HayatoTomita

snowyday

import math
from torch.optim import Optimizer

class Eve(Optimizer):
    """Implements Eve (Adam with feedback) algorithm.
    
    It has been proposed in `Improving Stochastic Gradient Descent with Feedback, `_.
    
    Arguments:
        params (iterable): iterable of parameters to optimize or dicts defining

jfsantos

using WAV

function inline_audioplayer(filepath)
  markup = """<audio controls="controls" {autoplay}>
              <source src="$filepath" />
              Your browser does not support the audio element.
              </audio>"""

  display(MIME("text/html") ,markup)
end

mmohiudd

<?php
use Facebook\FacebookSession;
use Facebook\FacebookRequest;
use Facebook\GraphUser;
use Facebook\FacebookRequestException;

FacebookSession::setDefaultApplication('YOUR_APP_ID','YOUR_APP_SECRET');

// Use one of the helper classes to get a FacebookSession object.
//   FacebookRedirectLoginHelper

tam17aki

import pyworld as pw
import pysptk
from scipy.io import wavfile
import numpy as np

fs, x = wavfile.read(pysptk.util.example_audio_file())
assert fs == 16000
wavfile.write('./orig.wav', fs, x)

# shortからfloatに変換します

davidaknowles

def pixel_shuffle_1d(x, upscale_factor):
    batch_size, channels, steps = x.size()
    channels //= upscale_factor
    input_view = x.contiguous().view(batch_size, channels, upscale_factor, steps)
    shuffle_out = input_view.permute(0, 1, 3, 2).contiguous()
    return shuffle_out.view(batch_size, channels, steps * upscale_factor)

xavierd

#include <clang-c/Index.h>
#include <cstdlib>
#include <iostream>

/*
 * Compile with:
 * g++ complete.cc -o complete -lclang -L/usr/lib/llvm
 * Run with:
 * LIBCLANG_TIMING=1 ./complete file.cc line column [clang args...]
 */

brannondorsey

Image-to-Image Translation with Conditional Adversarial Networks

Notes from arXiv:1611.07004v1 [cs.CV] 21 Nov 2016

• Euclidean distance between predicted and ground truth pixels is not a good method of judging similarity because it yields blurry images.
• GANs learn a loss function rather than using an existing one.
• GANs learn a loss that tries to classify if the output image is real or fake, while simultaneously training a generative model to minimize this loss.
• Conditional GANs (cGANs) learn a mapping from observed image x and random noise vector z to y: y = f(x, z)
• The generator G is trained to produce outputs that cannot be distinguished from "real" images by an adversarially trained discrimintor, D which is trained to do as well as possible at detecting the generator's "fakes".
• The discriminator D, learns to classify between real and synthesized pairs. The generator learns to fool the discriminator.
• Unlike an unconditional GAN, both th

taroushirani

#! /usr/bin/python

import argparse
import logging
from nnmnkwii.io import hts
from nnsvs.dsp import bandpass_filter
from nnsvs.gen import (
    gen_spsvs_static_features,
    gen_world_params,
    postprocess_duration,

gwtaylor

""" Theano CRBM implementation.

For details, see:
Taylor GW, Hinton GE, Roweis ST. Modeling Human Motion Using Binary Latent Variables. 
In: Advances in Neural Information Processing Systems 19. MIT Press; 2007. pp. 1345–1352.
Sample data:
https://uoguelphca-my.sharepoint.com/:u:/g/personal/gwtaylor_uoguelph_ca/EfJARkZuiX1JmwMKQxQqKJMBaMBUNOcF83FW_n9gk7OIbg?e=fnCjet
@author Graham Taylor"""

import numpy