I have defined a MLP (multi layer perceptron) with the Chain command, and this MLP is wrapped in a mutable structure. The gradient of this Chain (2 layer dense NN) returns nothing. Is this a bug, or am I doing this the wrong way? Minimum working example: function loss(filter, x, y) return nor…

Change ps = Flux.Params(filt.f) to ps = Flux.params(filt.f)

Flux: gradient of Chain returns nothing

CarloLucibello June 11, 2021, 9:37am 2

Change

ps = Flux.Params(filt.f)

ps = Flux.params(filt.f)

2 Likes

Topic		Replies	Views
Take gradient of parameters not working Machine Learning question , flux	0	344	January 12, 2021
Gradient not being computed when training NN using Flux Machine Learning question , flux , sciml	3	101	January 30, 2025
Flux loss: Gradient wrt input leads to empty gradient wrt parameters or to "can't differentiate foreigncall" Machine Learning flux , forwarddiff , diffeqflux	3	551	April 8, 2022
Problems relating to "gradient is nothing" General Usage	11	183	October 29, 2024
Found Bug in Flux General Usage question , package , bug , flux	13	1178	July 11, 2022