Community Profile

photo

Benjamin Ballintyn


Last seen: plus d'un an il y a |  Actif depuis 2019

Followers: 0   Following: 0

Statistiques

All
  • 5-Star Galaxy Level 1
  • First Submission
  • GitHub Submissions Level 1
  • First Answer

Afficher les badges

Feeds

Afficher par

A soumis


PoissonHMM
HMM for tracking hidden states from spike trains of many neurons (even with overlapping or multiple spikes per time bin).

plus de 3 ans il y a | 2 téléchargements |

Question


GPU memory build up from multiple mex calls in loop
Hi, I am having memory problems when repeatedly calling the mex version (generated using GPU Coder) of the following function (...

presque 4 ans il y a | 1 réponse | 0

0

réponse

Question


Writing data from GPU
Hi, I am trying to find the fastest way to write data to a binary file (currently using fwrite), from within a function that ge...

environ 4 ans il y a | 1 réponse | 0

1

réponse

A répondu
Specifying gpuArray input for codegen
Okay, I was able to fix this problem by getting gpucoder to produce the code that the app used to compile my function. Install ...

environ 4 ans il y a | 1

| A accepté

Question


Specifying gpuArray input for codegen
Hi, I am trying to accelerate some simulation code I have using my GPU. I am trying to do this by first creating a bunch of gpu...

plus de 4 ans il y a | 1 réponse | 1

1

réponse

A répondu
The class names of layer must match the class names of the validation/training data
After a little more playing around, I believe this is a bug. I tried to train with a dataset Xtr and received the above error. T...

plus de 4 ans il y a | 1

A répondu
Error : The prediction sequences are of feature dimension 1 but the input layer expects sequences of feature dimension 4
What are the sizes of each input datapoint in XTest?

plus de 4 ans il y a | 0

Question


The class names of layer must match the class names of the validation/training data
Hi, I am trying to train a bi-directional lstm (although I have had the same issue with normal lstms) to do sequence-to-sequenc...

plus de 4 ans il y a | 2 réponses | 1

2

réponses