Pytorch 预期输入批次大小（18）与目标批次大小（6）匹配

用于图像分类的RNN是否仅适用于灰度图像？ 以下程序适用于灰度图像分类

如果使用RGB图像，我有以下错误：

预期输入批次大小（18）与目标批次大小（6）匹配

在这一行

loss=标准（输出、标签）

我的列车数据加载、有效和测试如下

input_size  = 300
inputH = 300
inputW = 300

#Data transform (normalization & data augmentation)
stats = ((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
train_resize_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
                         tt.ToTensor(),
                         tt.Normalize(*stats)])

train_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
                         tt.RandomHorizontalFlip(),                                                  
                         tt.ToTensor(),
                         tt.Normalize(*stats)])
valid_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
                         tt.ToTensor(), 
                         tt.Normalize(*stats)])
test_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
                        tt.ToTensor(), 
                        tt.Normalize(*stats)])

#Create dataset
train_ds = ImageFolder('./data/train', train_tfms)
valid_ds = ImageFolder('./data/valid', valid_tfms)
test_ds = ImageFolder('./data/test', test_tfms)

from torch.utils.data.dataloader import DataLoader
batch_size = 6

#Training data loader
train_dl = DataLoader(train_ds, batch_size, shuffle = True, num_workers = 8, pin_memory=True)
#Validation data loader
valid_dl = DataLoader(valid_ds, batch_size, shuffle = True, num_workers = 8, pin_memory=True)
#Test data loader
test_dl = DataLoader(test_ds, 1, shuffle = False, num_workers = 1, pin_memory=True)

num_steps = 300
hidden_size = 256 #size of hidden layers
num_classes = 5
num_epochs = 20
learning_rate = 0.001
# Fully connected neural network with one hidden layer
num_layers = 2 # 2 RNN layers are stacked  
class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN, self).__init__()
        self.num_layers = num_layers
        self.hidden_size = hidden_size
        self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True, dropout=0.2)#batch must have first dimension
        #our inpyt needs to have shape
        #x -> (batch_size, seq, input_size)
        self.fc = nn.Linear(hidden_size, num_classes)#this fc is after RNN. So needs the last hidden size of RNN

    def forward(self, x):
        #according to ducumentation of RNN in pytorch
        #rnn needs input, h_0 for inputs at RNN (h_0 is initial hidden state)

        #the following one is initial hidden layer
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)#first one is number of layers and second one is batch size
        #output has two outputs. The first tensor contains the output features of the hidden last layer for all time steps
        #the second one is hidden state f
        out, _ = self.rnn(x, h0)
        #output has batch_size, num_steps, hidden size
        #we need to decode hidden state only the last time step
        #out (N, 30, 128)
        #Since we need only the last time step
        #Out (N, 128)
        out = out[:, -1, :] #-1 for last time step, take all for N and 128
        out = self.fc(out)
        return out


stacked_rnn_model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()#cross entropy has softmax at output
#optimizer = torch.optim.Adam(stacked_rnn_model.parameters(), lr=learning_rate) #optimizer used gradient optimization using Adam 
optimizer = torch.optim.SGD(stacked_rnn_model.parameters(), lr=learning_rate)
# Train the model
n_total_steps = len(train_dl)
    for epoch in range(num_epochs):
        t_losses=[]
        for i, (images, labels) in enumerate(train_dl):  
            # origin shape: [6, 3, 300, 300]
            # resized: [6, 300, 300]
            images = images.reshape(-1, num_steps, input_size).to(device)
            print('images shape')
            print(images.shape)
            labels = labels.to(device)
            
            # Forward pass
            outputs = stacked_rnn_model(images)
            print('outputs shape')
            print(outputs.shape)
            loss = criterion(outputs, labels)
            t_losses.append(loss)
            # Backward and optimize
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

我的模型如下

input_size  = 300
inputH = 300
inputW = 300

#Data transform (normalization & data augmentation)
stats = ((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
train_resize_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
                         tt.ToTensor(),
                         tt.Normalize(*stats)])

train_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
                         tt.RandomHorizontalFlip(),                                                  
                         tt.ToTensor(),
                         tt.Normalize(*stats)])
valid_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
                         tt.ToTensor(), 
                         tt.Normalize(*stats)])
test_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
                        tt.ToTensor(), 
                        tt.Normalize(*stats)])

#Create dataset
train_ds = ImageFolder('./data/train', train_tfms)
valid_ds = ImageFolder('./data/valid', valid_tfms)
test_ds = ImageFolder('./data/test', test_tfms)

from torch.utils.data.dataloader import DataLoader
batch_size = 6

#Training data loader
train_dl = DataLoader(train_ds, batch_size, shuffle = True, num_workers = 8, pin_memory=True)
#Validation data loader
valid_dl = DataLoader(valid_ds, batch_size, shuffle = True, num_workers = 8, pin_memory=True)
#Test data loader
test_dl = DataLoader(test_ds, 1, shuffle = False, num_workers = 1, pin_memory=True)

num_steps = 300
hidden_size = 256 #size of hidden layers
num_classes = 5
num_epochs = 20
learning_rate = 0.001
# Fully connected neural network with one hidden layer
num_layers = 2 # 2 RNN layers are stacked  
class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN, self).__init__()
        self.num_layers = num_layers
        self.hidden_size = hidden_size
        self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True, dropout=0.2)#batch must have first dimension
        #our inpyt needs to have shape
        #x -> (batch_size, seq, input_size)
        self.fc = nn.Linear(hidden_size, num_classes)#this fc is after RNN. So needs the last hidden size of RNN

    def forward(self, x):
        #according to ducumentation of RNN in pytorch
        #rnn needs input, h_0 for inputs at RNN (h_0 is initial hidden state)

        #the following one is initial hidden layer
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)#first one is number of layers and second one is batch size
        #output has two outputs. The first tensor contains the output features of the hidden last layer for all time steps
        #the second one is hidden state f
        out, _ = self.rnn(x, h0)
        #output has batch_size, num_steps, hidden size
        #we need to decode hidden state only the last time step
        #out (N, 30, 128)
        #Since we need only the last time step
        #Out (N, 128)
        out = out[:, -1, :] #-1 for last time step, take all for N and 128
        out = self.fc(out)
        return out


stacked_rnn_model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()#cross entropy has softmax at output
#optimizer = torch.optim.Adam(stacked_rnn_model.parameters(), lr=learning_rate) #optimizer used gradient optimization using Adam 
optimizer = torch.optim.SGD(stacked_rnn_model.parameters(), lr=learning_rate)
# Train the model
n_total_steps = len(train_dl)
    for epoch in range(num_epochs):
        t_losses=[]
        for i, (images, labels) in enumerate(train_dl):  
            # origin shape: [6, 3, 300, 300]
            # resized: [6, 300, 300]
            images = images.reshape(-1, num_steps, input_size).to(device)
            print('images shape')
            print(images.shape)
            labels = labels.to(device)
            
            # Forward pass
            outputs = stacked_rnn_model(images)
            print('outputs shape')
            print(outputs.shape)
            loss = criterion(outputs, labels)
            t_losses.append(loss)
            # Backward and optimize
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

打印图像和输出形状为

images shape
torch.Size([18, 300, 300])
outputs shape
torch.Size([18, 5])

---

错误在哪里；dr：您正在展平前两个轴，即

批处理

和

通道

---

我不确定你是否采取了正确的方法，但我会写这一层

无论如何，让我们来看看你面临的问题。您有一个数据加载器，可以生成

（6，3，300，300）

，即6个三通道

300x300

图像的批次。从外观上看，您希望将每个批元素

（3300300）

重塑为

（步长=300，-1）

然而，与此相反，您正在使用

图像影响第一个轴（您不应该这样做）。重塑（-1，num\u步长，input\u大小）

。这将在处理单通道图像时产生预期效果，因为

dim=1

不是“通道轴”。在你的例子中，你有3个通道，因此，结果的形状是：

（6*3*300*300//300//300300300）

，这是

（18,300300）

，因为

num_steps=300

和

input_size=300

。因此，只剩下18个批处理元素，而不是6个

相反，您需要的是使用

（批处理大小，步骤数，-1）

进行重塑。保留大小可变的最后一个轴（也称为“序列长度”）。这将产生一个形状

（6300900）

---

下面是一个经过更正和简化的代码段：

batch_size = 6
channels = 3
inputH, inputW = 300, 300
train_ds = TensorDataset(torch.rand(100, 3, inputH, inputW), torch.rand(100, 5))
train_dl = DataLoader(train_ds, batch_size)

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN, self).__init__()
        # (batch_size, seq, input_size)
        self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
        # (batch_size, hidden_size)
        self.fc = nn.Linear(hidden_size, num_classes)
        # (batch_size, num_classes)

    def forward(self, x):
        out, _ = self.rnn(x)
        out = out[:, -1, :]
        out = self.fc(out)
        return out

num_steps = 300
input_size = inputH*inputW*channels//num_steps
hidden_size = 256
num_classes = 5
num_layers = 2

rnn = RNN(input_size, hidden_size, num_layers, num_classes)
for x, y in train_dl:
    print(x.shape, y.shape)
    images = images.reshape(batch_size, num_steps, -1)
    print(images.shape)
    outputs = rnn(images)
    print(outputs.shape)
    break

---

---

正如我在开始时所说的，我对这种方法有点谨慎，因为基本上，您是以300个展平向量序列的形式向RNN馈送RGB

300x300

图像。。。我不能说这是否有意义，培训条件是否合理，模型是否能够从中学习。我可能错了

>什么是代码>输入/大小/代码>值，哪里是代码> StaskdEnrnnMype 定义？如果图像是灰度级的话，这是有意义的吗？如果你认为你正在逐行地处理你的图像作为一个序列的<代码> 300 /代码>向量的大小<代码> 300 < /代码>。我不确定RGB，你必须看看你的序列中的通道混合在哪里。。。如果它们是连续的或不连续的。在上面的代码中，输入大小是

3*300

，即三通道像素“线”，因此最终可以实际工作。。。你需要尝试一下训练，看看是否能取得效果。我希望我能帮上忙！是的，它有很大的帮助，但是为什么你在第一维度中考虑6×3×300×300 / / 300 / / 300。能再解释一次吗？当然。在代码中，您在大小为

（6,3300300）

（总长度：

6*3*300*300

）的张量上调用了

重塑（-1，num\u步数，输入\u大小）

。结果张量将在

dim=1

（即

300

）和

dim=2

（即

300

）上具有

num\u步长。在
dim=0
上，您有
-1
，这意味着“展平所有剩余组件”。剩余部件的尺寸为
总尺寸/产品（[size\u dim for there dim]）
（伪代码）。它对应于
6*3*300*300/（300*300）=18
。因此，在
dim=0
上，长度值为
18
。是的，这就是输入大小900没有任何意义的原因。现在我明白了，谢谢。