Music Segment Sequencing

Music Segment Sequencing with Triplet Network

Environment

• Python 3.7
• Pytorch 1.2.0
• Numpy 1.16.4
• Librosa 0.6.3
• Pydub 0.23.1
• Madmom 0.16.1
• Visdom 0.1.8.8

---

• You can replace the music segments in audio_data with your propose audio data.
• Run the code python train.py to train the model.
• Pre-trained model has been saved in runs folder.