Daisuke Niizumi's repositories
ml-sound-classifier
Machine Learning Sound Classifier
metric_learning
Metric Learning App Dev Resource
sound-clf-pytorch
Sound classifier tutorials/examples in PyTorch
protonet-fine-grained-clf
(Using) Prototypical Networks as a Fine Grained Classifier
freesound-audio-tagging-2019
Kaggle Freesound Audio Tagging 2019 Competition Solution
dcase2020_task2_variants
DCASE2020 Challenge Task 2 baseline variants
small_book_image_dataset
Small dataset of book images
pytorch_cnn_visualizations
Pytorch implementation of convolutional neural network visualization techniques
byol-pytorch
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
project-ml
Template for general machine learning project
pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
squeezedet-keras-plus
Keras implementation of the Squeeze Det Object Detection Deep Learning Framework
albumentations
fast image augmentation library and easy to use wrapper around other libraries
BYOL
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
DeepAnomalyDetection_benchmark
Benchmark for DeepLearning anomaly detection
EntropyPenalty
This repo provides code used in the paper "Entropy Penalty: Towards Generalization Beyond the IID Assumption" (https://arxiv.org/abs/1910.00164):
mlflow-docker-compose
Deploy mlflow with docker-compose
s3prl
Self-Supervised Speech/Sound Pre-training and Representation Learning Toolkit