pytorch 改变输入图像大小
pytorch change input image size
我是 pytorch 的新手，我正在学习教程，但是当我尝试修改代码以使用 64x64x3 图像而不是 32x32x3 图像时，我遇到了很多错误。这是教程中的代码：
import torch
from torch.utils.data import DataLoader
import torchvision
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Resize(32),
transforms.RandomCrop(32),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
batch_size = 4
trainset = ImageFolder("Train", transform=transform)
trainloader = DataLoader(trainset, shuffle=True, batch_size=batch_size, num_workers=0)
classes = ('Dog', 'Cat')
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(batch_size)))
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
print("training started")
from tqdm import tqdm
for epoch in range(5): # loop over the dataset multiple times
running_loss = 0.0
for i, data in tqdm(enumerate(trainloader, 0), desc=f"epoch: {epoch + 1}"):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if i % 2000 == 1999: # print every 2000 mini-batches
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0
print('Finished Training')
PATH = './net.pth'
torch.save(net.state_dict(), PATH)
如果我将“transforms.Resize(32)”和“transforms.RandomCrop(32)”更改为 64（以获得 64x64x3 图像），我会收到此错误
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
~\Documents\pyth\classifier\train_classifier.py in <module>
86
87 # forward + backward + optimize
---> 88 outputs = net(inputs)
89 loss = criterion(outputs, labels)
90 loss.backward()
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
~\Documents\pyth\classifier\train_classifier.py in forward(self, x)
57 x = self.pool(F.relu(self.conv1(x)))
58 x = self.pool(F.relu(self.conv2(x)))
---> 59 x = x.view(-1, 10816+1)
60 x = F.relu(self.fc1(x))
61 x = F.relu(self.fc2(x))
RuntimeError: shape '[-1, 10817]' is invalid for input of size 10816
´´´
and if i try to change the parameters of ´x.view(...)´ i get this error
´´´
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
~\Documents\pyth\classifier\train_classifier.py in <module>
86
87 # forward + backward + optimize
---> 88 outputs = net(inputs)
89 loss = criterion(outputs, labels)
90 loss.backward()
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
~\Documents\pyth\classifier\train_classifier.py in forward(self, x)
58 x = self.pool(F.relu(self.conv2(x)))
59 x = x.view(-1, 16 * 2 * 5 * 5)
---> 60 x = F.relu(self.fc1(x))
61 x = F.relu(self.fc2(x))
62 x = self.fc3(x)
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
~\Anaconda3\lib\site-packages\torch\nn\modules\linear.py in forward(self, input)
92
93 def forward(self, input: Tensor) -> Tensor:
---> 94 return F.linear(input, self.weight, self.bias)
95
96 def extra_repr(self) -> str:
~\Anaconda3\lib\site-packages\torch\nn\functional.py in linear(input, weight, bias)
1751 if has_torch_function_variadic(input, weight):
1752 return handle_torch_function(linear, (input, weight), input, weight, bias=bias)
-> 1753 return torch._C._nn.linear(input, weight, bias)
1754
1755
RuntimeError: mat1 and mat2 shapes cannot be multiplied (2x800 and 400x120)
´´´
我认为这应该可行，因为在执行第二次池化操作后，输出特征图为 N x C x 13 x 13
self.fc1 = nn.Linear(16 * 13 * 13, 120)
x = x.view(-1, 16 * 13 * 13)
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 13 * 13, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 13 * 13)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
我是 pytorch 的新手，我正在学习教程，但是当我尝试修改代码以使用 64x64x3 图像而不是 32x32x3 图像时，我遇到了很多错误。这是教程中的代码：
import torch
from torch.utils.data import DataLoader
import torchvision
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Resize(32),
transforms.RandomCrop(32),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
batch_size = 4
trainset = ImageFolder("Train", transform=transform)
trainloader = DataLoader(trainset, shuffle=True, batch_size=batch_size, num_workers=0)
classes = ('Dog', 'Cat')
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(batch_size)))
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
print("training started")
from tqdm import tqdm
for epoch in range(5): # loop over the dataset multiple times
running_loss = 0.0
for i, data in tqdm(enumerate(trainloader, 0), desc=f"epoch: {epoch + 1}"):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if i % 2000 == 1999: # print every 2000 mini-batches
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0
print('Finished Training')
PATH = './net.pth'
torch.save(net.state_dict(), PATH)
如果我将“transforms.Resize(32)”和“transforms.RandomCrop(32)”更改为 64（以获得 64x64x3 图像），我会收到此错误
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
~\Documents\pyth\classifier\train_classifier.py in <module>
86
87 # forward + backward + optimize
---> 88 outputs = net(inputs)
89 loss = criterion(outputs, labels)
90 loss.backward()
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
~\Documents\pyth\classifier\train_classifier.py in forward(self, x)
57 x = self.pool(F.relu(self.conv1(x)))
58 x = self.pool(F.relu(self.conv2(x)))
---> 59 x = x.view(-1, 10816+1)
60 x = F.relu(self.fc1(x))
61 x = F.relu(self.fc2(x))
RuntimeError: shape '[-1, 10817]' is invalid for input of size 10816
´´´
and if i try to change the parameters of ´x.view(...)´ i get this error
´´´
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
~\Documents\pyth\classifier\train_classifier.py in <module>
86
87 # forward + backward + optimize
---> 88 outputs = net(inputs)
89 loss = criterion(outputs, labels)
90 loss.backward()
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
~\Documents\pyth\classifier\train_classifier.py in forward(self, x)
58 x = self.pool(F.relu(self.conv2(x)))
59 x = x.view(-1, 16 * 2 * 5 * 5)
---> 60 x = F.relu(self.fc1(x))
61 x = F.relu(self.fc2(x))
62 x = self.fc3(x)
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
~\Anaconda3\lib\site-packages\torch\nn\modules\linear.py in forward(self, input)
92
93 def forward(self, input: Tensor) -> Tensor:
---> 94 return F.linear(input, self.weight, self.bias)
95
96 def extra_repr(self) -> str:
~\Anaconda3\lib\site-packages\torch\nn\functional.py in linear(input, weight, bias)
1751 if has_torch_function_variadic(input, weight):
1752 return handle_torch_function(linear, (input, weight), input, weight, bias=bias)
-> 1753 return torch._C._nn.linear(input, weight, bias)
1754
1755
RuntimeError: mat1 and mat2 shapes cannot be multiplied (2x800 and 400x120)
´´´
我认为这应该可行，因为在执行第二次池化操作后，输出特征图为 N x C x 13 x 13
self.fc1 = nn.Linear(16 * 13 * 13, 120)
x = x.view(-1, 16 * 13 * 13)
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 13 * 13, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 13 * 13)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x