This is a beginner level question on scikit learn’s test-train split module.
I am working trying to feed in 2 inputs to the input layer of my neural network, but I am not able to get the input matrix’s dimensions correct! What change I should implement to get this working!
X2 are my inputs and y is my output. e.g. I wish to input X1 = 3.14 and X2 = -1.0 and my y should be equal to 0.0 . This way I want to train my network.
As of now I am getting an error saying:
ValueError: Found input variables with inconsistent numbers of samples: [2, 126]
import numpy as np X1 = np.arange(0,4*np.pi,0.1) # start,stop,step X2 = np.cos(X1) y = np.sin(X1) X = [X1, X2] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.4)
For my network I will further build on a deep NN using keras, which will follow further code from here on.
model = Sequential() model.add(Dense(10, input_dim=2, activation='relu'))
Your X1 and X2 are not vectors
X1.shape – (126,)
When you created array X, you added two lists in two rows and got (2,126) shape.
but you need input X shape – (126,2), you features should be in columns.
first column X1, second column X2
You can simple transpose X array in your case, use this line instead:
X = np.array([X1, X2]).T