Open DilumAluthge opened 3 years ago
What kinds of layers do we need to start with?
That should be sufficient to e.g. do LeNet-5, right?
@chriselrod
Yeah, from the model zoo:
# LeNet5 "constructor".
# The model can be adapted to any image size
# and any number of output classes.
function LeNet5(; imgsize=(28,28,1), nclasses=10)
out_conv_size = (imgsize[1]÷4 - 3, imgsize[2]÷4 - 3, 16)
return Chain(
Conv((5, 5), imgsize[end]=>6, relu),
MaxPool((2, 2)),
Conv((5, 5), 6=>16, relu),
MaxPool((2, 2)),
flatten,
Dense(prod(out_conv_size), 120, relu),
Dense(120, 84, relu),
Dense(84, nclasses)
)
end
This is a meta-issue to track the issues that we need to solve in order for Octavian to become a competitive option for training neural networks on the CPU.