基于Tensor自动实现的简单网络

# __author: Y
# date: 2019/12/11


# h = W_1x+b_1
# a = max(0, h)
# Yhat = W_2a+b_2

# - forward pass
# -loss
# -backward pass

import numpy as np
import torch
# N是有多少个训练数据 D_in是输入维度
N , D_in, H, D_out = 64, 1000, 100, 10
# 随机创建一些训练数据
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)

w1 = torch.randn(D_in, H, requires_grad=True)
w2 = torch.randn(H, D_out, requires_grad=True)

learning_rate = 1e-6
for it in range(500):
    # Forward pass
    # h = x.mm(w1)  # N*H
    # h_relu = h.clamp(min=0)  # N*H
    # y_pred = h_relu.mm(w2) # N*D_out
    y_pred = x.mm(w1).clamp(min=0).mm(w2)

    # compute loss
    loss = (y_pred - y).pow(2).sum()  # computation graph
    print(it, loss.item())

    # Backward pass
    # compute the gradient
    # grad_y_pred = 2.0 * (y_pred-y)
    # grad_w2 = h_relu.t().mm(grad_y_pred)
    # grad_h_relu = grad_y_pred.mm(w2.t())
    # grad_h = grad_h_relu.clone()
    # grad_h[h<0] = 0
    # grad_w1 = x.t().mm(grad_h)
    loss.backward()  # 这一句就做了上面所有的操作


    # update weights of w1 and w2
    # w1 -= learning_rate*grad_w1
    # w2 -= learning_rate*grad_w2
    with torch.no_grad():
        w1 -= learning_rate * w1.grad
        w2 -= learning_rate * w2.grad
        w1.grad.zero_()  # 保证每次求得grad不会累加
        w2.grad.zero_()

结合前两篇博客看更容易理解一些。