我有 (650, 650) 个带标签的灰度图像，并尝试构建 pytorch CNN 模型。
我认为快完成了，但低于错误。
RuntimeError: Given groups=1, weight of size [32, 1, 3, 3], expected input[1, 32, 650, 650] to have 1 channels, but got 32 channels instead 我的整个代码如下。
import numpy as np
import pandas as pd
import torch
import torchvision
from torchvision import transforms
from torchvision.datasets import ImageFolder
from sklearn.model_selection import train_test_split
from torch.utils.data import DataLoader, TensorDataset
import torch.nn.functional as F
import torch.nn as nn
df = pd.DataFrame({"Img" : [np.random.randint(0, 255, size=(650, 650))], "label":[[1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]}) # this is pseudo data. only shape and type is same.
df.Img=df.Img.apply(lambda x: x.astype(np.single))
X_train, X_test, y_train, y_test = train_test_split(df, df.label, test_size=0.2, random_state=1)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.25, random_state=1)
X = torch.tensor(X_train['Img'].tolist(), dtype=torch.float32)
y = torch.tensor(X_train['label'].tolist())
dataset = TensorDataset(X, y)
val_dataset = TensorDataset(torch.tensor(X_val['F_Img'].tolist()), torch.tensor(X_val['label'].tolist()))
batch_size=32
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)
val_dataloader = DataLoader(val_dataset, batch_size=batch_size, shuffle=False)
train_dl = dataloader
val_dl = val_dataloader
class ImageClassificationBase(nn.Module):
def training_step(self, batch):
images, labels = batch
out = self(images) # Generate predictions
loss = F.cross_entropy(out, labels) # Calculate loss
return loss
def validation_step(self, batch):
images, labels = batch
out = self(images) # Generate predictions
loss = F.cross_entropy(out, labels) # Calculate loss
acc = accuracy(out, labels) # Calculate accuracy
return {'val_loss': loss.detach(), 'val_acc': acc}
def validation_epoch_end(self, outputs):
batch_losses = [x['val_loss'] for x in outputs]
epoch_loss = torch.stack(batch_losses).mean() # Combine losses
batch_accs = [x['val_acc'] for x in outputs]
epoch_acc = torch.stack(batch_accs).mean() # Combine accuracies
return {'val_loss': epoch_loss.item(), 'val_acc': epoch_acc.item()}
def epoch_end(self, epoch, result):
print("Epoch [{}], train_loss: {:.4f}, val_loss: {:.4f}, val_acc: {:.4f}".format(
epoch, result['train_loss'], result['val_loss'], result['val_acc']))
class Net(ImageClassificationBase):
def __init__(self):
super().__init__()
self.network = nn.Sequential(
nn.Conv2d(in_channels=1, out_channels=32, kernel_size = 3, padding = 1),
nn.ReLU(),
nn.Conv2d(32,64, kernel_size = 3, stride = 1, padding = 1),
nn.ReLU(),
nn.MaxPool2d(2,2),
nn.Conv2d(64, 128, kernel_size = 3, stride = 1, padding = 1),
nn.ReLU(),
nn.Conv2d(128 ,128, kernel_size = 3, stride = 1, padding = 1),
nn.ReLU(),
nn.MaxPool2d(2,2),
nn.Conv2d(128, 256, kernel_size = 3, stride = 1, padding = 1),
nn.ReLU(),
nn.Conv2d(256,256, kernel_size = 3, stride = 1, padding = 1),
nn.ReLU(),
nn.MaxPool2d(2,2),
nn.Flatten(),
nn.Linear(6561,1024),
nn.ReLU(),
nn.Linear(1024, 512),
nn.ReLU(),
nn.Dropout(p=0.5),
nn.Linear(512,13)
)
def forward(self, xb):
return self.network(xb)
def accuracy(outputs, labels):
_, preds = torch.max(outputs, dim=1)
return torch.tensor(torch.sum(preds == labels).item() / len(preds))
@torch.no_grad()
def evaluate(model, val_loader):
model.eval()
outputs = [model.validation_step(batch) for batch in val_loader]
return model.validation_epoch_end(outputs)
def fit(epochs, lr, model, train_loader, val_loader, opt_func = torch.optim.SGD):
history = []
optimizer = opt_func(model.parameters(),lr)
for epoch in range(epochs):
model.train()
train_losses = []
for batch in train_loader:
loss = model.training_step(batch)
train_losses.append(loss)
loss.backward()
optimizer.step()
optimizer.zero_grad()
result = evaluate(model, val_loader)
result['train_loss'] = torch.stack(train_losses).mean().item()
model.epoch_end(epoch, result)
history.append(result)
return history
num_epochs = 30
opt_func = torch.optim.Adam
lr = 0.001
#fitting the model on training data and record the result after each epoch
device = 'cuda' if torch.cuda.is_available() else 'cpu'
model = Net().to(device)
model
history = fit(num_epochs, lr, model, train_dl, val_dl, opt_func)
# RuntimeError: Given groups=1, weight of size [32, 1, 3, 3], expected input[1, 32, 650, 650] to have 1 channels, but got 32 channels instead
我用谷歌搜索了一下，发现了一些类似的问题
运行时错误：给定组=1，权重大小为[64,32,3,3]，预期输入[128,64,32,32]有32个通道，但得到了64个通道
点是模型中的形状匹配，但即使我知道，我也找不到问题出在哪里。我感到羞耻......
您的模型期望输入的形状为
(bs, ch, h, w)(32, 1, 650, 650)(1, 32, 650, 650)发生这种情况的原因是您的图像具有形状
(650, 650)(bs, 650, 650)nn.Conv2d(1, bs, 650, 650)解决方案是在图像中添加单位轴：
np.random.randint(0, 255, size=(1, 650, 650))这将导致您的数据加载器输出具有形状
(bs, 1, 650, 650)