ayoubbenaissa

n = 100
for epoch in range(n):
	epoch +=1
	#convert numpy array into torch variable:
	inputs = Variable(torch.from_numpy(x_train))
	labels = Variable(torch.from_numpy(y_train))

	#clear gradient w.r.t parameters:
	optimizer.zero_grad()

ayoubbenaissa

#Loss function:
criterion = nn.MSELoss()

#optimizer:
learning_rate = 0.01
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

ayoubbenaissa

#create class:
class LinearRegressionModel (nn.Module):
	def __init__(self, input_size, output_size):
		super(LinearRegressionModel, self).__init__()
		self.linear = nn.Linear(1, 1)
	def forward(self, x):
		out = self.linear(x)
		return out

#create object (instance from the class)

ayoubbenaissa

y = [2*i + 1 for i in range(11)] #y vector (y = 2x+1)

y_train = np.array(y, dtype=np.float32) #convert into numpy array

y_train = y_train.reshape(-1, 1)  

ayoubbenaissa

x = [i for i in range(11)] #x is a set

x_train = np.array(x, dtype=np.float32) #translate x into numpy array

x_train = x_train.reshape(-1, 1) #rasgape x_train to be an array of shape (11, 1)

ayoubbenaissa

#initialize the ANN
classifier = Sequential()

#add input layer and first hidden layer
classifier.add(Dense(activation="relu", input_dim=11, units=6, kernel_initializer="uniform"))

#add second hidden layer
classifier.add(Dense(activation="relu", units=6, kernel_initializer="uniform"))

#output layer:

ayoubbenaissa

#Creating the NN:
import keras
#sequential => initialize the neural network
from keras.models import Sequential
#Dense => build layers of the neural network
from keras.layers import Dense