Ожидаемый входной размер_пакета (18) соответствует целевому размеру_пакета (6)

Доступен ли RNN для классификации изображений только для серого изображения? Следующая программа работает для классификации серого изображения.

Если используются изображения RGB, у меня возникает эта ошибка:

Ожидаемый входной размер_пакета (18) соответствует целевому размеру_пакета (6)

в этой строке loss = criterion(outputs, labels).

Моя загрузка данных для поезда, действительного и тестового выглядит следующим образом.

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)

Моя модель выглядит следующим образом.

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()

Печать изображений и выходных форм

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

Где ошибка?