dvgodoy
A code mistake in the book
There is a mistake on page 113 of the book.
# on page 113
predictions = torch.tensor(0.5, 1.0)
labels = torch.tensor(2.0, 1.3)
Probably what you really want to write is
predictions = torch.tensor([0.5, 1.0])
labels = torch.tensor([2.0, 1.3])
Thank you Neuer
Page 738 of the book : There is: `x0 = points[0] # 4 data points x1 = points[1][2:] # 2 data points x2 = points[2][1:] # 3 data points
x0.shape, x1.shape, x2.shape`
But correctly, given the following code, it is:
`s0 = points[0] # 4 data points s1 = points[1][2:] # 2 data points s2 = points[2][1:] # 3 data points
s0.shape, s1.shape, s2.shape`
Nice book!
I add another code typo to this issue, that I found in the book (and in the notebook as well): Page 606:
batch_hidden = final_hidden.permute(1, 0, 2)
batch.shape
Should actually be:
batch_hidden = final_hidden.permute(1, 0, 2)
batch_hidden.shape
Otherwise an incorrect tensor shape will be printed ([3, 4, 2] instead of [3, 1, 2].
