anas-rz/specmix-pytorch
A Mixed Sample Data Augmentation method for Training with Time-Frequency Domain Features
This tool helps scientists and engineers working with audio or sensor data improve the accuracy of their machine learning models. It takes existing sound or signal spectrograms and intelligently blends them to create new, diverse training examples. The end result is a more robust model that performs better even with limited initial data.
No commits in the last 6 months.
Use this if you are training a machine learning model on time-frequency data (like audio or sensor signals) and need to enhance your dataset's diversity to improve model performance.
Not ideal if your data is not in a time-frequency spectrogram format or if you are not using PyTorch for your machine learning training.
Stars
10
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 05, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/anas-rz/specmix-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)