Community Profile

photo

Amanjit Dulai

Last seen: 3일 전 2016년부터 활동

Statistics

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

배지 보기

Content Feed

보기 기준

답변 있음
Text Data through RNN
Here is an example for training an LSTM to classify text: https://mathworks.com/help/textanalytics/ug/classify-text-data-using-...

20일 전 | 0

답변 있음
Error in predicted outputs for labels in neural network
As mentioned here: https://uk.mathworks.com/matlabcentral/answers/1835423-what-s-wrong-with-my-neural-network#answer_1085378 the...

약 1달 전 | 0

답변 있음
What's wrong with my neural network?
I managed to get this to work by reducing the learning rate: x = rand(75,11); y = randi(5, 5, 75); P = x'; T = y; % Set...

약 1달 전 | 0

| 수락됨

답변 있음
How to improve accuracy of SqueezeNet convolutional neural network?
Getting good performance with deep learning can take some experimenting. I tried some simple things with the data you linked to:...

3달 전 | 0

| 수락됨

답변 있음
Custom Vnet layer validation failed error
It's tricky to tell without the code for createVnetBn, but I would guess the problem is this line in prelu3dLayer: % Initialize...

3달 전 | 0

답변 있음
How to obtain Shapley Values with a pattern classification neural network?
It is possible to do this by passing a function handle to shapley. This function handle needs to output the score for the class ...

4달 전 | 0

| 수락됨

답변 있음
train brain tumor dataset
There is an example of training a network to perform 3-D Brain Tumor Segmentation here: https://mathworks.com/help/images/segme...

10달 전 | 0

답변 있음
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...

약 1년 전 | 3

| 수락됨

답변 있음
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...

1년 이상 전 | 0

답변 있음
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...

4년 이상 전 | 1

| 수락됨

답변 있음
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 ...

약 5년 전 | 1

답변 있음
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...

6년 이하 전 | 0

| 수락됨

답변 있음
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...

6년 이상 전 | 2

| 수락됨

답변 있음
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 ...

6년 이상 전 | 3