| # This is shorthened version of blog post | |
| # http://ksopyla.com/2017/02/tensorflow-gpu-virtualenv-python3/ | |
| # update packages | |
| sudo apt-get update | |
| sudo apt-get upgrade | |
| #Add the ppa repo for NVIDIA graphics driver | |
| sudo add-apt-repository ppa:graphics-drivers/ppa | |
| sudo apt-get update |
| import tensorflow as tf | |
| from tensorflow.python.framework import ops | |
| import numpy as np | |
| # Define custom py_func which takes also a grad op as argument: | |
| def py_func(func, inp, Tout, stateful=True, name=None, grad=None): | |
| # Need to generate a unique name to avoid duplicates: | |
| rnd_name = 'PyFuncGrad' + str(np.random.randint(0, 1E+8)) | |
A comparison of Theano with other deep learning frameworks, highlighting a series of low-level design choices in no particular order.
Overview
Symbolic: Theano, CGT; Automatic: Torch, MXNet
Symbolic and automatic differentiation are often confused or used interchangeably, although their implementations are significantly different.
| #!/usr/bin/python | |
| import wave | |
| import numpy | |
| import struct | |
| import sys | |
| import csv | |
| from scikits.samplerate import resample | |
| def write_wav(data, filename, framerate, amplitude): |