How to Flatten Input in `Nn. Sequential` in Pytorch

As being defined flatten method

torch.flatten(input, start_dim=0, end_dim=-1) → Tensor

is speed comparable to view(), but reshape is even faster.

import torch.nn as nn

class Flatten(nn.Module):
    def forward(self, input):
        return input.view(input.size(0), -1)

flatten = Flatten()

t = torch.Tensor(3,2,2).random_(0, 10)
print(t, t.shape)


#
f = torch.flatten(t, start_dim=1, end_dim=-1)
print(f, f.shape)


#
f = t.view(t.size(0), -1)
print(f, f.shape)


#
f = t.reshape(t.size(0), -1)
print(f, f.shape)

Speed check

# flatten 3.49 µs ± 146 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)
# view 3.23 µs ± 228 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)
# reshape 3.04 µs ± 93 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)

If we would use class from above

flatten = Flatten()
t = torch.Tensor(3,2,2).random_(0, 10)
%timeit f=flatten(t)


5.16 µs ± 122 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)

This result shows creating a class would be slower approach. This is why it is faster to flatten tensors inside forward. I think this is the main reason they haven't promoted nn.Flatten.

So my suggestion would be to use inside forward for speed. Something like this:

out = inp.reshape(inp.size(0), -1)

You can modify your code as follows,

Model = nn.Sequential(nn.Flatten(0, -1),
                     nn.Linear(784,256),
                     nn.ReLU(),
                     nn.Linear(256,128),
                     nn.ReLU(),
                     nn.Linear(128,64),
                     nn.ReLU(),
                     nn.Linear(64,10),
                     nn.LogSoftmax(dim=1))