Hi, I am trying to implement a simple train loop in julia to process images, but can’t make my model work. I create the model using the following code: model = Chain( Conv((3, 3), 3 => 32, relu; pad = (1, 1), bias = false), flatten, Dense(15488, max_rating), softmax ) I’ve tried to…

The error message indicates you are attempting to apply a conv operation to a single N0f8 value rather than an array of them. Would you mind showing your loss function implementation? Perhaps there is an extra broadcast operation.

Flux Conv layer method error

New to Julia

zeio January 16, 2023, 9:46pm 5

Yes, thank you! I’ve added this and also a couple of other changes to the training loop from documentation and now it works.

Topic		Replies	Views
Why is there a "Warning: Slow Fallback implementation" and a DimensionMismatch error? General Usage images , flux , csv	1	518	February 16, 2021
Problems using Flux New to Julia	7	470	June 6, 2023
Size Mismatch Convolution Layer Machine Learning question , flux	3	838	June 24, 2021
Julia Flux error- Unsupported dynamic function invocation (call to pointerref) New to Julia gpu , flux	0	622	January 10, 2021
Flux: Feed minibatch into Neural Network New to Julia flux	1	531	December 10, 2019

Flux Conv layer method error

Related topics