Mohammad Reza Taesiri taesiri

Tensorflow

System information

OS - High Sierra 10.13
Tensorflow - 1.4
Xcode command line tools - 8.2 (Download from here: Xcode - Support - Apple Developer & Switch to different clang version: sudo xcode-select --switch/Library/Developer/CommandLineTools & check version: clang -v)
Cmake - 3.7
Bazel - 0.7.0

https://github.com/aancel/admin/wiki/VirtualGL-on-Ubuntu

https://virtualgl.org/About/Introduction

https://www.turbovnc.org

VirtualGL

When you use ssh with X forwarding, you might have noticed that you cannot execute programs that require 3D acceleration. That's where VirtualGL comes into play.

(from https://www.scivision.co/numpy-image-bgr-to-rgb/)

Numpy / OpenCV image BGR to RGB

Conversion between any/all of BGR, RGB, and GBR may be necessary when working with Matplotlib expects M x N x 3 image, where last dimension is RGB.

OpenCV expects M x N x 3 image, where last dimension is BGR.

Scientific Cameras, some of which output an M X N x 3 image, where last dimension is GBR

	import matplotlib
	matplotlib.use('Agg')
	import matplotlib.pyplot as plt

	from numpy.random import rand
	from numpy import pi, arctan

	def cface(ax, x1,x2,x3,x4,x5,x6,x7,x8,x9,x10,x11,x12,x13,x14,x15,x16,x17,x18):
	# x1 = height of upper face
	# x2 = overlap of lower face

	try:
	import pyaudio
	import numpy as np
	import pylab
	import matplotlib.pyplot as plt
	from scipy.io import wavfile
	import time
	import sys
	import seaborn as sns
	except:

	import torch
	from torch.autograd import Variable
	import torch.nn as nn


	class Bottleneck(nn.Module):
	cardinality = 32 # the size of the set of transformations

	def __init__(self, nb_channels_in, nb_channels, nb_channels_out, stride=1):
	super().__init__()

	from keras import layers
	from keras import models
	import tensorflow as tf


	#
	# generator input params
	#

	rand_dim = (1, 1, 2048) # dimension of the generator's input tensor (gaussian noise)

	from keras import layers


	def residual_block(y, nb_channels, _strides=(1, 1), _project_shortcut=False):
	shortcut = y

	# down-sampling is performed with a stride of 2
	y = layers.Conv2D(nb_channels, kernel_size=(3, 3), strides=_strides, padding='same')(y)
	y = layers.BatchNormalization()(y)
	y = layers.LeakyReLU()(y)

	"""
	Clean and simple Keras implementation of network architectures described in:
	- (ResNet-50) [Deep Residual Learning for Image Recognition](https://arxiv.org/pdf/1512.03385.pdf).
	- (ResNeXt-50 32x4d) [Aggregated Residual Transformations for Deep Neural Networks](https://arxiv.org/pdf/1611.05431.pdf).

	Python 3.
	"""

	from keras import layers
	from keras import models