You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
SConv2dLSTM currently concatenates the hidden cell with the input cell, applies a single nn.Conv2d function of channel length 4*out_channel
The output is then split into 4 chunks (along the channel dimension), which are fed to each of the 4 LSTM gates
This means HxW of the hidden cell must be equal to HxW of input
Stride != 1 causes HxW to no longer be equal.
To fix this, a stride argument can trigger the conv to take place before concatenation of the hidden state mem and input x.
Far less efficient than running all conv operations in one hit, though I don't yet see a way around this.
The text was updated successfully, but these errors were encountered:
SConv2dLSTM currently concatenates the hidden cell with the input cell, applies a single nn.Conv2d function of channel length 4*out_channel
The output is then split into 4 chunks (along the channel dimension), which are fed to each of the 4 LSTM gates
This means HxW of the hidden cell must be equal to HxW of input
Stride != 1 causes HxW to no longer be equal.
To fix this, a stride argument can trigger the conv to take place before concatenation of the hidden state
mem
and inputx
.Far less efficient than running all conv operations in one hit, though I don't yet see a way around this.
The text was updated successfully, but these errors were encountered: