심층신경망 (실습)

NN 모델 정의

퍼셉트론

import torch

torch.manual_seed(777)

x=torch.FloatTensor([0,0],[0,1],[1,0],[1,1]])
y=torch.FloatTensor([[0],[1],[1],[0]])

# NN모델 정의
#layer 정의
linear=torch.nn.Linear(2,1,bias=True)
sigmoid=torch.nn.Sigmoid()

model=torch.nn.Sequential(linear,sigmoid)

#모델 학습환경 설정
loss=torch.nn.BCEloss()
optimizer=torch.optim.SGD(model.parameters(),lr=1)

for stop in range(10000):
#그래디언트 초기화
optimizer.zero_grad()
#Forward계산
hypothesis=model(x)
#Error 계산
cost= loss(hypothesis,Y)
#backward 계산
cost.backward()
#가중치 계산 optimizer.step()
if stop%100==0:
print(stop,cost.item())


#w,b 평가
 with torch.no_grad():
 hypothsis=model(x)
 predicted=(hyporhesis>0.5).float()
 accuracy=(predicted==Y).float().mean()
print('\n Hypothesis: ', hypothesis.numpy(), '\n Correct: ', predicted.numpy(), '\n Accuracy: ', accuracy.item())

 

 

NN 모델 정의

NN모델

import torch

torch.manual_seed(777)

x=torch.FloatTensor([0,0],[0,1],[1,0],[1,1]])
y=torch.FloatTensor([[0],[1],[1],[0]])

# NN모델 정의
#layer 정의
linear1=torch.nn.Linear(2,2,bias=True)
linear2=torch.nn.Linear(2,1,bias=True)
sigmoid=torch.nn.Sigmoid()

model=torch.nn.Sequential(linear1,sigmoid,linear2,sigmoid)

#모델 학습환경 설정
loss=torch.nn.BCEloss()
optimizer=torch.optim.SGD(model.parameters(),lr=1)

for stop in range(10000):
#그래디언트 초기화
optimizer.zero_grad()
#Forward계산
hypothesis=model(x)
#Error 계산
cost= loss(hypothesis,Y)
#backward 계산
cost.backward()
#가중치 계산 optimizer.step()
if stop%100==0:
print(stop,cost.item())


#w,b 평가
 with torch.no_grad():
 hypothsis=model(x)
 predicted=(hyporhesis>0.5).float()
 accuracy=(predicted==Y).float().mean()
print('\n Hypothesis: ', hypothesis.numpy(), '\n Correct: ', predicted.numpy(), '\n Accuracy: ', accuracy.item())

 

 

NN 모델 정의

• 더 깊고, 넓게 만들기
  • 깊게 => 은닉층 늘리기
  • 넓게 => feature 수 늘리기

import torch

torch.manual_seed(777)

x=torch.FloatTensor([0,0],[0,1],[1,0],[1,1]])
y=torch.FloatTensor([[0],[1],[1],[0]])

# NN모델 정의
#layer 정의
linear1=torch.nn.Linear(2,10,bias=True)
linear2=torch.nn.Linear(10,10,bias=True)
linear3=torch.nn.Linear(10,10,bias=True)
linear4=torch.nn.Linear(10,1,bias=True)
sigmoid=torch.nn.Sigmoid()

model=torch.nn.Sequential(linear1,sigmoid,linear2,sigmoid,linear3,sigmoid,linear4,sigmoid)

#모델 학습환경 설정
loss=torch.nn.BCEloss()
optimizer=torch.optim.SGD(model.parameters(),lr=1)

for stop in range(10000):
#그래디언트 초기화
optimizer.zero_grad()
#Forward계산
hypothesis=model(x)
#Error 계산
cost= loss(hypothesis,Y)
#backward 계산
cost.backward()
#가중치 계산 optimizer.step()
if stop%100==0:
print(stop,cost.item())


#w,b 평가
 with torch.no_grad():
 hypothsis=model(x)
 predicted=(hyporhesis>0.5).float()
 accuracy=(predicted==Y).float().mean()
print('\n Hypothesis: ', hypothesis.numpy(), '\n Correct: ', predicted.numpy(), '\n Accuracy: ', accuracy.item())