Community Profile

photo

Amanjit Dulai


MathWorks

5 total contributions since 2016

Contact

Amanjit Dulai's Badges

  • Knowledgeable Level 2
  • Revival Level 1
  • First Answer

View details...

Contributions in
View by

Answered
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...

1 year ago | 1

| accepted

Answered
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 ...

2 years ago | 1

Answered
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...

3 years ago | 0

| accepted

Answered
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...

3 years ago | 1

| accepted

Answered
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 ...

3 years ago | 2