jajoe
jajoe
Hello I had the same error. It was due to the model that I copied to the checkpoint_path. In the README, you can find several models. I downloaded two archives...
sudo pip3 install tensorflow-0.8.0-cp34-cp34m-linux_armv7l.whl works with my RPi2 Model B, and everything is OK. Thanks a lot, it's very useful ! (we need to use "sudo python3 ..." because of...
NMF could be interesting because there are a lot of applications (in dimensionality reduction and clustering). I'll implement it.
Interesting, thanks you for your suggestion
When I read other implementations (e.g https://beckernick.github.io/neural-network-scratch/), seldom I've seen sth to stop before the end of the X iterations.
Correction : if we can give a validation set to the train() function, we can monitor the convergence (by computing the accuracy on the validation set).
the option is missing, but I've seen that generally we use the same activation function for all layers with FNN (that's not the case with other types of neural networks)....
I believe (not sure) that the test called 'big case' has two output nodes. Here is the features/labels used : ```js var trainingSet = [[1, 1], [1, 2], [2, 1],...
In fact when we use classification the result is a defined class. So the result can't be continuous. You will probably have to define classes (e.g : class "0" corresponds...