Displaying 1 to 8 from 8 results

DataAugmentationForObjectDetection - Data Augmentation For Object Detection

  •    Jupyter

We support a variety of data augmentations, like. A quick start tutorial can be found in the file quick-start.ipynb in this repo.

image_augmentor - Data augmentation tool for images

  •    Python

This is a simple data augmentation tool for image files, intended for use with machine learning data sets. The tool scans a directory containing image files, and generates new images by performing a specified set of augmentation operations on each file that it finds. This process multiplies the number of training examples that can be used when developing a neural network, and should significantly improve the resulting network's performance, particularly when the number of training examples is relatively small. The <image dir> argument should be the path to a directory containing the image files to be augmented. The utility will search the directory recursively for files with any of the following extensions: jpg, jpeg, bmp, png.

muda - A library for augmenting annotated audio data

  •    Python

A library for Musical Data Augmentation. muda package implements annotation-aware musical data augmentation, as described in the muda paper.

nlp-augment - A collection of utilities used in exploring data augmentation of low-resource parallel corpuses

  •    Python

A collection of utilities used in exploring data augmentation of low-resource parallel corpuses. My experiments suggest that augmenting only the source side of the parallel data with rare words is more beneficial.

zeroth - Kaldi-based Korean ASR (한국어 음성인식) open-source project

  •    Shell

Zeroth is an open source project for Korean speech recognition implemented using the Kaldi toolkit. This project was developed as part of Atlas’s (https://www.goodatlas.com) Language AI platform, which enables enterprises to add intelligence to their B2C communications.

MobilePose-pytorch - Single Person Pose Estimation for Mobile Device

  •    Jupyter

MobilePose is a Tiny PyTorch implementation of single person 2D pose estimation framework. The aim is to provide the interface of the training/inference/evaluation, and the dataloader with various data augmentation options. And final trained model can satisfy basic requirements(speed+size+accuracy) for mobile device. Some codes for mobilenetV2 and display are brought from pytorch-mobilenet-v2 and tf-pose-estimation. Thanks to the original authors.

DeepConvSep - Deep Convolutional Neural Networks for Musical Source Separation

  •    Python

This repository contains classes for data generation and preprocessing and feature computation, useful in training neural networks with large datasets that do not fit into memory. Additionally, you can find classes to query samples of instrument sounds from RWC instrument sound dataset. In the 'examples' folder you can find use cases for the classes above for the case of music source separation. We provide code for feature computation (STFT) and for training convolutional neural networks for music source separation: singing voice source separation with the dataset iKala dataset, for voice, bass, drums separation with DSD100 dataset, for bassoon, clarinet, saxophone, violin with Bach10 dataset. The later is a good example for training a neural network with instrument samples from the RWC instrument sound database RWC instrument sound dataset, when the original score is available.