Community Profile


Amanjit Dulai


Last seen: 2 días ago Active since 2016


  • First Review
  • Knowledgeable Level 2
  • Revival Level 1
  • First Answer

View badges

Content Feed

View by

Is a Bi-GRU available - bidirectional Gated Recurrent Unit (GRU) - or a way to implement a Bi-GRU?
A bi-LSTM layer works by applying two LSTM layers on the data; one in the forward direction and one in the reverse direction. Yo...

alrededor de 1 mes ago | 1

| accepted

RMSE for 3D regression of image data
How many values does your network output? If you are using regressionLayer in your network, it will not divide the loss by the n...

4 meses ago | 0

Activations of freezed layers are different between before/after training, why?
The vectors are different because when you fine tune on a new dataset, the average image in "imageInputLayer" is recalculated fo...

más de 3 años ago | 1

| accepted

Custom Neural Network Sample Code Fails on GPU
Instead of using nndata2gpu to prepare your data for GPU training, you can use the 'useGPU' flag. Just change the call to train ...

alrededor de 4 años ago | 1

Neural networks - CUDAKernel/setConstantMemory - the data supplied is too big for constant 'hintsD'
I was able to reproduce your issue. The best solution is to do the GPU training a different way by using the 'useGPU' flag. This...

casi 5 años ago | 0

| accepted

Output processing function REMOVECONSTANTROWS is not supported with GPU.
The error message you are getting suggests that there are rows in your output data which are constant. Without knowing what your...

más de 5 años ago | 2

| accepted

Error when using 'useGPU' for training neural networks
I suspect that the problem here is related to the type for the variable d1. I managed to replicate your error by using a single ...

más de 5 años ago | 3