Why is ShuffleNetV1 different from description in paper ?

[LuYanFCP]

Difference

Your code in ShuffleNetV1/blocks.py

x = self.branch_main_1(x)
if self.group > 1:
    x = self.channel_shuffle(x)
x = self.branch_main_2(x)

The channel_shuffle operation is in the next of conv3x3 operation. But in the paper, the channel_shuffle operation occurs before the con3x3 operation.

[vlad3996]

It does not matter when to do channel shuffle : before Conv2d with groups=num_channels or after it.