pytorch入门学习第一课深度学习回顾

Modeling, Inference, Learning

什么是深度学习？

什么是神经网络？

激活函数

前向神经网络

Recurrent Neural Networks（RNN循环神经网络)

Seq2Seq with Attention

02 用PyTorch构建深度学习模型

深度学习模型框架概览

PyTorch可以做什么？

03 PyTorch精彩项目介绍

图像分类 ResNet

项目地址

Object Detection

项目地址

Image Style Transfer

在这里插入图片描述

项目地址

CycleGAN

项目地址

Image Captioning

项目地址

04 实战

用numpy实现两层神经网络
一个全连接ReLU神经网络，一个隐藏层，没有bias。用来从x预测y，使用L2 Loss。
这一实现完全使用numpy来计算前向神经网络，loss，和反向传播。
numpy ndarray是一个普通的n维array。它不知道任何关于深度学习或者梯度(gradient)的知识，也不知道计算图(computation graph)，只是一种用来计算数学运算的数据结构。

import numpy as np

# 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 input and output data
x = np.random.randn(N, D_in)
y = np.random.randn(N, D_out)

# Randomly initialize weights
w1 = np.random.randn(D_in, H)
w2 = np.random.randn(H, D_out)

learning_rate = 1e-6
for t in range(500):
    # Forward pass: compute predicted y
    h = x.dot(w1)
    h_relu = np.maximum(h, 0)
    y_pred = h_relu.dot(w2)

    # Compute and print loss
    loss = np.square(y_pred - y).sum()
    print(t, loss)

    # Backprop to compute gradients of w1 and w2 with respect to loss
    
    # loss = (y_pred - y) ** 2
    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)

    # Update weights
    w1 -= learning_rate * grad_w1
    w2 -= learning_rate * grad_w2

Tensor和autograd
PyTorch的一个重要功能就是autograd，也就是说只要定义了forward pass(前向神经网络)，计算了loss之后，PyTorch可以自动求导计算模型所有参数的梯度。

一个PyTorch的Tensor表示计算图中的一个节点。如果x是一个Tensor并且x.requires_grad=True那么x.grad是另一个储存着x当前梯度(相对于一个scalar，常常是loss)的向量。

import torch

dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU

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

# 创建随机的Tensor来保存输入和输出
# 设定requires_grad=False表示在反向传播的时候我们不需要计算gradient
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)

# 创建随机的Tensor和权重。
# 设置requires_grad=True表示我们希望反向传播的时候计算Tensor的gradient
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):
    # 前向传播:通过Tensor预测y；这个和普通的神经网络的前向传播没有任何不同，
    # 但是我们不需要保存网络的中间运算结果，因为我们不需要手动计算反向传播。
    y_pred = x.mm(w1).clamp(min=0).mm(w2)

    # 通过前向传播计算loss
    # loss是一个形状为(1，)的Tensor
    # loss.item()可以给我们返回一个loss的scalar
    loss = (y_pred - y).pow(2).sum()
    print(t, loss.item())

    # PyTorch给我们提供了autograd的方法做反向传播。如果一个Tensor的requires_grad=True，
    # backward会自动计算loss相对于每个Tensor的gradient。在backward之后，
    # w1.grad和w2.grad会包含两个loss相对于两个Tensor的gradient信息。
    loss.backward()

    # 我们可以手动做gradient descent(后面我们会介绍自动的方法)。
    # 用torch.no_grad()包含以下statements，因为w1和w2都是requires_grad=True，
    # 但是在更新weights之后我们并不需要再做autograd。
    # 另一种方法是在weight.data和weight.grad.data上做操作，这样就不会对grad产生影响。
    # tensor.data会我们一个tensor，这个tensor和原来的tensor指向相同的内存空间，
    # 但是不会记录计算图的历史。
    with torch.no_grad():
        w1 -= learning_rate * w1.grad
        w2 -= learning_rate * w2.grad

        # Manually zero the gradients after updating weights
        w1.grad.zero_()
        w2.grad.zero_()

PyTorch: 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

PyTorch: 自定义 nn Modules

import torch


class TwoLayerNet(torch.nn.Module):
    def __init__(self, D_in, H, D_out):
        """
        In the constructor we instantiate two nn.Linear modules and assign them as
        member variables.
        """
        super(TwoLayerNet, self).__init__()
        self.linear1 = torch.nn.Linear(D_in, H)
        self.linear2 = torch.nn.Linear(H, D_out)

    def forward(self, x):
        """
        In the forward function we accept a Tensor of input data and we must return
        a Tensor of output data. We can use Modules defined in the constructor as
        well as arbitrary operators on Tensors.
        """
        h_relu = self.linear1(x).clamp(min=0)
        y_pred = self.linear2(h_relu)
        return y_pred


# 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)

# Construct our model by instantiating the class defined above
model = TwoLayerNet(D_in, H, D_out)

# Construct our loss function and an Optimizer. The call to model.parameters()
# in the SGD constructor will contain the learnable parameters of the two
# nn.Linear modules which are members of the model.
criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-4)
for t in range(500):
    # Forward pass: Compute predicted y by passing x to the model
    y_pred = model(x)

    # Compute and print loss
    loss = criterion(y_pred, y)
    print(t, loss.item())

    # Zero gradients, perform a backward pass, and update the weights.
    optimizer.zero_grad()
    loss.backward()
    optimizer.step() 

FizzBuzz
FizzBuzz是一个简单的小游戏。游戏规则如下：从1开始往上数数，当遇到3的倍数的时候，说fizz，当遇到5的倍数，说buzz，当遇到15的倍数，就说fizzbuzz，其他情况下则正常数数。

我们可以写一个简单的小程序来决定要返回正常数值还是fizz, buzz 或者 fizzbuzz。

# One-hot encode the desired outputs: [number, "fizz", "buzz", "fizzbuzz"]
def fizz_buzz_encode(i):
    if   i % 15 == 0: return 3
    elif i % 5  == 0: return 2
    elif i % 3  == 0: return 1
    else:             return 0
    
def fizz_buzz_decode(i, prediction):
    return [str(i), "fizz", "buzz", "fizzbuzz"][prediction]

print(fizz_buzz_decode(1, fizz_buzz_encode(1)))
print(fizz_buzz_decode(2, fizz_buzz_encode(2)))
print(fizz_buzz_decode(5, fizz_buzz_encode(5)))
print(fizz_buzz_decode(12, fizz_buzz_encode(12)))
print(fizz_buzz_decode(15, fizz_buzz_encode(15)))

1
2
buzz
fizz
fizzbuzz

我们首先定义模型的输入与输出(训练数据)

import numpy as np
import torch

NUM_DIGITS = 10

# Represent each input by an array of its binary digits.
def binary_encode(i, num_digits):
    return np.array([i >> d & 1 for d in range(num_digits)])

trX = torch.Tensor([binary_encode(i, NUM_DIGITS) for i in range(101, 2 ** NUM_DIGITS)])
trY = torch.LongTensor([fizz_buzz_encode(i) for i in range(101, 2 ** NUM_DIGITS)])

然后我们用PyTorch定义模型

# Define the model
NUM_HIDDEN = 100
model = torch.nn.Sequential(
    torch.nn.Linear(NUM_DIGITS, NUM_HIDDEN),
    torch.nn.ReLU(),
    torch.nn.Linear(NUM_HIDDEN, 4)
)

为了让我们的模型学会FizzBuzz这个游戏，我们需要定义一个损失函数，和一个优化算法。 这个优化算法会不断优化（降低）损失函数，使得模型的在该任务上取得尽可能低的损失值。 损失值低往往表示我们的模型表现好，损失值高表示我们的模型表现差。 由于FizzBuzz游戏本质上是一个分类问题，我们选用Cross Entropyy Loss函数。 优化函数我们选用Stochastic Gradient Descent。

loss_fn = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr = 0.05)

以下是模型的训练代码

# Start training it
BATCH_SIZE = 128
for epoch in range(10000):
    for start in range(0, len(trX), BATCH_SIZE):
        end = start + BATCH_SIZE
        batchX = trX[start:end]
        batchY = trY[start:end]

        y_pred = model(batchX)
        loss = loss_fn(y_pred, batchY)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    # Find loss on training data
    loss = loss_fn(model(trX), trY).item()
    print('Epoch:', epoch, 'Loss:', loss)

最后我们用训练好的模型尝试在1到100这些数字上玩FizzBuzz游戏

testX = torch.Tensor([binary_encode(i, NUM_DIGITS) for i in range(1, 101)])
with torch.no_grad():
    testY = model(testX)
predictions = zip(range(1, 101), list(testY.max(1)[1].data.tolist()))

print([fizz_buzz_decode(i, x) for (i, x) in predictions])

['1', '2', 'fizz', 'buzz', 'buzz', 'fizz', '7', '8', 'fizz', 'buzz', '11', 'fizz', '13', '14', 'fizzbuzz', '16', '17', 'fizz', '19', 'buzz', 'fizz', '22', '23', 'fizz', 'buzz', '26', 'fizz', '28', '29', 'fizzbuzz', '31', '32', 'fizz', '34', 'buzz', 'fizz', '37', '38', 'fizz', 'buzz', '41', 'fizz', '43', '44', 'fizzbuzz', '46', '47', 'fizz', '49', 'buzz', 'fizz', '52', '53', 'fizz', 'buzz', '56', 'fizz', '58', '59', 'fizz', '61', '62', 'fizz', '64', 'buzz', 'fizz', '67', 'buzz', 'fizz', 'buzz', '71', 'fizz', '73', '74', 'fizzbuzz', '76', '77', 'fizz', '79', 'buzz', 'fizz', '82', '83', 'fizz', 'buzz', '86', 'fizz', '88', '89', 'fizzbuzz', '91', '92', 'fizz', '94', 'buzz', 'fizz', '97', '98', 'fizz', 'buzz']

print(np.sum(testY.max(1)[1].numpy() == np.array([fizz_buzz_encode(i) for i in range(1,101)])))
testY.max(1)[1].numpy() == np.array([fizz_buzz_encode(i) for i in range(1,101)])

array([ True,  True,  True, False,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True, False,  True,  True,  True,
        True,  True,  True,  True, False,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True])

查看模型的预测的结果是否正确

第1课课后复习导图

具体代码
链接：https://pan.baidu.com/s/17ocf9aK7GitLLlD4aDHLXg
提取码：vnc7