Plan | Do | Note |
---|---|---|---|
22.12.04 | Intro | V | 계획 생성 |
22.12.11 | PyTorch | V | [PTM] 1장. 딥러닝과 파이토치 라이브러리 소개 [PTM] 2장. 사전 훈련된 신경망 [PTM] 3장. 텐서 구조체 |
22.12.18 | PyTorch | V | [PTM] 4장. 실제 데이터를 텐서로 표현하기 [PTM] 5장. 학습 기법 |
22.12.28 | PyTorch | V | [PTM] 6장. 신경망을 활용한 데이터 적합 [PTM] 7장. 새와 비행기 구별하기: 이미지 학습 |
23.01.04 | PyTorch | V | [PTM] 8장. 컨볼루션을 활용한 일반화 [PTM] 9장. 암과 싸워 이기기 위한 파이토치 활용 |
23.01.14 | PyTorch | V | [PTM] 10장. 여러 데이터 소스를 통합 데이터셋으로 합치기 [PTM] 11장. 종양 탐지를 위한 분류 모델 훈련 |
23.01.18 | PyTorch | V | [BC] Part-1 Basic ML |
23.01.25 | PyTorch | V | [BC] Part-2 DNN |
23.02.01 | PyTorch | V | [BC] Part-3 CNN |
23.02.08 | PyTorch | V | [BC] Part-4 RNN |
23.02.19 | DSP1 | V | 1. Overview 2. Sound and waveforms 3.Intensity, loudness, and timbre |
23.02.22 | DSP2 | V | 4. Understanding audio signals 5. Types of audio features for ML 6. How to extract audio features |
23.03.01 | DSP3 | V | 7. Time-domain audio features 8. Implemneting the amplitude envelope 9. RMS energy and zero-crossing rate |
23.03.08 | DSP4 | V | 10. Fourier Transform: The Intuition 11. Complex numbers for audio signal processing 12. Defining the Fourier transform using complex numbers |
23.03.18 | DSP5 | V | 13. Discrete Fourier Transform 14. Extracting Spectrograms from Audio with Python 15. Short-Time Fourier Transfom explained easily |
23.03.22 | DSP6 | V | 16. Extracting Explained Easily 17. Mel Spectrogram Explained Easily 18. Mel Spectrogram with Python |
23.03.29 | DSP7 | V | 19. MFCCs Explained Easily 20. Extracting MFCCs with Python 21. Frequency-Domain Audio Features 22. Implementing Band Energy Ratio from Scratch with Python 23. Spectral centroid and bandwidth |
23.04.05 | DeepLearningForAudio | V | 1. Course overview 2. Ai, machine learning and deep learning 3. Implementing an artificial neuron from scratch 4. Vector and matrix operations |
23.04.16 | DeepLearningForAudio | V | 5. Computation in NN 6. Implementing a NN from scratch 7. Backpropagation and Gradient Descent 8. Training a NN: Implementing back propagation from scratch |
23.04.23 | DeepLearningForAudio | V | 9. How to implement a simple NN with TF 10. Understanding audio data for DL 11. Preprocessing audio data for DL 12. Music genre classification: Prepararing the dataset |
23.04.30 | DeepLearningForAudio | V | 13. Implementing a NN for music genre classification 14. Solving overfitting in NN 15. How does a CNN |
23.05.07 | DeepLearningForAudio | V | 15. How does a CNN 16. How to implement a CNN for music genre classification 17. RNN |
23.05.14 | DeepLearningForAudio | V | 18. LSTM 19. How to implement an RNN-LSTM for music genre classification |
- [PyTorch] [파이토치 딥러닝 마스터]
git clone https://github.com/deep-learning-with-pytorch/dlwpt-code