FluxML/Flux.jl
Auf GitHub ansehenWeights shape not validated against kernel, channels
Open
#2.506 geöffnet am 25. Okt. 2024
good first issuehelp wanted
Repository-Metriken
- Stars
- (4.725 Stars)
- PR-Merge-Metriken
- (Durchschn. Merge 4h 27m) (2 gemergte PRs in 30 T)
Beschreibung
weights = Flux.kaiming_normal()(3, 3, 1)
Conv((3, 3), 1 => 1; pad = (1, 1), init = (_...) -> weights)
# Conv((3,), 3 => 1, pad=1) # 10 parameters
weights = Flux.kaiming_normal()(3, 3, 1, 1)
Conv((3, 3), 1 => 1; pad = (1, 1), init = (_...) -> weights)
# Conv((3, 3), 1 => 1, pad=1) # 10 parameters
I wanted to strictly specify the weight init for testing, but encountered this odd result. I think there should be validation to ensure that the weight shape matches the kernel size and input channels, and error if there is a mismatch.