Stars
Teaching material for the course "Deep Learning for Music Analysis and Generation" I taught at National Taiwan University
Official Implementation of "Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music" (ISMIR 2021)
JupyterLab computational environment.
Perform transfer learning for MIR using Jukebox!
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
List of automatic music tagging research articles that are evaluated against MagnaTagATune Dataset
A library for efficient similarity search and clustering of dense vectors.
An All-MLP solution for Vision, from Google AI
Crack LeetCode, not only how, but also why.
[ISMIR 2019] A Bi-Directional Transformer for Musical Chord Recognition
Official implementation of compound word transformer (AAAI'21)
LEAF is a learnable alternative to audio features such as mel-filterbanks, that can be initialized as an approximation of mel-filterbanks, and then be trained for the task at hand, while using a ve…
PyTorch package for the discrete VAE used for DALL·E.
Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"
Code for "Gradient Surgery for Multi-Task Learning"
Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"
The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR 2019].
Multi-Task Learning Framework on PyTorch. State-of-the-art methods are implemented to effectively train models on multiple tasks.
A multi-task learning example for the paper https://arxiv.org/abs/1705.07115
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Implementation of the paper "Attentive Statistics Pooling for Deep Speaker Embedding" in Pytorch
Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.
Python version of the Playwright testing and automation library.
Collection of audio-focused loss functions in PyTorch