RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[3, 1, 224, 224] to have 3

最近跑代码，遇到了一个错误，如下所示：

torch.Size([3, 1, 224, 224])
Traceback (most recent call last):
  File "test_loocv.py", line 245, in <module>
    output = model_ft(test_data)
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torchvision-0.2.1-py3.6.egg/torchvision/models/resnet.py", line 139, in forward
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 301, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[3, 1, 224, 224] to have 3 channels, but got 1 channels instead

这是整个代码：

from __future__ import print_function, division
import torch
from torch.autograd import Variable
import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy
import torch.utils.data as data_utils
from torch.utils import data


data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.RandomRotation(20),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])
}


data_dir = "test_images"

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")


def imshow(inp, title=None):
    """Imshow for Tensor."""
    inp = inp.numpy().transpose((1, 2, 0))
    mean = np.array([0.485, 0.456, 0.406])
    std = np.array([0.229, 0.224, 0.225])
    inp = std * inp + mean
    inp = np.clip(inp, 0, 1)
    plt.imshow(inp)
    if title is not None:
        plt.title(title)
    plt.pause(0.001)  # pause a bit so that plots are updated



def train_model(model, criterion, optimizer, scheduler, dataloader, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train']:
            if phase == 'train':
                scheduler.step()
                model.train()  # Set model to training mode
            else:
                model.eval()   # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            #for inputs, labels in dataloaders[phase]:
            for inputs, labels in dataloader:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                # track history if only in train
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # backward + optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # deep copy the model
 #           if phase == 'val' and epoch_acc > best_acc:
 #               best_acc = epoch_acc
 #               best_model_wts = copy.deepcopy(model.state_dict())

        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
#    print('Best val Acc: {:4f}'.format(best_acc))

#    model.load_state_dict(best_model_wts)
    return model


def visualize_model(model, num_images=6):
    was_training = model.training
    model.eval()
    images_so_far = 0
    fig = plt.figure()

    with torch.no_grad():
        #for i, (inputs, labels) in enumerate(dataloaders['test]):
        for i, (inputs, labels) in enumerate(dataloaders['train']):

            inputs = inputs.to(device)
            labels = labels.to(device)

            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)

            for j in range(inputs.size()[0]):
                images_so_far += 1
                ax = plt.subplot(num_images//2, 2, images_so_far)
                ax.axis('off')
                ax.set_title('predicted: {}'.format(class_names[preds[j]]))
                imshow(inputs.cpu().data[j])

                if images_so_far == num_images:
                    model.train(mode=was_training)
                    return
        model.train(mode=was_training)



######################################################################
# Finetuning the convnet
# Load a pretrained model and reset final fully connected layer.

# model_ft = models.resnet18(pretrained=True)
model_ft = models.resnet50(pretrained=True)

num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)

model_ft = model_ft.to(device)

criterion = nn.CrossEntropyLoss()

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)



#model_ft = model_ft.cuda()
nb_samples = 10
nb_classes = 2


data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.RandomRotation(20),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])
}

'''val_loader = data.DataLoader(
        image_datasets['train'],
        num_workers=2,
        batch_size=1
    )
val_loader = iter(val_loader)'''

image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train']}

dataset_sizes = {x: len(image_datasets[x]) for x in ['train']}
class_names = image_datasets['train'].classes

# LOOCV
loocv_preds = []
loocv_targets = []
for idx in range(nb_samples):
    
    print('Using sample {} as test data'.format(idx))
    
    # Get all indices and remove test sample
    train_indices = list(range(len(image_datasets['train']))) 
    del train_indices[idx]
    
    # Create new sampler
    sampler = data.SubsetRandomSampler(train_indices)

    dataloader = data.DataLoader(
        image_datasets['train'],
        num_workers=2,
        batch_size=1,
        sampler=sampler
    )
    
    # Train model
    for batch_idx, (samples, target) in enumerate(dataloader):
        print('Batch {}'.format(batch_idx))
        model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, dataloader, num_epochs=2) # do I add this line here?
                
    # Test on LOO sample
    model_ft.eval()
    test_data, test_target = image_datasets['train'][idx]
    test_data = test_data.cuda()
    #test_target = test_target.cuda()
    test_target = torch.tensor(test_target)
    test_target = test_target.cuda()
    test_data.unsqueeze_(1)
    test_target.unsqueeze_(0)
    print(test_data.shape)
    output = model_ft(test_data)
    pred = torch.argmax(output, 1)
    loocv_preds.append(pred)
    loocv_targets.append(test_target.item())

如上图所示，具有以下形状：test_datatorch.Size([3, 1, 224, 224])

报告的错误说输入的大小应该是 [b， 3， w， h]，但我们的是 [3， 1， 224， 224]，所以它不接受它。尝试使用移置来更改前两个维度。

将 [H，W，C] 转换为 [C，H，W]，要包含 batch_size（N） 使用 DataLoader，它将自动包含：

image = image.transpose（（2， 0， 1））