验证安装

from __future__ import print_function
import torch
x = torch.rand(5, 3)
print(x)

# 验证cuda可以使用
torch.cuda.is_available()

基本操作

# resize(=tf.reshape)
x = torch.randn(4, 4)
y = x.view(16)
z = x.view(-1, 8)  # the size -1 is inferred from other dimensions

# torch.Size([4, 4]) torch.Size([16]) torch.Size([2, 8])
print(x.size(), y.size(), z.size())

# 查看变量类型
print(a.dtype)

# 查看变量位置
print(a.device)
a.is_cuda

# 更换device位置
cuda0 = torch.device('cuda:0')
d = torch.randn(2, device=cuda2)
e = torch.randn(2).to(cuda2)
f = torch.randn(2).cuda(cuda2)

# Variables wrap a Tensor
# requires_grad indicates whether a variable is trainable.
x = Variable(torch.ones(2, 2), requires_grad=True)
# Variable containing:
# 1  1
# 1  1
# [torch.FloatTensor of size 2x2]

view()

# Returns a new tensor with the same data as the self tensor but of a different shape.
>>> x = torch.randn(4, 4)
>>> x.size()
torch.Size([4, 4])
>>> y = x.view(16)
>>> y.size()
torch.Size([16])
>>> z = x.view(-1, 8)  # the size -1 is inferred from other dimensions
>>> z.size()
torch.Size([2, 8])

permute()

# Permute the dimensions of this tensor.
>>> x = torch.randn(2, 3, 5)
>>> x.size()
torch.Size([2, 3, 5])
>>> x.permute(2, 0, 1).size()
torch.Size([5, 2, 3])

repeat()

# Repeats this tensor along the specified dimensions.
>>> x = torch.tensor([1, 2, 3])
>>> x.repeat(4, 2)
tensor([[ 1,  2,  3,  1,  2,  3],
        [ 1,  2,  3,  1,  2,  3],
        [ 1,  2,  3,  1,  2,  3],
        [ 1,  2,  3,  1,  2,  3]])
>>> x.repeat(4, 2, 1).size()
torch.Size([4, 2, 3])

torch.zeros()

# Returns a tensor filled with the scalar value 0, with the shape defined by the variable argument sizes.
>>> torch.zeros(2, 3)
tensor([[ 0.,  0.,  0.],
        [ 0.,  0.,  0.]])

>>> torch.zeros(5)
tensor([ 0.,  0.,  0.,  0.,  0.])

torch.mul()

# Multiplies each element of the input input with the scalar value and returns a new resulting tensor.

>>> a = torch.randn(3)
>>> a
tensor([ 0.2015, -0.4255,  2.6087])
>>> torch.mul(a, 100)
tensor([  20.1494,  -42.5491,  260.8663])

torch.bmm()

# Batch Matrix x Matrix
# Size 10x3x5
batch1 = torch.randn(10, 3, 4)
batch2 = torch.randn(10, 4, 5)
r = torch.bmm(batch1, batch2)

# Batch Matrix + Matrix x Matrix
# Performs a batch matrix-matrix product
# 3x4 + (5x3x4 X 5x4x2 ) -> 5x3x2
M = torch.randn(3, 2)
batch1 = torch.randn(5, 3, 4)
batch2 = torch.randn(5, 4, 2)
r = torch.addbmm(M, batch1, batch2)

torch.cat()

# Concatenates the given sequence of seq tensors in the given dimension. All tensors must either have the same shape (except in the concatenating dimension) or be empty.

>>> x = torch.randn(2, 3)
>>> x
tensor([[ 0.6580, -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497]])
>>> torch.cat((x, x, x), 0)
tensor([[ 0.6580, -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497],
        [ 0.6580, -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497],
        [ 0.6580, -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497]])
>>> torch.cat((x, x, x), 1)
tensor([[ 0.6580, -1.0969, -0.4614,  0.6580, -1.0969, -0.4614,  0.6580,
         -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497, -0.1034, -0.5790,  0.1497, -0.1034,
         -0.5790,  0.1497]])

torch.transpose(input, dim0, dim1)->Tensor

# Returns a tensor that is a transposed version of input. The given dimensions dim0 and dim1 are swapped.
>>> x = torch.randn(2, 3)
>>> x
tensor([[ 1.0028, -0.9893,  0.5809],
        [-0.1669,  0.7299,  0.4942]])
>>> torch.transpose(x, 0, 1)
tensor([[ 1.0028, -0.1669],
        [-0.9893,  0.7299],
        [ 0.5809,  0.4942]])

torch.squeeze()

# 对数据的维度进行压缩,去掉维数为1的的维度,比如是一行或者一列这种,一个一行三列(1,3)的数去掉第一个维数为一的维度之后就变成(3)行。squeeze(a)就是将a中所有为1的维度删掉。不为1的维度没有影响。

>>> x = torch.zeros(2, 1, 2, 1, 2)
>>> x.size()
torch.Size([2, 1, 2, 1, 2])
>>> y = torch.squeeze(x)
>>> y.size()
torch.Size([2, 2, 2])
>>> y = torch.squeeze(x, 0)
>>> y.size()
torch.Size([2, 1, 2, 1, 2])
>>> y = torch.squeeze(x, 1)
>>> y.size()
torch.Size([2, 2, 1, 2])

touch.nn.Linear

#Applies a linear transformation to the incoming data:y = xAT+b
touch.nn.Linear(in_features, out_features, bias=True)

矩阵转置

>>> x = torch.randn(2, 3)
>>> x
tensor([[ 0.4875,  0.9158, -0.5872],
        [ 0.3938, -0.6929,  0.6932]])
>>> torch.t(x)
tensor([[ 0.4875,  0.3938],
        [ 0.9158, -0.6929],
        [-0.5872,  0.6932]])

类型转换

# cpu->gpu
data.cuda()

# gpu->cpu
data.cpu()

# Tensor–>Numpy.ndarray
data.numpy()

# Numpy.ndarray–>Tensor
torch.from_numpy(data)

# torch.double()将该tensor投射为double类型
newtensor = tensor.double()

# torch.float()将该tensor投射为float类型
newtensor = tensor.float()

torch.unsqueeze()

# 对数据维度进行扩充。给指定位置加上维数为一的维度,比如原本有个三行的数据(3),在0的位置加了一维就变成一行三列(1,3)。
>>> x = torch.tensor([1, 2, 3, 4])
>>> torch.unsqueeze(x, 0)
tensor([[ 1,  2,  3,  4]])
>>> torch.unsqueeze(x, 1)
tensor([[ 1],
        [ 2],
        [ 3],
        [ 4]])

简单的神经网络结构

import torch
import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


net = Net()
print(net)
# 输出网络结构

input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)
# 输出预测结果

params = list(net.parameters())
print(len(params))
print(params[0].size())  # conv1's .weight
# The learnable parameters of a model are returned by net.parameters()

nn

import torch

# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)

# Use the nn package to define our model as a sequence of layers. nn.Sequential
# is a Module which contains other Modules, and applies them in sequence to
# produce its output. Each Linear Module computes output from input using a
# linear function, and holds internal Tensors for its weight and bias.
model = torch.nn.Sequential(
    torch.nn.Linear(D_in, H),
    torch.nn.ReLU(),
    torch.nn.Linear(H, D_out),
)

# The nn package also contains definitions of popular loss functions; in this
# case we will use Mean Squared Error (MSE) as our loss function.
loss_fn = torch.nn.MSELoss(reduction='sum')

learning_rate = 1e-4
for t in range(500):
    # Forward pass: compute predicted y by passing x to the model. Module objects
    # override the __call__ operator so you can call them like functions. When
    # doing so you pass a Tensor of input data to the Module and it produces
    # a Tensor of output data.
    y_pred = model(x)

    # Compute and print loss. We pass Tensors containing the predicted and true
    # values of y, and the loss function returns a Tensor containing the
    # loss.
    loss = loss_fn(y_pred, y)
    print(t, loss.item())

    # Zero the gradients before running the backward pass.
    model.zero_grad()

    # Backward pass: compute gradient of the loss with respect to all the learnable
    # parameters of the model. Internally, the parameters of each Module are stored
    # in Tensors with requires_grad=True, so this call will compute gradients for
    # all learnable parameters in the model.
    loss.backward()

    # Update the weights using gradient descent. Each parameter is a Tensor, so
    # we can access its gradients like we did before.
    with torch.no_grad():
        for param in model.parameters():
            param -= learning_rate * param.grad

nn.LSTM

lstm = nn.LSTM(3, 3, 2)  # Input dim is 3, output dim is 3, num_layers is 2 mean stacking two LSTMs together to form a stacked LSTM
inputs = [torch.randn(1, 3) for _ in range(5)]  # make a sequence of length 5

# initialize the hidden state.
hidden = (torch.randn(1, 1, 3),
          torch.randn(1, 1, 3))
for i in inputs:
    # Step through the sequence one element at a time.
    # after each step, hidden contains the hidden state.
    out, hidden = lstm(i.view(1, 1, -1), hidden)

# LSTMCell
rnn = nn.LSTMCell(10, 20)
input = torch.randn(6, 3, 10)
hx = torch.randn(3, 20)
cx = torch.randn(3, 20)
output = []
for i in range(6):
	hx, cx = rnn(input[i], (hx, cx))
	output.append(hx)

序列化保存模型

#save
torch.save(model.state_dict(), PATH)

#load
model = CivilNet(*args, **kwargs)
model.load_state_dict(torch.load(PATH))
model.eval()

序列化中间过程中的checkpoint

#save
torch.save({
            'epoch': epoch,
            'model_state_dict': model.state_dict(),
            'optimizer_state_dict': optimizer.state_dict(),
            'loss': loss,
            ...
            }, PATH)

#load
model = CivilNet(*args, **kwargs)
optimizer = TheOptimizerClass(*args, **kwargs)

checkpoint = torch.load(PATH)
model.load_state_dict(checkpoint['model_state_dict'])
optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
epoch = checkpoint['epoch']
loss = checkpoint['loss']

model.train()
#model.eval()

将多个模型序列化到一个文件里

#save
torch.save({
            'modelA_state_dict': modelA.state_dict(),
            'modelB_state_dict': modelB.state_dict(),
            'optimizerA_state_dict': optimizerA.state_dict(),
            'optimizerB_state_dict': optimizerB.state_dict(),
            ...
            }, PATH)

#load
modelA = TheModelAClass(*args, **kwargs)
modelB = TheModelBClass(*args, **kwargs)
optimizerA = TheOptimizerAClass(*args, **kwargs)
optimizerB = TheOptimizerBClass(*args, **kwargs)

checkpoint = torch.load(PATH)
modelA.load_state_dict(checkpoint['modelA_state_dict'])
modelB.load_state_dict(checkpoint['modelB_state_dict'])
optimizerA.load_state_dict(checkpoint['optimizerA_state_dict'])
optimizerB.load_state_dict(checkpoint['optimizerB_state_dict'])