typo in model structure

- the final model structure uses 3 channel input.
- no data transformation was done to transform input images from 3 channel (RGB) to 1 channel (Grayscale).

beginner_source/introyt/introyt1_tutorial.py

@@ -176,9 +176,9 @@ class LeNet(nn.Module):
 
     def __init__(self):
         super(LeNet, self).__init__()
-        # 1 input image channel (black & white), 6 output channels, 5x5 square convolution
+        # 3 input image channel (RGB image), 6 output channels, 5x5 square convolution
         # kernel
-        self.conv1 = nn.Conv2d(1, 6, 5)
+        self.conv1 = nn.Conv2d(3, 6, 5)
         self.conv2 = nn.Conv2d(6, 16, 5)
         # an affine operation: y = Wx + b
         self.fc1 = nn.Linear(16 * 5 * 5, 120)  # 5*5 from image dimension