RuntimeError: Given groups=1, weight of size 16 1 5 5, expected input[100, 3, 256, 256] to have 1 channels, but got 3 channels instead

I try to run the following programe for images classification problem in Pytorch:

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import torch.utils.data as data

# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# Hyper parameters
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001

TRAIN_DATA_PATH = "train/"
TEST_DATA_PATH = "test/"
TRANSFORM_IMG = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(256),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406],
                         std=[0.229, 0.224, 0.225] )
    ])

train_dataset = torchvision.datasets.ImageFolder(root=TRAIN_DATA_PATH, transform=TRANSFORM_IMG)
train_loader = data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True,  num_workers=4)
test_dataset = torchvision.datasets.ImageFolder(root=TEST_DATA_PATH, transform=TRANSFORM_IMG)
test_loader  = data.DataLoader(test_dataset, batch_size=batch_size, shuffle=True, num_workers=4)

# Convolutional neural network (two convolutional layers)
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(7 * 7 * 32, num_classes)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out


model = ConvNet(num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i + 1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                  .format(epoch + 1, num_epochs, i + 1, total_step, loss.item()))

# Test the model
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

# Save the model checkpoint
torch.save(model.state_dict(), 'model/model.ckpt')

But I get a RuntimeError:

Traceback (most recent call last):

RuntimeError: Given groups=1, weight of size 16 1 5 5, expected input[100, 3, 256, 256] to have 1 channels, but got 3 channels instead

Someone could help to fix the bug? Thanks a lot.

Reference related:

https://discuss.pytorch.org/t/given-groups-1-weight-16-1-5-5-so-expected-input-100-3-64-64-to-have-1-channels-but-got-3-channels-instead/28831/17

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

Your input layer self.layer1 starts with a 2d convolution nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2). This conv layer expects an input with two spatial dimensions and one channel, and outputs a tesnor with the same spatial dimensions and 16 channels.
However, your input has three channels and not one (RGB image instead of gray level image).

Make sure your net and data are in synch.