我正在建立一个CNN,以便对EMNIST数据集进行图像分类。
为此,我具有以下数据集:
import scipy .io
emnist = scipy.io.loadmat(DIRECTORY + '/emnist-letters.mat')
data = emnist ['dataset']
X_train = data ['train'][0, 0]['images'][0, 0]
X_train = X_train.reshape((-1,28,28), order='F')
y_train = data ['train'][0, 0]['labels'][0, 0]
X_test = data ['test'][0, 0]['images'][0, 0]
X_test = X_test.reshape((-1,28,28), order = 'F')
y_test = data ['test'][0, 0]['labels'][0, 0]
形状:
请注意,图片是灰度的,因此颜色仅用一个数字表示。
我准备如下:
train_dataset = torch.utils.data.TensorDataset(torch.from_numpy(X_train), torch.from_numpy(y_train))
test_dataset = torch.utils.data.TensorDataset(torch.from_numpy(X_test), torch.from_numpy(y_test))
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
我的模型如下:
class CNNModel(nn.Module):
def __init__(self):
super(CNNModel, self).__init__()
self.cnn_layers = Sequential(
# Defining a 2D convolution layer
Conv2d(1, 4, kernel_size=3, stride=1, padding=1),
BatchNorm2d(4),
ReLU(inplace=True),
MaxPool2d(kernel_size=2, stride=2),
# Defining another 2D convolution layer
Conv2d(4, 4, kernel_size=3, stride=1, padding=1),
BatchNorm2d(4),
ReLU(inplace=True),
MaxPool2d(kernel_size=2, stride=2),
)
self.linear_layers = Sequential(
Linear(4 * 7 * 7, 10)
)
# Defining the forward pass
def forward(self, x):
x = self.cnn_layers(x)
x = x.view(x.size(0), -1)
x = self.linear_layers(x)
return x
model = CNNModel()
下面的代码是我用来训练模型的代码的一部分:
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = Variable(images)
labels = Variable(labels)
# Forward pass to get output/logits
outputs = model(images)
但是,通过执行我的代码,我得到了以下错误:
RuntimeError: Expected 4-dimensional input for 4-dimensional weight [4, 1, 3, 3], but got 3-dimensional input of size [100, 28, 28] instead
因此,当我输入3D时,需要输入4D。我应该怎么做才能得到3D模型而不是4D模型?
Here提出了类似的问题,但是我看不到如何将其转换为我的代码
答案 0 :(得分:1)
卷积期望输入的大小为 [batch_size,通道,高度,宽度] ,但是您的图像的大小为 [batch_size,高度,宽度] ,< em> channel 维度丢失。灰度用单个通道表示,您已将第一个卷积的in_channels
正确设置为1,但是图像没有匹配的尺寸。
您可以使用torch.unsqueeze
轻松添加奇异尺寸。
另外,请不要使用Variable
,它已被2年前发布的PyTorch 0.4.0弃用,其所有功能已合并到张量中。
for i, (images, labels) in enumerate(train_loader):
# Add a single channel dimension
# From: [batch_size, height, width]
# To: [batch_size, 1, height, width]
images = images.unsqueeze(1)
# Forward pass to get output/logits
outputs = model(images)