Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- class NeuralNetwork:
- def __init__(self):
- self.layers = []
- self.loss = None
- self.loss_prime = None
- def add(self, layer):
- self.layers.append(layer)
- return self
- def use(self, loss, loss_prime):
- self.loss = loss
- self.loss_prime = loss_prime
- return self
- def fit(self, x_train, y_train, epochs, learning_rate):
- samples = len(x_train)
- for i in range(epochs): # each epoch represents one iteration over all samples
- err = 0
- for j in range(samples): # our gradient descent logic from earlier in the article
- output = x_train[j]
- for layer in self.layers:
- output = layer.forward_propagation(output)
- err += self.loss(y_train[j], output)
- error = self.loss_prime(y_train[j], output)
- for layer in reversed(self.layers):
- error = layer.backward_propagation(error, learning_rate)
- err /= samples
- print('epoch %d/%d error=%f' % (i+1, epochs, err))
- return self
- def predict(self, input_data):
- samples = len(input_data)
- result = []
- for i in range(samples): # basically running the forward propagation of all layers to get the result
- output = input_data[i]
- for layer in self.layers:
- output = layer.forward_propagation(output)
- result.append(output)
- return result
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement