代码拉取完成,页面将自动刷新
# coding:utf-8
# pytorch测试
# 用numpy实现神经网络
def WU():
import numpy as np
N, D_in, H, D_out = 64, 1000, 100, 10
x = np.random.randn(N, D_in)
y = np.random.randn(N, D_out)
w1 = np.random.randn(D_in, H)
w2 = np.random.randn(H, D_out)
learning_rate = 1e-6
for t in range(500):
h = x.dot(w1)
h_relu = np.maximum(h, 0)
y_pred = h_relu.dot(w2)
loss = np.square(y_pred - y).sum()
print(t, loss)
grad_y_pred = 2.0 * (y_pred - y)
grad_w2 = h_relu.T.dot(grad_y_pred)
grad_h_relu = grad_y_pred.dot(w2.T)
grad_h = grad_h_relu.copy()
grad_h[h < 0] = 0
grad_w1 = x.T.dot(grad_h)
w1 -= learning_rate * grad_w1
w2 -= learning_rate * grad_w2
print(y - y_pred)
# 张量版的神经网络
def tensor_nn():
import torch
dtype = torch.float
device = torch.device("cpu")
N, D_in, H, D_out = 64, 1000, 100, 10
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)
w1 = torch.randn(D_in, H, device=device, dtype=dtype)
w2 = torch.randn(H, D_out, device=device, dtype=dtype)
learning_rate = 1e-6
for t in range(500):
h = x.mm(w1)
h_relu = h.clamp(min=0)
y_pred = h_relu.mm(w2)
loss = (y_pred - y).pow(2).sum().item()
if t % 100 == 99:
print(t, loss)
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)
w1 -= learning_rate * grad_w1
w2 -= learning_rate * grad_w2
# 自动梯度
def AG():
import torch
dtype = torch.float
device = torch.device("cpu")
N, D_in, H, D_out = 64, 1000, 100, 10
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)
w1 = torch.randn(D_in, H, device=device, dtype=dtype, requires_grad=True)
w2 = torch.randn(H, D_out, device=device, dtype=dtype, requires_grad=True)
learning_rate = 1e-6
for t in range(500):
y_pred = x.mm(w1).clamp(min=0).mm(w2)
loss = (y_pred - y).pow(2).sum()
if t % 100 == 99:
print(t, loss)
loss.backward()
with torch.no_grad():
w1 -= learning_rate * w1.grad
w2 -= learning_rate * w2.grad
w1.grad.zero_()
w2.grad.zero_()
# 自己定义前向后向过程
def DefFB():
import torch
class MyReLU(torch.autograd.Function):
@staticmethod
def forward(ctx, input):
ctx.save_for_backward(input)
return input.clamp(min=0)
@staticmethod
def backward(ctx, grad_output):
input, = ctx.saved_tensors
grad_input = grad_output.clone()
grad_input[input < 0] = 0
return grad_input
dtype = torch.float
device = torch.device("cpu")
N, D_in, H, D_out = 64, 1000, 100, 10
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)
w1 = torch.randn(D_in, H, device=device, dtype=dtype, requires_grad=True)
w2 = torch.randn(H, D_out, device=device, dtype=dtype, requires_grad=True)
learning_rate = 1e-6
for t in range(500):
relu = MyReLU.apply
y_pred = relu(x.mm(w1)).mm(w2)
loss = (y_pred - y).pow(2).sum()
if t % 100 == 99:
print(t, loss)
loss.backward()
with torch.no_grad():
w1 -= learning_rate * w1.grad
w2 -= learning_rate * w2.grad
w1.grad.zero_()
w2.grad.zero_()
# 用nn模块定义神经网络
def nn_test():
import torch
N, D_in, H, D_out = 64, 1000, 100, 10
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
model = torch.nn.Sequential(
torch.nn.Linear(D_in, H),
torch.nn.ReLU(),
torch.nn.Linear(H, D_out),
)
loss_fn = torch.nn.MSELoss(reduction = "sum")
learning_rate = 1e-4
for t in range(500):
y_pred = model(x)
loss = loss_fn(y_pred, y)
if t % 100 == 99:
print(t, loss)
model.zero_grad()
loss.backward()
with torch.no_grad():
for param in model.parameters():
param -= learning_rate*param.grad
if __name__ == "__main__":
WU()
tensor_nn()
AG()
DefFB()
nn_test()
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。