Feeds
已回答
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 ...
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 前 | 1
提问
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 前 | 0 个回答 | 1
0
个回答提问
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 前 | 1 个回答 | 0
1
个回答已回答
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...
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 前 | 1
| 已接受
已回答
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...
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 前 | 1
已回答
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'...
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 前 | 0
提问
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 前 | 3 个回答 | 0
3
个回答已回答
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...
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 前 | 1
| 已接受