Community Profile

photo

Divya Gaddipati


Last seen: Today

MathWorks

103 total contributions since 2019

I am an Application Software Engineer at Mathworks India.
My main areas of interest are Computer Vision and Machine Learning.

DISCLAIMER: Any advice or opinions here are my own and in no way reflect that of Mathworks.

Contact

Divya Gaddipati's Badges

  • 3 Month Streak
  • Knowledgeable Level 3
  • Revival Level 2
  • First Answer

View details...

Contributions in
View by

Answered
How to produce an acoustic sound waves for leakage detection in pvc pipes. is it possible in matlab?
You can refer to the following link for an answer provided to a similar question https://www.mathworks.com/matlabcentral/answer...

14 days ago | 0

Answered
.tif.dat Image analysis
Similar question has already been asked and answered by the community which might be of relevance you. Please refer to the follo...

15 days ago | 0

Answered
U-net segmentation gives error for layers output size after starts to training
It seems like your last conv layer is of size [512, 512, 4], whereas it should have been [512,512,1]. You can use analyzeNetwor...

15 days ago | 0

| accepted

Answered
I want to apply 1D CNN on sequence data, is there any provision for this additional layer in MATLAB?
Currently 1D convolutional layers are not supported. As a potential workaround you can try using imageInputLayer. https://www....

15 days ago | 0

Answered
How to designthe SAGAN self attention layer?
You would have to create a custom layer. If you are using R2020a version, you'll be able to load the custom layer into the Deep ...

15 days ago | 0

Answered
Deploy classification learner model
Refer to the following link on how to use your model on new data https://www.mathworks.com/help/stats/export-classification-mod...

15 days ago | 0

Answered
Yolo v3 training on coco data set
You can refer to the following link for training a YOLOv3 object detector. In place of the dataset used in this example, you can...

16 days ago | 0

Answered
Input Data format in deep learning
Hi, If you're doing a sequence-to-sequence classification, for the input layer, you have to use the sequenceInputLayer and for ...

16 days ago | 0

Answered
How do I correlate two tables with a different number of rows?
You could also convert the table to a matrix and use interpolation on the smaller matrix to resize it to the larger matrix's siz...

1 month ago | 1

| accepted

Answered
Finding the number of occurance of each value in the each columns of a matrix.
A similar question has already been asked and answered by the community which could be of relevance to you. You can refer to th...

1 month ago | 0

| accepted

Answered
Joining two curves on an image
You can use imdilate to make the lines come closer to each other. This will increase the width of the lines as well. To reduce t...

1 month ago | 0

Answered
How to use trainNetwork with varying lengths of inputs and outputs?
From the error, I'm guessing the size of the output from the last layer of your network is not same as the size of YTrain, which...

1 month ago | 0

Answered
How can I use Two-Dimensional True Compression on arbitrarly sized images?
Since wcompress works only on images of sizes with power of 2, you could either resize the images to a particular size like (25...

1 month ago | 1

| accepted

Answered
Is a LSTM parameter to sequence regression possible?
For a sequence input, you can use sequenceInputLayer. sequenceInputLayer(featureDimension) For more informatiom on sequenceI...

2 months ago | 0

Answered
trained stacked auto encoders
One way is to use imageDatastore. datasetPath = fullfile('/path/to/dataset'); imds = imageDatastore(datasetPath, ... 'Inc...

2 months ago | 0

Answered
Different results between Deep Learning Network Analyzer and Deep Network Designer analysis
I assume you're using R2020a. I have brought this issue to the notice of our developers. They will investigate the matter furt...

2 months ago | 0

Answered
How can I create parallel pools in Simulink simulation
You can refer to Run Parallel Simulations documentation to get started.

2 months ago | 0

Answered
Error while running Example of TrainAnSSDObjectDetector
From the error "The value of 'bboxB' is invalid. Expected input to be finite.", it seems like one or more of the groundtruth bou...

2 months ago | 0

Answered
Error while training SSD object detector
Make sure your groundtruths are valid and non-empty i.e., the values of the bounding boxes are finite, positive, non-fractional,...

2 months ago | 0

Answered
Error using trainNetwork - Number of observations in X and Y disagree.
Try using net = trainNetwork(TB_train, TS_train, Layers, options);

2 months ago | 0

Answered
Looping and indexing with global variables
Hi, Seems like the variable "diff_ca" is empty. Try initializing it to an array of zeros first time the function mainfun2 is ca...

2 months ago | 0

Answered
Reading in txt data files with changing names
Based on the file name type, you should form the "foldername" and "fileselectfortime". You can modify your code as shown below:...

4 months ago | 0

| accepted

Answered
Which version of Matlab is compatible with macOS Sierra 10.12.6?
The System Requirements page states that the earliest Mac OS on which release R2020a is supported is macOS High Sierra (10.13.6)...

4 months ago | 0

Answered
How measure sensitivity and specificity when using kfold cross validation?
Hi, You can use confusionmat to obtain the True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), wh...

4 months ago | 1

| accepted

Answered
Multiple input (sequence and static) to a dag network
Hi, The latest version of MATLAB allows the training of networks with multiple inputs. Please refer to the following link for...

4 months ago | 0

Answered
Binary Search - Descending order
Hi, You need to keep searching until you find the target. For this you need to add a while loop, which keeps reducing the searc...

4 months ago | 0

Answered
what is the 'NSMethod','exhaustive' k-nearest neighbor classifier
Hi, NSMethod is the Nearest neighbor search method, specified as either 'kdtree' or 'exhaustive'. 'kdtree' — Creates and uses ...

4 months ago | 0

| accepted

Answered
image processing: how to separate back ground(black) from the foreground objects (white)
Depending on the complexity of the image, different segmentation techniques can be used: Watershed segmentation: Watershed segm...

4 months ago | 0

Answered
Time info is not read correctly by readtable
Hi, This is a known issue and our development team is working on it. Until this issue is resolved, please use Microsoft Excel...

4 months ago | 1

Answered
Improvement of the neural net fitting app
Poor neural network performance might be because the error is not able to reach the goal. If this occurs then you can try the fo...

5 months ago | 0

| accepted

Load more