왜 컨볼루셔널 인공신경망이 필요할까? (Why Convolutional Neural Network?)¶
- MNIST data
- Àΰø½Å°æ¸Á ¸¸À¸·Î ¾î´ÀÁ¤µµ ¼º´ÉÀÌ ³ª¿À´ÂÁö È®ÀÎÇغ¸ÀÚ
- 5.6 ±âº»ÀûÀÎ ÇÕ¼º°ö ½Å°æ¸Á ½Ç½ÀÀ» ¸ÕÀúº¸°í ÀÌ ÆÄÀÏÀ» º¸½Ã¸é µË´Ï´Ù.
In [1]:
# ÆÄÀÌÅäÄ¡ ¹× ÅäÄ¡ºñÁ¯ ¼³Ä¡
# ·±Å¸ÀÓÀ» GPU ¸ðµå·Î ¹Ù²ã¼ ½ÇÇàÇϼ¼¿ä
!pip install torch torchvision
In [0]:
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.init as init
import torchvision.datasets as dset
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
2) Set hyperparameters¶
In [0]:
batch_size = 256
learning_rate = 0.0002
num_epoch = 10
In [4]:
mnist_train = dset.MNIST("../", train=True, transform=transforms.ToTensor(), target_transform=None, download=True)
mnist_test = dset.MNIST("../", train=False, transform=transforms.ToTensor(), target_transform=None, download=True)
2) Check Dataset¶
In [5]:
print(mnist_train.__getitem__(0)[1], mnist_train.__len__())
mnist_test.__getitem__(0)[1], mnist_test.__len__()
Out[5]:
3) Set DataLoader¶
In [0]:
train_loader = torch.utils.data.DataLoader(mnist_train,batch_size=batch_size, shuffle=True,num_workers=2,drop_last=True)
test_loader = torch.utils.data.DataLoader(mnist_test,batch_size=batch_size, shuffle=False,num_workers=2,drop_last=True)
In [0]:
class Linear(nn.Module):
def __init__(self):
super(Linear,self).__init__()
self.layer = nn.Sequential(
nn.Linear(784,300),
nn.ReLU(),
nn.Linear(300,100),
nn.ReLU(),
nn.Linear(100,10),
nn.ReLU()
)
def forward(self,x):
out = x.view(batch_size,-1)
out = self.layer(out)
return out
2) Loss func & Optimizer¶
In [8]:
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
model = Linear().to(device)
loss_func = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
5. Train¶
In [9]:
loss_arr =[]
for i in range(num_epoch):
for j,[image,label] in enumerate(train_loader):
x = image.to(device)
y_= label.to(device)
optimizer.zero_grad()
output = model.forward(x)
loss = loss_func(output,y_)
loss.backward()
optimizer.step()
if j % 1000 == 0:
print(loss)
loss_arr.append(loss.cpu().detach().numpy())
In [0]:
#param_list = list(model.parameters())
#print(param_list)
5. Visualize Training Loss¶
In [10]:
plt.plot(loss_arr)
plt.show()
6. Test¶
In [11]:
correct = 0
total = 0
with torch.no_grad():
for image,label in test_loader:
x = image.to(device)
y_= label.to(device)
output = model.forward(x)
_,output_index = torch.max(output,1)
total += label.size(0)
correct += (output_index == y_).sum().float()
print("Accuracy of Test Data: {}".format(100*correct/total))
In [0]: