更多见深度学习.pytorch
目录
1.4依赖于叶子节点的节点，requires_grad默认为true
1.torch.autograd
1.1torch.autograd.barkward()
自动求梯度。
参数：tensor:用于求导的张量；retain_graph:保存计算图；create_graph:创建导数计算图，用于高阶求导；grad_tensors:多梯度权重；
# ====================================== retain_graph ==============================================
# flag = True
flag = False
if flag:
w = torch.tensor([1.], requires_grad=True)
x = torch.tensor([2.], requires_grad=True)
a = torch.add(w, x)
b = torch.add(w, 1)
y = torch.mul(a, b)
y.backward(retain_graph=True)
print(w.grad)
y.backward()
#此处为什么等于10
print(w.grad)如果不设置retain_graph=True,第二次调用y.backward()会报错。因为：？？
# ====================================== grad_tensors ==============================================
flag = True
# flag = False
if flag:
w = torch.tensor([1.], requires_grad=True)
x = torch.tensor([2.], requires_grad=True)
a = torch.add(w, x) # retain_grad()
b = torch.add(w, 1)
y0 = torch.mul(a, b) # y0 = (x+w) * (w+1)
y1 = torch.add(a, b) # y1 = (x+w) + (w+1) dy1/dw = 2
loss = torch.cat([y0, y1], dim=0) # [y0, y1]
grad_tensors = torch.tensor([1., 2.])
loss.backward(gradient=grad_tensors) # gradient 传入 torch.autograd.backward()中的grad_tensors
print(w.grad)输出：
tensor([9.])倘若改变权重，即：
grad_tensors = torch.tensor([1., 3.])
w的梯度变为11.
tensor([11.])1.2torch.autograd.grad()
求取梯度。
参数：
outputs:用于求导的张量
inputs:需要梯度的张量
create_graph：创建导数计算图
retain_graph:保存计算图
grad_outputs:多梯度权重
# ====================================== autograd.gard ==============================================
flag = True
# flag = False
if flag:
x = torch.tensor([3.], requires_grad=True)
y = torch.pow(x, 2) # y = x**2
grad_1 = torch.autograd.grad(y, x, create_graph=True) # grad_1 = dy/dx = 2x = 2 * 3 = 6
print(grad_1)
grad_2 = torch.autograd.grad(grad_1[0], x) # grad_2 = d(dy/dx)/dx = d(2x)/dx = 2
print(grad_2)输出：
(tensor([6.], grad_fn=<MulBackward0>),)
(tensor([2.]),)
说明：
计算grad_1时需要设置create_graph=true，保存导数计算图，这样才能继续计算grad_1的导数。
grad_1是元组，元组第一个元素是导数值，所以计算grad_2时需要取出grad_1的导数值即grad_1[0]。
1.3梯度不会自动清零
# ====================================== tips: 1 ==============================================
flag = True
# flag = False
if flag:
w = torch.tensor([1.], requires_grad=True)
x = torch.tensor([2.], requires_grad=True)
for i in range(4):
a = torch.add(w, x)
b = torch.add(w, 1)
y = torch.mul(a, b)
y.backward()
print(w.grad)
#w.grad.zero_()输出：
tensor([5.])
tensor([10.])
tensor([15.])
tensor([20.])如果不手动清零，w.grad就会累加。添加手动清零，zero_下划线代表原地操作。
w.grad.zero_()手动清零后,输出：
tensor([5.])
tensor([5.])
tensor([5.])
tensor([5.])1.4依赖于叶子节点的节点，requires_grad默认为true
# ====================================== tips: 2 ==============================================
flag = True
# flag = False
if flag:
w = torch.tensor([1.], requires_grad=True)
x = torch.tensor([2.], requires_grad=True)
a = torch.add(w, x)
b = torch.add(w, 1)
y = torch.mul(a, b)
print(a.requires_grad, b.requires_grad, y.requires_grad)输出：
True True True
1.5叶子节点不执行in-place
首先介绍一下什么是原地操作。
# ====================================== tips: 3 ==============================================
flag = True
# flag = False
if flag:
a = torch.ones((1, ))
print(id(a), a)
a = a + torch.ones((1, ))
print(id(a), a)输出
1768719029576 tensor([1.])
1768720256840 tensor([2.])输出的两个a地址不相同，所以不是原地操作
# ====================================== tips: 3 ==============================================
flag = True
# flag = False
if flag:
a = torch.ones((1, ))
print(id(a), a)
a += torch.ones((1, ))
print(id(a), a)输出：
2581512492360 tensor([1.])
2581512492360 tensor([2.])两个a的地址相同，所以该操作为原地操作。
因为计算中间变量的梯度，会用到叶子节点，会保存叶子节点的地址。如果叶子节点进行了in-place操作，计算中间变量的梯度就会报错。
2.逻辑回归
# -*- coding: utf-8 -*-
"""
# @file name : lesson-05-Logsitic-Regression.py
# @author : tingsongyu
# @date : 2019-09-03 10:08:00
# @brief : 逻辑回归模型训练
"""
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import numpy as np
torch.manual_seed(10)
# ============================ step 1/5 生成数据 ============================
sample_nums = 100
mean_value = 1.7
bias = 1
n_data = torch.ones(sample_nums, 2)
x0 = torch.normal(mean_value * n_data, 1) + bias # 类别0 数据 shape=(100, 2)
y0 = torch.zeros(sample_nums) # 类别0 标签 shape=(100)
x1 = torch.normal(-mean_value * n_data, 1) + bias # 类别1 数据 shape=(100, 2)
y1 = torch.ones(sample_nums) # 类别1 标签 shape=(100)
train_x = torch.cat((x0, x1), 0)
train_y = torch.cat((y0, y1), 0)
# ============================ step 2/5 选择模型 ============================
class LR(nn.Module):
def __init__(self):
super(LR, self).__init__()
self.features = nn.Linear(2, 1)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
x = self.features(x)
x = self.sigmoid(x)
return x
lr_net = LR() # 实例化逻辑回归模型
# ============================ step 3/5 选择损失函数 ============================
loss_fn = nn.BCELoss()
# ============================ step 4/5 选择优化器 ============================
lr = 0.01 # 学习率
optimizer = torch.optim.SGD(lr_net.parameters(), lr=lr, momentum=0.9)
# ============================ step 5/5 模型训练 ============================
for iteration in range(1000):
# 前向传播
y_pred = lr_net(train_x)
# 计算 loss
loss = loss_fn(y_pred.squeeze(), train_y)
# 反向传播
loss.backward()
# 更新参数
optimizer.step()
# 清空梯度
optimizer.zero_grad()
# 绘图
if iteration % 20 == 0:
mask = y_pred.ge(0.5).float().squeeze() # 以0.5为阈值进行分类
correct = (mask == train_y).sum() # 计算正确预测的样本个数
acc = correct.item() / train_y.size(0) # 计算分类准确率
plt.scatter(x0.data.numpy()[:, 0], x0.data.numpy()[:, 1], c='r', label='class 0')
plt.scatter(x1.data.numpy()[:, 0], x1.data.numpy()[:, 1], c='b', label='class 1')
w0, w1 = lr_net.features.weight[0]
w0, w1 = float(w0.item()), float(w1.item())
plot_b = float(lr_net.features.bias[0].item())
plot_x = np.arange(-6, 6, 0.1)
plot_y = (-w0 * plot_x - plot_b) / w1
plt.xlim(-5, 7)
plt.ylim(-7, 7)
plt.plot(plot_x, plot_y)
plt.text(-5, 5, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color': 'red'})
plt.title("Iteration: {}\nw0:{:.2f} w1:{:.2f} b: {:.2f} accuracy:{:.2%}".format(iteration, w0, w1, plot_b, acc))
plt.legend()
plt.show()
plt.pause(0.5)
if acc > 0.99:
break
195
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
