photo

J


Last seen: 21 days ago |  Active since 2018

Followers: 0   Following: 0

Message

Statistics

  • Knowledgeable Level 1
  • First Answer
  • Revival Level 1

View badges

Feeds

View by

Answered
Cross-Entropy Loss in Classification Layers
I ended up just writing my own custom layers. Another language is an option, but I also sympathize with those who have a large ...

5 years ago | 1

Question


Neural Network Checkpoints only every 'N' Epochs??
In the MATLAB documentation for Deep Learning Toolbox (formerly Neural Network Toolbox) we see that we can use <https://www.math...

6 years ago | 0 answers | 1

0

answers

Question


Cross-Entropy Loss in Classification Layers
The MATLAB documentation is very clear to say that a <https://www.mathworks.com/help/deeplearning/ref/classificationlayer.html c...

6 years ago | 1 answer | 0

1

answer

Answered
R2018a Neural Network Toolbox "Bugs"??
At least for (2), the issue is that checkpoints don't save the state of the solver (momentum parameters, etc), so your solver ca...

6 years ago | 1

| accepted

Answered
How to manually change pre-trained CNN's (AlexNet) weights?
Bump! I have a hard time believing that one cannot take an existing SeriesNetwork, and either: 1. Modify properties of it, o...

6 years ago | 1

Answered
R2018a Neural Network Toolbox "Bugs"??
Here is an example of what the validation plot looks like at the very end with the consistent "drop" in the "Final" data points'...

6 years ago | 0

Question


R2018a Neural Network Toolbox "Bugs"??
In R2018a Neural Network Toolbox I have noticed two oddities: (1) When training a CNN with trainNetwork and 'options' field ...

6 years ago | 3 answers | 0

3

answers

Answered
why using imageDataAugmenter doesn't increase the size of my training data set ?
I am guessing that when augmentation is on, it trains "exactly" the way it trained when it was turned off, but performs a random...

6 years ago | 1

| accepted