pytorch 入门

安装

输入 conda install pytorch torchvision cuda80 -c soumith
参考资料
测试：

$ python
>>> import pytorch

线性回归

1. torch.manual_seed的意义：产生相同的随机数，从而保证每次训练出来的模型是一样的 https://blog.csdn.net/zh515858237/article/details/83901179

# -*- coding:utf8 -*-
import torch
import numpy as np
import torch.autograd 
from torch.autograd import Variable
import matplotlib.pyplot as plt

torch.manual_seed(2017)
# 读入数据 x 和 y
x_train = np.array([[3.3], [4.4], [5.5], [6.71], [6.93], [4.168],
                    [9.779], [6.182], [7.59], [2.167], [7.042],
                    [10.791], [5.313], [7.997], [3.1]], dtype=np.float32)

y_train = np.array([[1.7], [2.76], [2.09], [3.19], [1.694], [1.573],
                    [3.366], [2.596], [2.53], [1.221], [2.827],
                    [3.465], [1.65], [2.904], [1.3]], dtype=np.float32)
# 转换成 Tensor
x_train = torch.from_numpy(x_train)
y_train = torch.from_numpy(y_train)

# 定义参数 w 和 b
w = Variable(torch.randn(1), requires_grad=True) # 随机初始化
b = Variable(torch.zeros(1), requires_grad=True) # 使用 0 进行初始化

# 构建线性回归模型
x_train = Variable(x_train)
y_train = Variable(y_train)

def linear_model(x):
    return x * w + b

# 计算误差
def get_loss(y_, y):
    return torch.mean((y_ - y_train) ** 2)


for e in range(10): # 进行 10 次更新
    y_ = linear_model(x_train)
    loss = get_loss(y_, y_train)
    loss.backward()
    # print('w.grad',w.grad)
    # print('b.grad',b.grad) 
    w.data = w.data - 1e-2 * w.grad.data # 更新 w
    b.data = b.data - 1e-2 * b.grad.data # 更新 b 
    print('epoch: {}, loss: {}'.format(e, loss))
    w.grad.zero_() 
    b.grad.zero_()

y_ = linear_model(x_train)

plt.plot(x_train.data.numpy(), y_train.data.numpy(), 'bo', label='real')
plt.plot(x_train.data.numpy(), y_.data.numpy(), 'ro', label='estimated')
plt.show()
plt.legend()

卷积

# -*- coding:utf8 -*-
import numpy as np
import torch
from torch import nn
from torch.autograd import Variable
import torch.nn.functional as F
from PIL import Image
import matplotlib.pyplot as plt
im = Image.open('./cat.jpg').convert('L') # 读入一张灰度图的图片
im = np.array(im, dtype='float32') # 将其转换为一个矩阵
# 可视化图片
plt.imshow(im.astype('uint8'), cmap='gray')
plt.show()

# 将图片矩阵转化为 pytorch tensor，并适配卷积输入的要求
im = torch.from_numpy(im.reshape((1, 1, im.shape[0], im.shape[1])))  # (1,1,311, 481)

# 使用 nn.Conv2d
conv1 = nn.Conv2d(1, 1, 3, bias=False) # 定义卷积

sobel_kernel = np.array([[-1, -1, -1], [-1, 8, -1], [-1, -1, -1]], dtype='float32') # 定义轮廓检测算子 (3, 3)
sobel_kernel = sobel_kernel.reshape((1, 1, 3, 3)) # 适配卷积的输入输出
conv1.weight.data = torch.from_numpy(sobel_kernel) # 给卷积的 kernel 赋值

edge1 = conv1(Variable(im)) # 作用在图片上  ('edge1:', (1, 1, 309, 479))
print("edge1:",edge1.size())
edge1 = edge1.data.squeeze().numpy() # 将输出转换为图片的格式

plt.imshow(edge1, cmap='gray')
plt.show()

# 使用 F.conv2d
sobel_kernel = np.array([[-1, -1, -1], [-1, 8, -1], [-1, -1, -1]], dtype='float32') # 定义轮廓检测算子
sobel_kernel = sobel_kernel.reshape((1, 1, 3, 3)) # 适配卷积的输入输出
weight = Variable(torch.from_numpy(sobel_kernel))

edge2 = F.conv2d(Variable(im), weight) # 作用在图片上  ('edge2:', (1, 1, 309, 479))

print("edge2:",edge2.size())
edge2 = edge2.data.squeeze().numpy() # 将输出转换为图片的格式

plt.imshow(edge2, cmap='gray')
plt.show()

资源

• pytorch 预训练的模型 https://pytorch.org/docs/stable/torchvision/models.html

• pytorch 中文文档 https://ptorch.com/docs/1/torch-nn