Hi, I’m training the DenseNet from Metalhead.jl on the CIFAR-10 dataset which generally seems to work quite well. However, I can’t seem to find out how to access the output from individual layers in the Chain. I know about Flux.activations() but it just gives me an array of size size(Flux.activati…

The DenseNet in Metalhead.jl is a large Chain wrapper around two smaller Chains - a backbone and a classifier head. Flux.activations acts on the larger Chain in your example. I think what you might be looking for might be something like Flux.activations(Metalhead.backbone(model), x). You should get …

Flux: Obtaining individual layer output for DenseNet from Metalhead.jl

Specific Domains Machine Learning

marcpabst July 6, 2022, 11:43am 3

That seems to be exactly what I was looking for Thanks!

1 Like

Topic		Replies	Views
Flux.jl, treat rows independently General Usage flux	0	420	September 16, 2019
How to retrive input values from Flux Dense layer General Usage flux	2	367	October 3, 2022
How to pass the output of custom layers into Dense layer Machine Learning	1	636	June 19, 2019
Hidden layers in Flux Machine Learning question	5	1358	May 22, 2020
Flux Activations() computes the forward pass again Machine Learning	2	483	May 11, 2020

Flux: Obtaining individual layer output for DenseNet from Metalhead.jl

Related topics