Error at custom image classification with PyTorch weight of size?

Question

Edit Question:

I'm using my own black and white tiff images dataset and I created the model_0 as the videos I will put my code That's the error I got

Given groups=1, weight of size [10, 1, 3, 3], expected input[32, 3, 128, 128] to have 1 channels, but got 3 channels instead

here is the full code:

# Create simple transform

simple_transform = transforms.Compose([
    transforms.Resize(size=(128, 128)),
    transforms.ToTensor(),
])

# Load data and transform data

train_data_simple = datasets.ImageFolder(root=train_dir,
                                          transform=simple_transform)

test_data_simple = datasets.ImageFolder(root=test_dir,
                                          transform=simple_transform)

# Turn dataset into DataLoader

BATCH_SIZE = 32
NUM_WORKERS = 2

train_dataloader_simple = DataLoader(dataset=train_data_simple,
                                     batch_size=BATCH_SIZE,
                                     num_workers=NUM_WORKERS,
                                     shuffle=True)

test_dataloader_simple = DataLoader(dataset=test_data_simple,
                                     batch_size=BATCH_SIZE,
                                     num_workers=NUM_WORKERS,
                                     shuffle=False)

class TingVGG(nn.Module):
    def __init__(self, input_shape: int, hidden_units: int, output_shape: int) -> None:
        super().__init__()
        self.conv_block1 = nn.Sequential(nn.Conv2d(in_channels=input_shape,out_channels=hidden_units,kernel_size=3,stride=1,padding=1),
        nn.ReLU(),
        nn.Conv2d(in_channels=hidden_units, out_channels=hidden_units, kernel_size=3,stride=1,padding=1),
        nn.ReLU(),
        nn.MaxPool2d(kernel_size=2, stride=2)
        )
        
        self.conv_block2 = nn.Sequential(nn.Conv2d(in_channels=hidden_units,out_channels=hidden_units,kernel_size=3,stride=1,padding=1),
        nn.ReLU(),
        nn.Conv2d(in_channels=hidden_units, out_channels=hidden_units, kernel_size=3,stride=1,padding=1),
        nn.ReLU(),
        nn.MaxPool2d(kernel_size=2, stride=2)
        )
        
        self.classifier = nn.Sequential(nn.Flatten(), nn.Linear(in_features=hidden_units ,out_features=output_shape))
        
        
    def forward(self, x: torch.Tensor):
        x = self.conv_block1(x)
        #print(x.shape)
        x = self.conv_block2(x)
        #print(x.shape)
        x = self.classifier(x)
        #print(x.shape)
        return x

torch.manual_seed(42)
model_0 = TingVGG(input_shape=1, # Number of Color channel in the input image (c, h, w)
                  hidden_units=10,
                  output_shape=len(train_data.classes)).to(device)
model_0

image_batch, label_batch = next(iter(train_dataloader_simple))
image_batch.shape, label_batch.shape

The output is:

(torch.Size([32, 3, 128, 128]), torch.Size([32]))

I think it should be

(torch.Size([32, 1, 128, 128]), torch.Size([32]))


model_0(image_batch.to(device))  # when I run this code I got the error

I don't know where is the fault in my code. I just began to learn PyTorch, please help me and excuse me if my question is not that good

Answer 1

Meh, you said you images are black and white so you only have one channel.
So, Why did you put input_shape=3? Just change that to 1.