#!/usr/bin/env python
# coding: utf-8
# # 신경망 깊게 쌓아 컬러 데이터셋에 적용하기
# Convolutional Neural Network (CNN) 을 쌓아올려 딥한 러닝을 해봅시다.
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torchvision import transforms, datasets, models
USE_CUDA = torch.cuda.is_available()
DEVICE = torch.device("cuda" if USE_CUDA else "cpu")
# ## 하이퍼파라미터
EPOCHS = 40
BATCH_SIZE = 64
# ## 데이터셋 불러오기
train_loader = torch.utils.data.DataLoader(
datasets.CIFAR10('./.data',
train=True,
download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,),
(0.3081,))])),
batch_size=BATCH_SIZE, shuffle=True)
test_loader = torch.utils.data.DataLoader(
datasets.CIFAR10('./.data',
train=False,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,),
(0.3081,))])),
batch_size=BATCH_SIZE, shuffle=True)
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
x = F.relu(F.max_pool2d(self.conv1(x),2))
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
x = x.view(-1, 320)
x = F.relu(self.fc1(x))
x = F.dropout(x)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
model = CNN().to(DEVICE)
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
print(model)
def train(model, train_loader, optimizer, epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(DEVICE), target.to(DEVICE)
optimizer.zero_grad()
output = model(data)
loss = F.cross_entropy(output, target)
loss.backward()
optimizer.step()
if batch_idx % 200 == 0:
print('Train Epoch: {} [{}/{}({:.0f}%)]\tLoss: {:.6f}'.format(epoch, batch_dix * len(data),
len(train_loader.dataset),
100.*batch_idx / len(train_loader),
loss.item()))
def evaluate(model, test_loader):
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(DEVICE), target.to(DEVICE)
output = model(data)
# 배치 오차를 합산
test_loss += F.cross_entropy(output, target,
reduction='sum').item()
# 가장 높은 값을 가진 인덱스가 바로 예측값
pred = output.max(1, keepdim=True)[1]
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
test_accuracy = 100. * correct / len(test_loader.dataset)
return test_loss, test_accuracy
for epoch in range(1, EPOCHS + 1):
train(model, train_loader, optimizer, epoch)
test_loss, test_accuracy = evaluate(model, test_loader)
print('[{}] Test Loss: {:.4f}, Accuracy: {:.2f}%'.format(
epoch, test_loss, test_accuracy))
----------------------------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-3-c50570b052a0> in <module>
24
25 for epoch in range(1, EPOCHS + 1):
---> 26 train(model, train_loader, optimizer, epoch)
27 test_loss, test_accuracy = evaluate(model, test_loader)
28
<ipython-input-2-8034379e07ea> in train(model, train_loader, optimizer, epoch)
6 data, target = data.to(DEVICE), target.to(DEVICE)
7 optimizer.zero_grad()
----> 8 output = model(data)
9 loss = F.cross_entropy(output, target)
10 loss.backward()
~\anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
<ipython-input-1-fdc19dfe5bb3> in forward(self, x)
53
54 def forward(self, x):
---> 55 x = F.relu(F.max_pool2d(self.conv1(x),2))
56 x = F.relu(F.max_pool2d(self.conv2_drop(self.coPreformatted textnv2(x)), 2))
57 x = x.view(-1, 320)
~\anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~\anaconda3\lib\site-packages\torch\nn\modules\conv.py in forward(self, input)
421
422 def forward(self, input: Tensor) -> Tensor:
--> 423 return self._conv_forward(input, self.weight)
424
425 class Conv3d(_ConvNd):
~\anaconda3\lib\site-packages\torch\nn\modules\conv.py in _conv_forward(self, input, weight)
417 weight, self.bias, self.stride,
418 _pair(0), self.dilation, self.groups)
--> 419 return F.conv2d(input, weight, self.bias, self.stride,
420 self.padding, self.dilation, self.groups)
421
RuntimeError: Given groups=1, weight of size [10, 1, 5, 5], expected input[64, 3, 32, 32] to have 1 channels, but got 3 channels instead
The first conv layer in your model (conv1 = nn.Conv2d(1, 10, kernel_size=5)) expects an input tensor with a single channel, while you are passing a batch of 64 image tensors each with 3 channels.
You would either have to transform the CIFAR10 images to grayscale images or change the conv1 layer to accept 3 input channels.