Answer by Kire for Keras multiple inputs masking
I have solved this problem by creating a separable masking layer which acts on each channel independently.import TensorFlow.keras.layers as tflclass SeperableMaskingLayer(tfl.Layer):def __init__(self,...
View ArticleAnswer by B Douchet for Keras multiple inputs masking
Ok so because I didn't know the answer and was curious about it, I made some experimentations. I first created a sequence made of 3 time steps and 3 features :inputs = np.ones([1, 3,...
View ArticleKeras multiple inputs masking
I am building a LSTM model with multiple inputs (the number is given by n_inputs). I scaled the inputs in (0, 1) and replaced all the NaN of the inputs with -1. Now I want the model to ignore such NaN...
View Article
More Pages to Explore .....