Eder Santana EderSantana

This configuration worked for me, hope it helps

	import numpy as np
	from keras.layers import GRU, initializations, K
	from collections import OrderedDict

	class GRULN(GRU):
	'''Gated Recurrent Unit with Layer Normalization
	Current impelemtation only works with consume_less = 'gpu' which is already
	set.

	# Arguments

	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))

	# GL interoperability example, by Peter Berrington.
	# Draws a rotating teapot, using cuda to invert the RGB value
	# each frame

	from OpenGL.GL import *
	from OpenGL.GLUT import *
	from OpenGL.GLU import *
	from OpenGL.GL.ARB.vertex_buffer_object import *
	from OpenGL.GL.ARB.pixel_buffer_object import *

	"""
	Demonstrating CUDA JIT integration
	"""
	from __future__ import print_function
	from numba import cuda
	import numpy
	import os

	# Declare function to link to
	bar = cuda.declare_device('bar', 'int32(voidptr, int32)')

	'''
	A logistic regression example using the meta-graph checkpointing
	features of Tensorflow.

	Author: João Felipe Santos, based on code by Aymeric Damien
	(https://github.com/aymericdamien/TensorFlow-Examples/)
	'''

	from __future__ import print_function

	#!/usr/bin/env python
	"""
	A quick, partial implementation of ENet (https://arxiv.org/abs/1606.02147) using PyTorch.
	The original Torch ENet implementation can process a 480x360 image in ~12 ms (on a P2 AWS
	instance). TensorFlow takes ~35 ms. The PyTorch implementation takes ~25 ms, an improvement
	over TensorFlow, but worse than the original Torch.
	"""

	from __future__ import absolute_import

Hardware