pytorch CNN 模型中的 BatchNorm2d 错误
error in BatchNorm2d in pytorch CNN model
我的数据库有大小为 128 * 128* 1 的灰度图像,每个批处理大小 =10
我正在使用 cnn 模型,但我在 BatchNorm2d
中遇到了这个错误
预期的 4D 输入(得到 2D 输入)
我发布了我用来转换图像的方式(灰度 - 张量 - 归一化)并将其分成批次
data_transforms = {
'train': transforms.Compose([
transforms.Grayscale(num_output_channels=1),
transforms.Resize(128),
transforms.CenterCrop(128),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5])
]),
'val': transforms.Compose([
transforms.Grayscale(num_output_channels=1),
transforms.Resize(128),
transforms.CenterCrop(128),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5])
]),
}
data_dir = '/content/drive/My Drive/Colab Notebooks/pytorch'
dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])
for x in ['train', 'val']}
dset_loaders = {x: torch.utils.data.DataLoader(dsets[x], batch_size=10,
shuffle=True, num_workers=25)
for x in ['train', 'val']}
dset_sizes = {x: len(dsets[x]) for x in ['train', 'val']}
dset_classes = dsets['train'].classes
我用过这个模型
class HeartNet(nn.Module):
def __init__(self, num_classes=7):
super(HeartNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(1, 64, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(64),
nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(64),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(128),
nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(128),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(256),
nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(256),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.classifier = nn.Sequential(
nn.Dropout(0.5),
nn.Linear(16*16*256, 2048),
nn.ELU(inplace=True),
nn.BatchNorm2d(2048),
nn.Linear(2048, num_classes)
)
nn.init.xavier_uniform_(self.classifier[1].weight)
nn.init.xavier_uniform_(self.classifier[4].weight)
def forward(self, x):
x = self.features(x)
x = x.view(x.size(0), 16 * 16 * 256)
x = self.classifier(x)
return x
我该如何解决这个问题?
您的 self.classifier
子网络中的批量规范层有问题:虽然您的 self.features
子网络是完全卷积的并且需要 BatchNorm2d
,但 self.classifier
sub 网络是一个全连接的多层感知器 (MLP) 网络,本质上是一维的。请注意 forward
函数如何在将特征图 x
提供给分类器之前从特征图中移除空间维度。
尝试将 self.classifier
中的 BatchNorm2d
替换为 BatchNorm1d
。
我的数据库有大小为 128 * 128* 1 的灰度图像,每个批处理大小 =10
我正在使用 cnn 模型,但我在 BatchNorm2d
中遇到了这个错误
预期的 4D 输入(得到 2D 输入)
我发布了我用来转换图像的方式(灰度 - 张量 - 归一化)并将其分成批次
data_transforms = {
'train': transforms.Compose([
transforms.Grayscale(num_output_channels=1),
transforms.Resize(128),
transforms.CenterCrop(128),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5])
]),
'val': transforms.Compose([
transforms.Grayscale(num_output_channels=1),
transforms.Resize(128),
transforms.CenterCrop(128),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5])
]),
}
data_dir = '/content/drive/My Drive/Colab Notebooks/pytorch'
dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])
for x in ['train', 'val']}
dset_loaders = {x: torch.utils.data.DataLoader(dsets[x], batch_size=10,
shuffle=True, num_workers=25)
for x in ['train', 'val']}
dset_sizes = {x: len(dsets[x]) for x in ['train', 'val']}
dset_classes = dsets['train'].classes
我用过这个模型
class HeartNet(nn.Module):
def __init__(self, num_classes=7):
super(HeartNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(1, 64, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(64),
nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(64),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(128),
nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(128),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(256),
nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),
nn.ELU(inplace=True),
nn.BatchNorm2d(256),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.classifier = nn.Sequential(
nn.Dropout(0.5),
nn.Linear(16*16*256, 2048),
nn.ELU(inplace=True),
nn.BatchNorm2d(2048),
nn.Linear(2048, num_classes)
)
nn.init.xavier_uniform_(self.classifier[1].weight)
nn.init.xavier_uniform_(self.classifier[4].weight)
def forward(self, x):
x = self.features(x)
x = x.view(x.size(0), 16 * 16 * 256)
x = self.classifier(x)
return x
我该如何解决这个问题?
您的 self.classifier
子网络中的批量规范层有问题:虽然您的 self.features
子网络是完全卷积的并且需要 BatchNorm2d
,但 self.classifier
sub 网络是一个全连接的多层感知器 (MLP) 网络,本质上是一维的。请注意 forward
函数如何在将特征图 x
提供给分类器之前从特征图中移除空间维度。
尝试将 self.classifier
中的 BatchNorm2d
替换为 BatchNorm1d
。