error: output shape doesn't match broadcast shape

[prayagupa]

This is great resource. Thank you putting it in internet. As a beginner I see following error. This is on a macOS with no GPU.

~/miniconda3/lib/python3.9/site-packages/torchvision/transforms/functional.py in normalize(tensor, mean, std, inplace)
    333     if std.ndim == 1:
    334         std = std.view(-1, 1, 1)
--> 335     tensor.sub_(mean).div_(std)
    336     return tensor
    337 

RuntimeError: output with shape [1, 28, 28] doesn't match the broadcast shape [3, 28, 28]

If its something you can help? I appreciate your time.