[Python] Is Relu includes linear computation in TensorFlow?

In Tensorflow:

"model = Sequential([
Flatten(input_shape=(28, 28)),
Dense(128, activation='relu'),
Dense(64, activation='relu'),
Dense(10, activation='softmax')


])

In pytorch:

"self.l1 = nn.Linear(784, 128)
self.relu = nn.ReLU()
self.l2 = nn.Linear(128, 64)
self.relu2 = nn.ReLU()
self.output = nn.Linear(64, 10)"


Why are we applying the nn.Linear in Pytorch but not in Tensorflow?

Continue reading...