前言
Numpy提供了n维数组对象和许多计算这些数组的函数。Numpy是一个通用的科学计算框架,但是它没有提供任何关于计算图、深度学习、梯度下降等的方法,给快速搭建神经网络带来了困难,我们可以使用Numpy来简单的搭建一个两层的神经网络,该网络具有前向传递和反向传播。
案例
# -*- coding: utf-8 -*-
import numpy as np
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
# Create random input and output data
x = np.random.randn(N, D_in) # 64*1000
y = np.random.randn(N, D_out) # 64*10
# Randomly initialize weights
w1 = np.random.randn(D_in, H) # 1000*100
w2 = np.random.randn(H, D_out) #100*10
learning_rate = 1e-6
for t in range(500):
# Forward pass: compute predicted y
h = x.dot(w1) # dot()返回的是两个数组的点积(dot product) 64*100
h_relu = np.maximum(h, 0) # X和Y逐位进行比较,选择最大值,最少接受两个参数 # 64*100
y_pred = h_relu.dot(w2) # 64*10
# # Compute and print loss
loss = np.square(y_pred - y).sum() # a num
print(t, loss)
# # Backprop to compute gradients of w1 and w2 with respect to loss
grad_y_pred = 2.0 * (y_pred - y) # 64*10
grad_w2 = h_relu.T.dot(grad_y_pred) # 100*10
grad_h_relu = grad_y_pred.dot(w2.T) # 64*100
grad_h = grad_h_relu.copy()
grad_h[h < 0] = 0 # 64*100
grad_w1 = x.T.dot(grad_h) # 1000*100
# Update weights
w1 -= learning_rate * grad_w1
w2 -= learning_rate * grad_w2