Define layers for 1 layer nn to discriminate between Iris-virginica vs. others, using only petal length and petal width as input features

define_layer.py

# define training constants
learning_rate = 1
number_of_epochs = 5000

np.random.seed(48) # set seed value so that the results are reproduceable
                   # (weights will now be initailzaed to the same pseudo-random numbers, each time)

# Our network architecture has the shape: 
#                       (input)--> [Linear->Sigmoid] -->(output)  


#------ LAYER-1 ----- define output layer that takes in training data 
Z1 = LinearLayer(input_shape=X_train.shape, n_out=1, ini_type='plain')
A1 = SigmoidLayer(Z1.Z.shape)