Community Profile

photo

Richard

MathWorks

Last seen: 5 days ago Active since 2011

Statistics

  • 3 Month Streak
  • Knowledgeable Level 3
  • Revival Level 1
  • First Answer

View badges

Content Feed

View by

Answered
Hi everyone, I am not able to figure out the "too many input arguments error" kindly help
When you specify training data as a table, you can't pass in two separate inputs for predictors and responses. Instead you need...

8 months ago | 0

Answered
How do I debug a convolutional neural network with a custom training loop that is not learning?
These lines of code: % Use model outputs to predict the diffusion signal for each image % in mini batch Spred = zeros(size(dl...

9 months ago | 0

| accepted

Answered
Unable to perform assignment because the indices on the left side are not compatible with the size of the right side.
The functionLayer you created will only work with inputs that have a batch size of 1 - it is reshaping the input to K x 7 x 1 x...

9 months ago | 0

Answered
U-net looses connections, becomes linear rather than U-shaped (unetLayers)
This is not being caused by the training, or saving and loading: the network is likely correct at that point. The loss of conne...

9 months ago | 0

| accepted

Answered
Cannot get tracing to work on complex custom deep learning layer
You are passing the bijector network into dlfeval as data that is copied inside the closure of an anonymous function. dlfeval c...

10 months ago | 0

| accepted

Answered
Not able to calculate gradient of loss function in a neural network program
I think this may be due to your introduction of the complex value into the output of the model, NN. Even though you are later s...

10 months ago | 0

| accepted

Answered
ReLu 'Activation function' is not a recognized parameter in convolution2dLayer
"Activation" is not a valid input option for convolution2dLayer in MATLAB. In MATLAB, activation functions are specified by con...

11 months ago | 0

| accepted

Answered
I am trying to preprocess an Image Datastore using 'transform' function which will be input for training a CNN. I think I lose the labels in the transformation, how can I fix?
Ali, you are correct that the issue is that the TransformedDatastore does not have a Labels property and is no longer trivially ...

1 year ago | 1

| accepted

Answered
Normalizing input data for DeepLearning Trainer interface takes very long time
You can set the ResetInputNormalization training option to false to prevent the input statistics being recomputed every time. Y...

1 year ago | 0

Answered
Gradient of loss for variational autoencoder?
Zero gradients are normally caused by the computation between the inputs and the output loss not being traced. When dlgradient ...

1 year ago | 0

| accepted

Answered
Why happens all the gradients of the generator are zero (from the beginning to the end) when training a GAN
All of the calculations that are "between" the variables you want gradients with respect to, and the loss value, need to be cont...

1 year ago | 0

| accepted

Answered
handle class obj is getting only zero
I think that you might have incorrect syntax for the function definition of the rossubscriber callback. The documentation for t...

2 years ago | 0

Answered
Previously accessible file is now inaccessible.
The errot itself is related to performance optimizations within the dlnetwork class. You should be able to prevent it by specif...

2 years ago | 1

| accepted

Answered
Unrecognized function or variable 'GR_outputpredicted'. Error in testcnn (line 75) predictionError = test_GR_output - GR_outputpredicted;
As the error message says, the variable you tried to use does not exist. You have a typo on line 74. You have created GR_ouput...

2 years ago | 0

| accepted

Answered
I am getting error in "Denoise Speech Using Deep Learning Network" example?
The second error is being described by these lines in the output: Error using tall/cellfun (line 19) Unrecognized func...

2 years ago | 0

| accepted

Answered
cuda kernel does not work when a data is transfer to the GPU. any problem with my gateway MEX code?
Hi Moein, There is no way of allocating MATLAB arrays directly as pinned CUDA memory. Inputs to a mex function will always be ...

3 years ago | 0

| accepted

Answered
cuda kernel does not work when a data is transfer to the GPU. any problem with my gateway MEX code?
Moein, there are a couple of issues that I can see in the code. The first issue is that it is not initializing the GPU device i...

3 years ago | 0

Answered
Log axis on plots of different types
If you already have a set of axes with a plot in them then you need to explicitly set the y-axis on the existing axes handle: ...

10 years ago | 0

Answered
multiple datatip value extraction
Hi Kumaresan, You can get the values of datatip positions using the datacursormode and getCursorInfo functions: d = da...

12 years ago | 3

| accepted

Answered
Data Cursor Position Issue
Conor, sorry for the delay, I didn't notice your comment until today. This is a bug in older versions of MATLAB. I can see t...

12 years ago | 0

| accepted

Answered
A mysterious problem regarding NaNs, imagesc and subplots.
A workaround is to use a surface with flat shading (the default) and just view it from above. You do have to do a bit of extra ...

13 years ago | 1

Answered
Calling a variable from a variable
These kind of situations are best handled by storing the original data in a variable type that is designed to map strings to dat...

13 years ago | 0

Answered
CreateData function in MBC, selecting variables from a .mat file
Following on from Ian's reply, here is a concrete example of importing using a data structure. The easiest and most robust way ...

13 years ago | 3

Answered
Data Cursor Problem wtih Alt-Click
Mel, I can reproduce the error by doing the following: # Start GUIDE # Add a menu item, label it "File" and give it the tag ...

13 years ago | 0

| accepted

Answered
Data Cursor Problem wtih Alt-Click
Mel, At a glance this doesn't look like it can be directly caused by data cursors: it looks like a missing function in your g...

13 years ago | 0

Answered
loadobj input argument type determination?
You can think of objects as being saved as a set of pairs of properties and their values. When you load one, it creates a new o...

13 years ago | 0

Answered
Retrieve the figure from the surface fitting tool
If you generate code from your fit, and then run that code, it will produce the same set of plots that you originally had but in...

13 years ago | 0

| accepted

Answered
SEgmentation Violation detected. m_interpreter.dll errors
Firstly, I agree with Jan and Walter - it is always best to send segmentation violation stack traces directly to MathWorks Suppo...

13 years ago | 0

Answered
Create an empty array of class event.listener
You can create empty objects with the static empty() method of a class, as documented at <http://www.mathworks.com/help/techdoc/...

13 years ago | 3

| accepted

Answered
Help vectorize my poor code or make it faster
If your y and z values are all integers then I think this will work in place of the nested for loops: idx = sub2ind(size(ma...

13 years ago | 1

| accepted

Load more