这篇教程PyTorch一小时掌握之autograd机制篇写得很实用，希望能帮到您。
概述PyTorch 干的最厉害的一件事情就是帮我们把反向传播全部计算好了.
代码实现
手动定义求导import torch# 方法一x = torch.randn(3, 4, requires_grad=True)# 方法二x = torch.randn(3,4)x.requires_grad = True b = torch.randn(3, 4, requires_grad=True)t = x + by = t.sum()print(y)print(y.backward())print(b.grad)print(x.requires_grad)print(b.requires_grad)print(t.requires_grad) 输出结果:
tensor(1.1532, grad_fn=<SumBackward0>)
None
tensor([[1., 1., 1., 1.],
[1., 1., 1., 1.],
[1., 1., 1., 1.]])
True
True
True
计算流量# 计算流量x = torch.rand(1)w = torch.rand(1, requires_grad=True)b = torch.rand(1, requires_grad=True)y = w * xz = y + bprint(x.requires_grad, w.requires_grad,b.requires_grad, z.requires_grad)print(x.is_leaf, w.is_leaf, b.is_leaf, y.is_leaf,z.is_leaf) 输出结果:
False True True True
True True True False False
反向传播计算# 反向传播z.backward(retain_graph= True) # 如果不清空会累加起来print(w.grad)print(b.grad) 输出结果:
tensor([0.1485])
tensor([1.])
线性回归
导包import numpy as npimport torchimport torch.nn as nn
构造 x, y# 构造数据X_values = [i for i in range(11)]X_train = np.array(X_values, dtype=np.float32)X_train = X_train.reshape(-1, 1)print(X_train.shape) # (11, 1)y_values = [2 * i + 1 for i in X_values]y_train = np.array(y_values, dtype=np.float32)y_train = y_train.reshape(-1,1)print(y_train.shape) # (11, 1) 输出结果:
(11, 1)
(11, 1)
构造模型# 构造模型class LinerRegressionModel(nn.Module): def __init__(self, input_dim, output_dim): super(LinerRegressionModel, self).__init__() self.liner = nn.Linear(input_dim, output_dim) def forward(self, x): out = self.liner(x) return outinput_dim = 1output_dim = 1model = LinerRegressionModel(input_dim, output_dim)print(model) 输出结果:
LinerRegressionModel(
(liner): Linear(in_features=1, out_features=1, bias=True)
)
参数 & 损失函数# 超参数enpochs = 1000learning_rate = 0.01# 损失函数optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)criterion = nn.MSELoss()
训练模型# 训练模型for epoch in range(enpochs): # 转成tensor inputs = torch.from_numpy(X_train) labels = torch.from_numpy(y_train) # 梯度每次迭代清零 optimizer.zero_grad() # 前向传播 outputs = model(inputs) # 计算损失 loss = criterion(outputs, labels) # 反向传播 loss.backward() # 更新参数 optimizer.step() if epoch % 50 == 0: print("epoch {}, loss {}".format(epoch, loss.item()))输出结果:
epoch 0, loss 114.47456359863281
epoch 50, loss 0.00021522105089388788
epoch 100, loss 0.00012275540211703628
epoch 150, loss 7.001651829341426e-05
epoch 200, loss 3.9934264350449666e-05
epoch 250, loss 2.2777328922529705e-05
epoch 300, loss 1.2990592040296178e-05
epoch 350, loss 7.409254521917319e-06
epoch 400, loss 4.227155841363128e-06
epoch 450, loss 2.410347860859474e-06
epoch 500, loss 1.3751249525739695e-06
epoch 550, loss 7.844975016269018e-07
epoch 600, loss 4.4756839656656666e-07
epoch 650, loss 2.5517596213830984e-07
epoch 700, loss 1.4577410922811396e-07
epoch 750, loss 8.30393886985803e-08
epoch 800, loss 4.747753479250605e-08
epoch 850, loss 2.709844615367274e-08
epoch 900, loss 1.5436164346738224e-08
epoch 950, loss 8.783858973515635e-09
完整代码import numpy as npimport torchimport torch.nn as nn# 构造数据X_values = [i for i in range(11)]X_train = np.array(X_values, dtype=np.float32)X_train = X_train.reshape(-1, 1)print(X_train.shape) # (11, 1)y_values = [2 * i + 1 for i in X_values]y_train = np.array(y_values, dtype=np.float32)y_train = y_train.reshape(-1,1)print(y_train.shape) # (11, 1)# 构造模型class LinerRegressionModel(nn.Module): def __init__(self, input_dim, output_dim): super(LinerRegressionModel, self).__init__() self.liner = nn.Linear(input_dim, output_dim) def forward(self, x): out = self.liner(x) return outinput_dim = 1output_dim = 1model = LinerRegressionModel(input_dim, output_dim)print(model)# 超参数enpochs = 1000learning_rate = 0.01# 损失函数optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)criterion = nn.MSELoss()# 训练模型for epoch in range(enpochs): # 转成tensor inputs = torch.from_numpy(X_train) labels = torch.from_numpy(y_train) # 梯度每次迭代清零 optimizer.zero_grad() # 前向传播 outputs = model(inputs) # 计算损失 loss = criterion(outputs, labels) # 反向传播 loss.backward() # 更新参数 optimizer.step() if epoch % 50 == 0: print("epoch {}, loss {}".format(epoch, loss.item()))到此这篇关于PyTorch一小时掌握之autograd机制篇的文章就介绍到这了,更多相关PyTorch autograd内容请搜索51zixue.net以前的文章或继续浏览下面的相关文章希望大家以后多多支持51zixue.net！
pytorch教程resnet.py的实现文件源码分析
浅析form标签中的GET和POST提交方式区别 |
