Stack Overflow
Stack Overflow

Questions tagged [matconvnet]

MatConvNet is a MATLAB toolbox implementing Convolutional Neural Networks (CNNs) for computer vision applications.

67 questions
1
vote
0 answers

Run MatConvNet on CPU with maximum number of workers

I wish to run MatConvNet on CPU (no GPU at all), with 44 number of workers in parallel computing. Which part of the codes should be modified? Any help is highly appreciated.
Faranak
  • 41
  • 1
  • 4
1
vote
1 answer

Convolutional layer to fully connected layer in Matconvnet

I am trying to understand how the MNIST example in the Matconvnet is designed. It looks like they are using a LeNet variation, but since I did not use Matconvnet before, I am having difficulties how the connection between the last convolutional…
Ufuk Can Bicici
  • 3,589
  • 4
  • 28
  • 57
1
vote
1 answer

train the network with matlab matconvnet

I want to train my network using matlab and matconvnet-1.0-beta25. My problem is regression and I use pdist as loss function to get mse. The inputs data is 56*56*64*6000 and the targets data is 56*56*64*6000 and network architecture is as…
user9218823
1
vote
2 answers

Error using mex -setup: "No supported compiler or SDK was found"

I am using MatConvNet with the Microsoft Visual C/C++ 2015 compiler. It was installed and it worked. However, when I run mex -setup I get the error message No supported compiler or SDK was found. MatConvNet still works and the compiler file is…
jlhw
  • 245
  • 1
  • 17
1
vote
0 answers

matcovnet pooling_cup.cpp pooling_backward_cpu function parameters

Hi I am trying to write a new pooling layer in matcovnet. I tried with Matlab code but it is way too much slow, so now I am trying to implement with cpp code. I am trying to use pooling_cup.cpp code to implement my work. But I am confused with…
Cpt. Price
  • 71
  • 2
  • 8
1
vote
0 answers

Custom Loss function for MSE on Matconvnet

Issue when creating a custom loss function. Sorry I am a bit new to matconvnet So essentially the output for my Neural Network is aimed to be a vector with 2 elements (ex: [1,2]) with an error function based upon the RMSE So I changed the cnn_train…
Daniel Lee
  • 11
  • 2
1
vote
1 answer

Error in updating final FC layer for fine tuning AlexNet

Hello I have recently started working on fine tuning the Alexnet model for my own dataset. I want to modify the final two layer as I have only two classes: net.layers = net.layers(1:end-2); But when I modify the final FC layer like that and it…
Addee
  • 663
  • 10
  • 21
1
vote
1 answer

MatConvNet, Error vs Objective Plot Understanding

How is one supposed to interpret the graph output for the DAG wrapper? There is absolutely minimum documentation on this. What does energy vs epochs mean when relating to "Objective"? What is the difference between the ERROR plot and the OBJECTIVE…
Charles
  • 43
  • 1
  • 7
1
vote
1 answer

Visualize the learned filter of each CNN layer

anyone please tell me how to visualize the learned filter of each CNN layer? The following answers tell me how to only visualize the learned filters of the first CNN layer, but could not visulize the other CNN layers. 1) You can just recover the…
Addee
  • 663
  • 10
  • 21
1
vote
2 answers

Deep Neural Network training, why is the network training not converging?

I'm using MATCONVNET DagNN. Using AlexNet architecture. The last few layers of my architecture are [![net = dagnn.DagNN() ; imdb_32 =load('imdb_all_32_pd_norm.mat'); imdb_32=imdb_32.imdb; % some common options opts.train.batchSize = 100; …
h612
  • 544
  • 2
  • 11
1
vote
0 answers

Constant error in neural network, MatConvNet

Solved: Previously my dataset had around 1000 images. I increased it to 50 000 and now the neural network learns and works. I have created a convolutional neural network for recognizing three emotions from facial expression(positive, neutral,…
Nicole
  • 31
  • 6
1
vote
1 answer

How to add a custom layer and loss function into a pretrained CNN model by matconvnet?

I'm new to matconvnet. Recently, I'd like to try a new loss function instead of the existing one in pretrained model, e.g., vgg-16, which usually uses softmax loss layer. What's more, I want to use a new feature extractor layer, instead of pooling…
zack.Zcy
  • 31
  • 1
  • 3
1
vote
0 answers

MatConvNet: set weight for classes

Imagine the output of the CNN is 1x1920. The classes to be classified are 1 and 2, with very few 2. For example, a label for one image can be: 111111111111111112111111111111111111111111111111111111111111111111111111... For the CNN is easy to say…
Damia Fuentes
  • 5,308
  • 6
  • 33
  • 65
1
vote
2 answers

How to force MATLAB 2016a to use gcc-4.7.x instead of the one I have (gcc-5.4.1)?

There are some posts about this for the older releases of MATLAB, but they don't seem to work for R2016a. I'm trying to install MatConvNet on Ubuntu 16.04. When I run the vl_compilenn command as described here, it gives me a warning as…
Dr. Prasanna Date
  • 745
  • 1
  • 9
  • 29
1
vote
1 answer

How to convert .caffemodel into .mat format

I wanted to use my fine-tuned caffe model in matconvnet for further processing. But the script provided by Andrea vedaldi at https://github.com/vlfeat/matconvnet/blob/master/utils/import-caffe.py leaves the following errors which I am not able to…
geek
  • 65
  • 2
  • 11
1
2
3 4 5