def apply_activation_fun(data,activation="relu"): if activation=="relu": return A.relu(data) elif activation == "softmax": return A.softmax(data) elif activation == "tanh": return A.tanh(data) elif activation == "softplus": return A.softplus(data) elif activation == "swish": return A.swish(data) elif activation == "sigmoid": return A.sigmoid(data)
def feed_forward(self, layer): """Feeds forward the layers values""" for i in range(len(self.bias.weights)): layer.nodes[i].value = 0 for i in range(len(self.nodes)): for weight in range(len(self.nodes[i].weights)): layer.nodes[weight].value += self.nodes[i].value * self.nodes[ i].weights[weight] for weight in range(len(self.bias.weights)): layer.nodes[weight].value += self.bias.weights[weight] for w in range(len(layer.nodes)): # use tanh as our activation function layer.nodes[w].value = Activation.tanh(layer.nodes[w].value)