J

Last seen: 6 maanden ago | Active since 2018

Followers: 0 Following: 0

Message

Statistics

Feeds

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 ...

meer dan 6 jaar 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...

ongeveer 7 jaar 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...

ongeveer 7 jaar 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...

meer dan 7 jaar 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...

meer dan 7 jaar 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'...

meer dan 7 jaar 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 ...

meer dan 7 jaar 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...

meer dan 7 jaar ago | 1

| accepted