![](/img/trans.png)
[英]RuntimeError: size mismatch, m1: [5 x 10], m2: [5 x 32] at /pytorch/aten/src/TH/generic/THTensorMath.cpp
[英]RuntimeError: size mismatch, m1: [32 x 1], m2: [32 x 9]
我正在構建一個 CNN 並對其進行字母 A 到 I(9 類)的手勢分類訓練,每個圖像都是 224x224 大小的 RGB。
不確定我需要轉置哪個矩陣以及如何轉置。 我已經設法匹配層的輸入和輸出,但是矩陣乘法的事情,不太確定如何解決它。
class LargeNet(nn.Module):
def __init__(self):
super(LargeNet, self).__init__()
self.name = "large"
self.conv1 = nn.Conv2d(3, 5, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(5, 10, 5)
self.fc1 = nn.Linear(10 * 53 * 53, 32)
self.fc2 = nn.Linear(32, 9)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
print('x1')
x = self.pool(F.relu(self.conv2(x)))
print('x2')
x = x.view(-1, 10*53*53)
print('x3')
x = F.relu(self.fc1(x))
print('x4')
x = x.view(-1, 1)
x = self.fc2(x)
print('x5')
x = x.squeeze(1) # Flatten to [batch_size]
return x
和培訓代碼
#Loss and optimizer
criterion = nn.BCEWithLogitsLoss()
optimizer = optim.SGD(model2.parameters(), lr=learning_rate, momentum=0.9)
# Train the model
total_step = len(train_loader)
loss_list = []
acc_list = []
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
print(i,images.size(),labels.size())
# Run the forward pass
outputs = model2(images)
labels=labels.unsqueeze(1)
labels=labels.float()
loss = criterion(outputs, labels)
代碼打印到 x4,然后我收到此錯誤 RuntimeError: size mismatch, m1: [32 x 1], m2: [32 x 9] at C:\w\1\s\tmp_conda_3.7_055457\conda\conda- bld\pytorch_1565416617654\work\aten\src\TH/generic/THTensorMath.cpp:752
完整的回溯錯誤: https://ibb.co/ykqy5wM
在您的forward
function 中不需要x=x.view(-1,1)
和x = x.squeeze(1)
。 刪除這兩行。 您的 output 形狀將是(batch_size, 9)
。
此外,您需要將labels
轉換為單熱編碼,其形狀為(batch_size, 9)
。
class LargeNet(nn.Module):
def __init__(self):
super(LargeNet, self).__init__()
self.name = "large"
self.conv1 = nn.Conv2d(3, 5, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(5, 10, 5)
self.fc1 = nn.Linear(10 * 53 * 53, 32)
self.fc2 = nn.Linear(32, 9)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 10*53*53)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return x
model2 = LargeNet()
#Loss and optimizer
criterion = nn.BCEWithLogitsLoss()
# nn.BCELoss()
optimizer = optim.SGD(model2.parameters(), lr=0.1, momentum=0.9)
images = torch.from_numpy(np.random.randn(2,3,224,224)).float() # fake images, batch_size is 2
labels = torch.tensor([1,2]).long() # fake labels
outputs = model2(images)
one_hot_labels = torch.eye(9)[labels]
loss = criterion(outputs, one_hot_labels)
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.