def initialize_param(self):
sd = math.sqrt(1.0 / self.shape[0])
self.param = tfg.Variable(tff.get_truncated_normal(shape=self.shape,
mean=self.mean,
sd=sd,
low=-sd,
upp=sd), name=self.name)
def initialize_param(self):
self.param = tfg.Variable(tff.get_truncated_normal(shape=self.shape,
mean=self.mean,
sd=self.sd,
low=self.low,
upp=self.upp),
name=self.name)
def initialize_param(self):
init_range = np.sqrt(6.0 / (self.shape[0] + self.shape[1]))
self.param = tfg.Variable(
(init_range -
(-init_range) * np.random.random_sample(size=self.shape) +
(-init_range)),
name=self.name)
def initialize_param(self):
if len(self.shape) == 2:
sd = math.sqrt(2.0 / (self.shape[0] + self.shape[1]))
else:
sd = math.sqrt(2.0 / self.shape[0])
self.param = tfg.Variable(np.random.uniform(low=-sd,
high=sd,
size=self.shape), name=self.name)
def initialize_param(self):
sd = math.sqrt(2.0 / (self.shape[1] * self.shape[2] * self.shape[3]))
self.param = tfg.Variable(tff.get_truncated_normal(shape=self.shape,
mean=0.0,
sd=sd,
low=-sd,
upp=sd),
name=self.name)
def initialize_param(self):
if len(self.shape) == 2:
sd = math.sqrt(4.0 / (self.shape[0] + self.shape[1]))
else:
sd = math.sqrt(2.0 / self.shape[0])
self.param = tfg.Variable(np.random.normal(loc=0.0,
scale=sd,
size=self.shape),
name=self.name)
def initialize_param(self):
if len(self.shape) == 2:
sd = math.sqrt(2.0 / (self.shape[0] + self.shape[1]))
else:
sd = math.sqrt(2.0 / self.shape[0])
self.param = tfg.Variable(tff.get_truncated_normal(shape=self.shape,
mean=self.mean,
sd=sd,
low=-sd,
upp=sd), name=self.name)
def initialize_param(self):
self.param = tfg.Variable(np.random.random(size=self.shape),
name=self.name)
def initialize_param(self):
self.param = tfg.Variable(np.random.normal(loc=self.mean,
scale=self.sd,
size=self.shape),
name=self.name)
def initialize_param(self):
self.param = tfg.Variable(np.ones(shape=self.shape) * 0.1,
name=self.name)
def initialize_param(self):
self.param = tfg.Variable(np.random.randn(self.shape[0],
self.shape[1]),
name=self.name)
def initialize_param(self):
self.param = tfg.Variable(np.zeros(shape=self.shape), name=self.name)
def initialize_param(self):
self.param = tfg.Variable(self.value, name=self.name)
from tensorflux import graph as tfg
from tensorflux import session as tfs
import networkx as nx
import matplotlib.pyplot as plt
g = tfg.Graph()
g.initialize()
# Create variables
w = tfg.Variable(5.0, name="a")
b = tfg.Variable(-1.0, name="b")
# Create placeholder
x = tfg.Placeholder(name="x")
## Create hidden node y
#y = tfg.Matmul(A, x, name="y")
#
## Create output node z
#z = tfg.Add(y, b, name="z")
#nx.draw_networkx(g, with_labels=True)
#plt.show(block=True)
session = tfs.Session()
output = session.run(z, {x: 1.0})
output = session.run(z, {x: 2.0})
print(output)
def initialize_param(self):
#print (self.shape[0], self.shape[1] )
self.param = tfg.Variable(np.random.uniform(low=-1,
high=1,
size=self.shape),
name=self.name)
from tensorflux import graph as tfg
from tensorflux import session as tfs
import networkx as nx
import matplotlib.pyplot as plt
# g= graph.Graph()
g = tfg.Graph()
g.initialize()
# Create variables
a = tfg.Variable(5.0, name='a')
b = tfg.Variable(1.0, name='b')
# Create placeholder
x = tfg.Placeholder(name='x')
# Create hidden node y
y = tfg.Mul(a, x, name="y")
# Create output node z
z = tfg.Add(y, b, name="z")
#nx.draw_networkx(g, with_labels=True)
#plt.show(block=True)
session = tfs.Session()
output = session.run(z, {x: 1.0})
print(output)
print(z.input_nodes[0], z.input_nodes[1])
print(z.output)
# placeholder 생성
x = tfg.Placeholder(name = "X")
# Create hidden node y
y = tfg.Mul(a, x, name="y")
# Create output node z
z = tfg.Add(y, b, name="z") #z : operation
session = tfs.Session()
output = session.run(z, {x: 1.0})
print(output)
"""
# Create variables
A = tfg.Variable([[1, 0], [0, -1]], name="a")
b = tfg.Variable([1, 1], name="b")
# Create placeholder
x = tfg.Placeholder(name="x")
# Create hidden node y
y = tfg.Matmul(A, x, name="y") #a, x, b가 행렬이기 때문에 mul이 아니라 matmul
# Create output node z
z = tfg.Add(y, b, name="z")
nx.draw_networkx(g, with_labels=True)
plt.show(block=True)
session = tfs.Session()
from tensorflux import graph as tfg # graph 모듈을 객체화
from tensorflux import session as tfs
import networkx as nx
import matplotlib.pyplot as plt
g = tfg.Graph()
g.initialize()
#--------------
# Create variables
a = tfg.Variable(5.0, name="a")
b = tfg.Variable(1.0, name="b")
# Create placeholder
x = tfg.Placeholder(name="x")
# Create hidden node y
y = tfg.Mul(a, x, name="y")
# Create output node z
z = tfg.Add(y, b, name="z")
session = tfs.Session()
output = session.run(z, {x: 1.0}) # z:operation
print(output)
print()
print("-------------------")
#--------------
# Create variables
# Not scalar, list
A = tfg.Variable([[1, 0], [0, -1]], name="A")
import tensorflux.graph as tfg import tensorflux.session as tfs apple_price = 100 apple_num = 2 orange_price = 150 orange_num = 3 tax = 1.1 g = tfg.Graph() # Create variables a = tfg.Variable(apple_price, name="a") b = tfg.Variable(apple_num, name="b") c = tfg.Variable(orange_price, name="c") d = tfg.Variable(orange_num, name="d") e = tfg.Variable(tax, name="e") # Create Mul operation node f = tfg.Mul(a, b, name="f") g = tfg.Mul(c, d, name="g") # Create Add operation node h = tfg.Add(f, g, name="h") # Create Mul operation node i = tfg.Mul(h, e, name="i")
def initialize_param(self):
sd = math.sqrt(1.0 / self.shape[0])
self.param = tfg.Variable(np.random.uniform(low=-sd,
high=sd,
size=self.shape), name=self.name)
from tensorflux import graph as tfg
from tensorflux import session as tfs
#import networkx as nx
#import matplotlib.pyplot as plt
g = tfg.Graph() # 컴퓨테이션 그래프 클래스를 생성
#g.initialize() # 컴퓨테이션 그래프 클래스를 초기화
#"""
# Create variables
a = tfg.Variable(5.0, name="a") #변수 클래스 a를 생성하고 초기화
b = tfg.Variable(-1.0, name="b") #변수 클래스 b를 생성하고 초기화
# Create placeholder
x = tfg.Placeholder(name="x") #플레이스홀더는 이후 입력할 값으로 현재는 값까지는 초기화하지 않음
# Create hidden node y
y = tfg.Mul(a, x, name="y") #곱 연산 클래스를 생성
# Create output node z
z = tfg.Add(y, b, name="z") #합 연산 클래스를 생성
#nx.draw_networkx(g, with_labels=True)
#plt.show(block=True)
# 수행~~~~~~~~~~~~~~~~~~~~~~
session = tfs.Session()
output = session.run(z, {x: 1.0})
print(output)
output = session.run(z, {x: 2.0})
print(output)
import tensorflux.graph as tfg
import tensorflux.session as tfs
apple_price = 100
apple_num = 2
tax = 1.1
g = tfg.Graph()
# Create variables
a = tfg.Variable(apple_price, name="a")
b = tfg.Variable(apple_num, name="b")
c = tfg.Variable(tax, name="c")
# Create Mul operation node
d = tfg.Mul(a, b, name="d")
# Create Mul operation node
e = tfg.Mul(d, c, name="e")
session = tfs.Session()
# forward
total_apple_price = session.run(d, verbose=False)
print("total_apple_price: {:f}".format(float(total_apple_price)))
final_price = session.run(e, verbose=False)
print("final_price: {:f}".format(float(final_price)))
print()
#backward
d_in = 1