aFewThings

/*
 *  This example code is made for describe how to convert OpenCV's Mat class to Boost Numpy's ndarray class and vice versa.
 *  As far as I know, there was some library or boilerplate code about converting Mat to ndarray. But to me those methods were too expensive and difficult to understand.
 *  Recently, I have found that Boost Python has Numpy extension and it gives ndarray class properly.
 *  No other modules are used for conversion, only Boost Python, Boost Numpy, and OpenCV. (Version : Windows7, Python3.5, BoostPython 1.68, OpenCV 4.0.0)
 *  This code is designed to show you a specific case like converting 'CV_8UC3' type Mat image to 'uint8' dtype ndarray. And it contains a minimum of code to explain.
 *  I hope you get the idea of converting ndarray to fit your case properly through this example.
 */

#define BOOST_PYTHON_STATIC_LIB

aFewThings

import librosa

import matplotlib.pyplot as plt
import torch
from torchaudio.transforms import MelSpectrogram

n_fft = 2048
win_len = None
hop_len = 512
n_mels = 128

aFewThings

#!/bin/bash

### steps ####
# verify the system has a cuda-capable gpu
# download and install the nvidia cuda toolkit and cudnn
# setup environmental variables
# verify the installation
###

### to verify your gpu is cuda enable check