photo

Gabija Marsalkaite

Last seen: 4 giorni fa |  Attivo dal 2019

Followers: 0   Following: 0

Statistica

  • 3 Month Streak
  • Knowledgeable Level 2
  • First Answer

Visualizza badge

Feeds

Visto da

Risposto
Different types of Neural Network
The links bellow show how to do that: https://www.mathworks.com/matlabcentral/answers/266413-what-is-the-matlab-code-for-cascad...

oltre 5 anni fa | 1

| accettato

Risposto
Getting helper functions and objects
These files were introduced in R2019a so the most straight forward way would be either updating or writing them yourself. Also k...

oltre 5 anni fa | 2

Risposto
Error using trainNetwork (line 165) - Dot indexing is not supported for variables of this type
Dot indexing is not supported for variables of this type may be caused by missing or unsupported layer. Please make sure that yo...

oltre 5 anni fa | 0

Risposto
My ONNX network doesn't work when loaded in my Java application
Hi Luigi, One possibility is differences in normalisation of data - Alexnet has zero-center normalisation in the first layer i...

oltre 5 anni fa | 0

| accettato

Risposto
Laptop crashing when opening matlab in Gui mode ( watch dog error)
Bug with keyword watchdog was not encountered before in MATLAB. From a quick investigation that does look like a problem between...

oltre 5 anni fa | 0

Risposto
Deep Learning for Maritime environment
The number of images is a difficult question. The smallest dataset I trained a network on was around 1000 images but that depend...

oltre 5 anni fa | 1

| accettato

Risposto
Combining images and numerical values in a deep neural network
Probably simplest way is to add other features as channels. There is example by Uber Engineering where they added gradients for ...

oltre 5 anni fa | 0

| accettato

Risposto
the error appears in defining weightedAdditionLayer
Assuming you have a layer with two inputs (input1 and input2) and one output, 'backward' expects layer, input1, input2, output, ...

oltre 5 anni fa | 0

Risposto
Deep Learning: Train Network to "Play Game"
Hi Michael, This strongly depends on how you want to implement it. Deep learning alone is most often used for tasks with labele...

oltre 5 anni fa | 1

| accettato

Risposto
How can I input complex data 3-D matrices in a convolutional neural network (using deep learning toolbox)?
MATLAB does not have explicit support for complex numbers in neural networks in 2019a (this may change in later releases). In yo...

oltre 5 anni fa | 1

Risposto
Deep Learning Toolbox - How to replicate training/testing results for reproducibility purposes
As you already mentioned reproducibility strongly depends on environment. At the moment there is no way to choose which GPU algo...

oltre 5 anni fa | 1