-
New to deep learning so this question may be basic-
I trained on a set of 37k labelled images using the 'Classifier training of inception resnet v1' guide.
It looks like the training went well, but …
N2ITN updated
6 years ago
-
We should make sure that the CNN and RNN actually are using the same structure of input and output data. Moreover, they should use the same internal methods (e.g. for calculating the accuracy)
-
Just wondering, are there any plan for modifications to be able to use LightGBM in Random Forest mode? It would be really interesting to see how LightGBM fares in a (potential) Random Forest mode, bot…
-
-
After spending some time trying to find solutions for #106 it has become clear that the action system is flawed. Currently the game doesn't predict the AP outcome of an action, but instead directly en…
-
Several issues may affect prediction
1. We are using feature scaling (like centre, standardise etc) on the training dataset, but not using the same mean and standard deviation for the features dur…
-
To be precise: honest RF can be trained, but once we want to do a prediction the algorithm dies and one has to restart R.
-
If a model object with mstop = 0 is used for prediction the argument newdata is ignored, i.e., for
`predict(m[0], newdata = data)`
the argument newdata is not used.
Consider the following MWE:
…
-
Hi , I installed everything on W10 x64 python 2.7 - installed
pip install -U spacy
python -m spacy.en.download all -
conda install scikit-learn
I installed and followed restaurant example dire…
-
Hi meijieru,
First of all, thanks so much for the package, it works nicely and is easy to install and test.
I am really interested in your package and I am trying to go deeper by redoing the who…