Closed flukeskywalker closed 9 years ago
Is the 'first' the outer-most or the inner-most axis? (i.e., will the fully-connected weight matrix be #units * #inputs or vice-versa?)
Fully connected matrix will be #units * #inputs
.
Conv layer weights will be #filters * #num_input_filters * kernel_size
.
In that case yes, that sounds good!
:+1:
Great. I've already changed FC, and will move RNN/LSTM too.
I think we should (or need to) rearrange the axes of the weight matrices. The convention should be that the first axis always corresponds to the number of units/neurons in the layer. This will:
This does not require too much work yet. If it sounds good I can do it.