Community Profile

photo

Johannes Bergstrom

MathWorks

Active since 2018

Statistics

  • 3 Month Streak
  • Revival Level 1
  • Knowledgeable Level 2
  • First Answer

View badges

Content Feed

View by

Answered
How to create user defined layer in deep network designer
You can write your own layer: https://www.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layers.html

3 years ago | 1

| accepted

Answered
multi cpu trainign using trainignOptions
Training a network on a single low-performance GPU is usually faster than training on multiple CPUs. So you will likely need a v...

3 years ago | 0

| accepted

Answered
Where can I get the matlab code for FaceNet, InceptionV3 & inceptionresnetv2 ? Can anyone provide me the link if you know.
What do you mena by 'code for network X'? Do you want code that creates the network architecture from scratch? Or do you just wa...

3 years ago | 0

Answered
Deep learning using CNN - question about training.
Does you network use batch normalization layers? After training finishes, trainNetwork loops thorugh the whole data set to cal...

3 years ago | 0

Answered
How to find two layers to replace in googlenet?
I presume you are looking at this example: https://www.mathworks.com/help/deeplearning/examples/train-deep-learning-network-to-c...

3 years ago | 0

Answered
Why am I getting invalid function error for a function in an installed package?
Hi, MATLAB examples have supporting files that are off the path and stored in the Examples directory. To run any MATLAB example...

3 years ago | 0

Answered
How can I use the example Transfer Learning Using Alexnet with Vgg16?
Vgg16 requires a lot of GPU memory and you don't have very much of it. The error message says "Try reducing 'MiniBatchSize' usin...

3 years ago | 0

| accepted

Answered
How do I Specify the Input Size on a Fully Connected Layer?
The fully connected layer automatically calculates the input size. The input to 'fc1' in the lenet5 layer array is 4-by-4-by-16....

3 years ago | 0

Answered
Classification of AlexNet deep dreams is always wrong (always nematode)
Try setting the <https://www.mathworks.com/help/deeplearning/ref/deepdreamimage.html#bvlp_pc-OutputScaling 'OutputScaling'> valu...

3 years ago | 0

| accepted

Answered
How to replicate the example "Transfer Learning Using AlexNet" with GoogleNet?
You can use this example: <https://www.mathworks.com/help/deeplearning/examples/train-deep-learning-network-to-classify-new-imag...

3 years ago | 0

| accepted

Answered
transfer learning layers in alexnet and googlenet ?
Here is a page where you can compare pretrained networks: https://www.mathworks.com/help/deeplearning/ug/pretrained-convolution...

3 years ago | 0

| accepted

Answered
Different behavior of 'activations' function of Neural Network Toolbox between 2017b and 2018a.
This is the expected behavior. Please see the release notes under 'Functionality Being Removed or Changed', https://www.mathwork...

3 years ago | 1

| accepted

Answered
R2018a Neural Network Toolbox "Bugs"??
Regarding (1), please see https://www.mathworks.com/help/nnet/examples/monitor-deep-learning-training-progress.html If your n...

3 years ago | 0

Answered
how can I replace the softmax layer with another classifier as svm in convolution network
Here is an example: https://www.mathworks.com/help/nnet/examples/feature-extraction-using-alexnet.html

3 years ago | 1