PyTorch：开始入门的一些小代码下（from 莫烦）
1.CNN
这里一开始的时候import torchvision会报错，我在装pytorch的时候居然没有自动装上torchvision，所以去官网下载了.whl的包。
conda install pippip install torchvision-0.1.9-py2.py3-none-any.whl这样import torchvision的时候就没有问题辣。
import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
torch.manual_seed(1) # reproducible
# Hyper Parameters
EPOCH = 1 # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 50 # batch size
LR = 0.001 # learning rate
DOWNLOAD_MNIST = False # set to False if you have downloaded True表示需要下载数据
# Mnist digits dataset 在官网下载数据
train_data = torchvision.datasets.MNIST(
root='./mnist/',
train=True, # this is training data
transform=torchvision.transforms.ToTensor(), # Converts a PIL.Image or numpy.ndarray to
# torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
download=DOWNLOAD_MNIST, # download it if you don't have it
)
#download之后大概会有6万的训练集，1万的测试集
'''
# plot one example
print(train_data.train_data.size()) # (60000, 28, 28)
print(train_data.train_labels.size()) # (60000)
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()
'''
# Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
# convert test data into Variable, pick 2000 samples to speed up testing
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False) #提取的是test data
test_x = Variable(torch.unsqueeze(test_data.test_data, dim=1), volatile=True).type(torch.FloatTensor)[:2000]/255. # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
#traindata将原来的[0-255]压缩到了[0.0, 1.0]这个区间，所以test data也要/255做同样处理
test_y = test_data.test_labels[:2000] #为了节省时间只取了2000个测试 :)
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
#尺寸:[1*28*28]->[16*28*28]->[16*14*14]
self.conv1 = nn.Sequential( # input shape (1, 28, 28)
nn.Conv2d(
in_channels=1, # input height 本例中灰度图只有1层（非RGB）
out_channels=16, # n_filters 输出filter的个数
kernel_size=5, # filter size
stride=1, # filter movement/step
padding=2, # if want same width and length of this image after con2d, padding=(kernel_size-1)/2 if stride=1
), # output shape (16, 28, 28)
nn.ReLU(), # activation
nn.MaxPool2d(kernel_size=2), # choose max value in 2x2 area, output shape (16, 14, 14)
)
#尺寸:[16*14*14]->[32*14*14]->[32*7*7]
self.conv2 = nn.Sequential( # input shape (1, 28, 28)
nn.Conv2d(16, 32, 5, 1, 2), # output shape (32, 14, 14)
nn.ReLU(), # activation
nn.MaxPool2d(2), # output shape (32, 7, 7)
)
#因为输入图像维度为[1*28*28],经过2层Conv后尺寸变为[32*7*7]
#尺寸:[32*7*7]->[1*10] （数字0-9，10类）
self.out = nn.Linear(32 * 7 * 7, 10) # fully connected layer, output 10 classes
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
#将原有的[32*7*7]的数据变成32*7*7的行向量
x = x.view(x.size(0), -1) # flatten the output of conv2 to (batch_size, 32 * 7 * 7)
output = self.out(x)
return output, x # return x for visualization
cnn = CNN()
print(cnn) # net architecture
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR) # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss() # the target label is not one-hotted
# following function (plot_with_labels) is for visualization, can be ignored if not interested
from matplotlib import cm
try: from sklearn.manifold import TSNE; HAS_SK = True
except: HAS_SK = False; print('Please install sklearn for layer visualization')
def plot_with_labels(lowDWeights, labels):
plt.cla()
X, Y = lowDWeights[:, 0], lowDWeights[:, 1]
for x, y, s in zip(X, Y, labels):
c = cm.rainbow(int(255 * s / 9)); plt.text(x, y, s, backgroundcolor=c, fontsize=9)
plt.xlim(X.min(), X.max()); plt.ylim(Y.min(), Y.max()); plt.title('Visualize last layer'); plt.show(); plt.pause(0.01)
plt.ion()
# training and testing
for epoch in range(EPOCH):
for step, (x, y) in enumerate(train_loader): # gives batch data, normalize x when iterate train_loader
b_x = Variable(x) # batch x
b_y = Variable(y) # batch y
output = cnn(b_x)[0] # cnn output
loss = loss_func(output, b_y) # cross entropy loss
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
if step % 50 == 0:
test_output, last_layer = cnn(test_x)
pred_y = torch.max(test_output, 1)[1].data.squeeze()
accuracy = sum(pred_y == test_y) / float(test_y.size(0))
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data[0], '| test accuracy: %.2f' % accuracy)
if HAS_SK:
# Visualization of trained flatten layer (T-SNE)
tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
plot_only = 500
low_dim_embs = tsne.fit_transform(last_layer.data.numpy()[:plot_only, :])
labels = test_y.numpy()[:plot_only]
plot_with_labels(low_dim_embs, labels)
plt.ioff()
# print 10 predictions from test data
test_output, _ = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')
可以看到分类边界一点点变清晰的过程，最后结果损失在0.0424，准确率达到了0.98。
2.RNN
import torch
from torch import nn
from torch.autograd import Variable
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
torch.manual_seed(1) # reproducible
# Hyper Parameters
EPOCH = 1 # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 64 # batch size
TIME_STEP = 28 # rnn time step / image height
INPUT_SIZE = 28 # rnn input size / image width
LR = 0.01 # learning rate
DOWNLOAD_MNIST = False # set to True if haven't download the data
# Mnist digital dataset
train_data = dsets.MNIST(
root='./mnist/',
train=True, # this is training data
transform=transforms.ToTensor(), # Converts a PIL.Image or numpy.ndarray to
# torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
download=DOWNLOAD_MNIST, # download it if you don't have it
)
'''
# plot one example
print(train_data.train_data.size()) # (60000, 28, 28)
print(train_data.train_labels.size()) # (60000)
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()
'''
# Data Loader for easy mini-batch return in training
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
# convert test data into Variable, pick 2000 samples to speed up testing
test_data = dsets.MNIST(root='./mnist/', train=False, transform=transforms.ToTensor())
test_x = Variable(test_data.test_data, volatile=True).type(torch.FloatTensor)[:2000]/255. # shape (2000, 28, 28) value in range(0,1)
test_y = test_data.test_labels.numpy().squeeze()[:2000] # covert to numpy array
class RNN(nn.Module):
def __init__(self):
super(RNN, self).__init__()
self.rnn = nn.LSTM( # if use nn.RNN(), it hardly learns
input_size=INPUT_SIZE, #LSTM的方法逐行读取图片，所以是28
hidden_size=64, # rnn hidden unit
num_layers=1, # number of rnn layer
batch_first=True, # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size)
)
self.out = nn.Linear(64, 10)
def forward(self, x):
# x shape (batch, time_step, input_size)
# r_out shape (batch, time_step, output_size)
# h_n shape (n_layers, batch, hidden_size)
# h_c shape (n_layers, batch, hidden_size)
r_out, (h_n, h_c) = self.rnn(x, None) # None represents zero initial hidden state
# choose r_out at the last time step 一定要取最后一个
out = self.out(r_out[:, -1, :])
return out
rnn = RNN()
print(rnn)
optimizer = torch.optim.Adam(rnn.parameters(), lr=LR) # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss() # the target label is not one-hotted
# training and testing
for epoch in range(EPOCH):
for step, (x, y) in enumerate(train_loader): # gives batch data
b_x = Variable(x.view(-1, 28, 28)) # reshape x to (batch, time_step, input_size)
b_y = Variable(y) # batch y
output = rnn(b_x) # rnn output
loss = loss_func(output, b_y) # cross entropy loss
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
if step % 100 == 0:
test_output = rnn(test_x) # (samples, time_step, input_size)
pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
accuracy = sum(pred_y == test_y) / float(test_y.size)
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data[0], '| test accuracy: %.2f' % accuracy)
# print 10 predictions from test data
test_output = rnn(test_x[:10].view(-1, 28, 28))
pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
print(pred_y, 'prediction number')
print(test_y[:10], 'real number')RNN (
(rnn): LSTM(28, 64, batch_first=True)
(out): Linear (64 -> 10)
)
Epoch: 0 | train loss: 2.3127 | test accuracy: 0.14
Epoch: 0 | train loss: 0.7868 | test accuracy: 0.68
Epoch: 0 | train loss: 0.8782 | test accuracy: 0.81
Epoch: 0 | train loss: 0.3738 | test accuracy: 0.88
Epoch: 0 | train loss: 0.3002 | test accuracy: 0.92
Epoch: 0 | train loss: 0.1786 | test accuracy: 0.94
Epoch: 0 | train loss: 0.1762 | test accuracy: 0.95
Epoch: 0 | train loss: 0.2623 | test accuracy: 0.94
Epoch: 0 | train loss: 0.1319 | test accuracy: 0.96
Epoch: 0 | train loss: 0.1281 | test accuracy: 0.94
[7 2 1 0 4 1 4 9 6 9] prediction number
[7 2 1 0 4 1 4 9 5 9] real number
以上是分类。另一种回归的方法。
import torch
from torch import nn
from torch.autograd import Variable
import numpy as np
import matplotlib.pyplot as plt
torch.manual_seed(1) # reproducible
# Hyper Parameters
TIME_STEP = 10 # rnn time step
INPUT_SIZE = 1 # rnn input size
LR = 0.02 # learning rate
# show data
steps = np.linspace(0, np.pi*2, 100, dtype=np.float32)
x_np = np.sin(steps) # float32 for converting torch FloatTensor
y_np = np.cos(steps)
plt.plot(steps, y_np, 'r-', label='target (cos)')
plt.plot(steps, x_np, 'b-', label='input (sin)')
plt.legend(loc='best')
plt.show()
class RNN(nn.Module):
def __init__(self):
super(RNN, self).__init__()
self.rnn = nn.RNN(
input_size=INPUT_SIZE,
hidden_size=32, # rnn hidden unit
num_layers=1, # number of rnn layer
batch_first=True, # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size)
)
self.out = nn.Linear(32, 1)
def forward(self, x, h_state):
# x (batch, time_step, input_size)
# h_state (n_layers, batch, hidden_size)
# r_out (batch, time_step, hidden_size)
r_out, h_state = self.rnn(x, h_state)
outs = [] # save all predictions
for time_step in range(r_out.size(1)): # calculate output for each time step
outs.append(self.out(r_out[:, time_step, :]))
return torch.stack(outs, dim=1), h_state
# instead, for simplicity, you can replace above codes by follows
# r_out = r_out.view(-1, 32)
# outs = self.out(r_out)
# return outs, h_state
rnn = RNN()
print(rnn)
optimizer = torch.optim.Adam(rnn.parameters(), lr=LR) # optimize all cnn parameters
loss_func = nn.MSELoss()
h_state = None # for initial hidden state
plt.figure(1, figsize=(12, 5))
plt.ion() # continuously plot
for step in range(60):
start, end = step * np.pi, (step+1)*np.pi # time range
# use sin predicts cos
steps = np.linspace(start, end, TIME_STEP, dtype=np.float32)
x_np = np.sin(steps) # float32 for converting torch FloatTensor
y_np = np.cos(steps)
x = Variable(torch.from_numpy(x_np[np.newaxis, :, np.newaxis])) # shape (batch, time_step, input_size)
y = Variable(torch.from_numpy(y_np[np.newaxis, :, np.newaxis]))
prediction, h_state = rnn(x, h_state) # rnn output
# !! next step is important !!
h_state = Variable(h_state.data) # repack the hidden state, break the connection from last iteration
loss = loss_func(prediction, y) # cross entropy loss
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
# plotting
plt.plot(steps, y_np.flatten(), 'r-')
plt.plot(steps, prediction.data.numpy().flatten(), 'b-')
plt.draw(); plt.pause(0.05)
plt.ioff()
plt.show()RNN (
(rnn): RNN(1, 32, batch_first=True)
(out): Linear (32 -> 1)
)
3.AutoEncoder
一种无监督学习的分类过程。无需test data。
import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm
import numpy as np
torch.manual_seed(1) # reproducible
# Hyper Parameters
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005 # learning rate
DOWNLOAD_MNIST = False
N_TEST_IMG = 5
# Mnist digits dataset
train_data = torchvision.datasets.MNIST(
root='./mnist/',
train=True, # this is training data
transform=torchvision.transforms.ToTensor(), # Converts a PIL.Image or numpy.ndarray to
# torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
download=DOWNLOAD_MNIST, # download it if you don't have it
)
# plot one example
print(train_data.train_data.size()) # (60000, 28, 28)
print(train_data.train_labels.size()) # (60000)
plt.imshow(train_data.train_data[2].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[2])
plt.show()
# Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
class AutoEncoder(nn.Module):
def __init__(self):
super(AutoEncoder, self).__init__()
self.encoder = nn.Sequential(
nn.Linear(28*28, 128),
nn.Tanh(),
nn.Linear(128, 64),
nn.Tanh(),
nn.Linear(64, 12),
nn.Tanh(),
nn.Linear(12, 3), # compress to 3 features which can be visualized in plt
)
self.decoder = nn.Sequential(
nn.Linear(3, 12),
nn.Tanh(),
nn.Linear(12, 64),
nn.Tanh(),
nn.Linear(64, 128),
nn.Tanh(),
nn.Linear(128, 28*28),
nn.Sigmoid(), # compress to a range (0, 1) 压缩到0-1的范围
)
def forward(self, x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return encoded, decoded
autoencoder = AutoEncoder()
optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)
loss_func = nn.MSELoss()
# initialize figure
f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
plt.ion() # continuously plot
# original data (first row) for viewing
view_data = Variable(train_data.train_data[:N_TEST_IMG].view(-1, 28*28).type(torch.FloatTensor)/255.)
for i in range(N_TEST_IMG):
a[0][i].imshow(np.reshape(view_data.data.numpy()[i], (28, 28)), cmap='gray'); a[0][i].set_xticks(()); a[0][i].set_yticks(())
for epoch in range(EPOCH):
for step, (x, y) in enumerate(train_loader):
b_x = Variable(x.view(-1, 28*28)) # batch x, shape (batch, 28*28)
b_y = Variable(x.view(-1, 28*28)) # batch y, shape (batch, 28*28) 还是X!!
b_label = Variable(y) # batch label
encoded, decoded = autoencoder(b_x)
loss = loss_func(decoded, b_y) # mean square error
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
if step % 100 == 0:
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data[0])
# plotting decoded image (second row)
_, decoded_data = autoencoder(view_data)
for i in range(N_TEST_IMG):
a[1][i].clear()
a[1][i].imshow(np.reshape(decoded_data.data.numpy()[i], (28, 28)), cmap='gray')
a[1][i].set_xticks(()); a[1][i].set_yticks(())
plt.draw(); plt.pause(0.05)
plt.ioff()
plt.show()
# visualize in 3D plot
view_data = Variable(train_data.train_data[:200].view(-1, 28*28).type(torch.FloatTensor)/255.)
encoded_data, _ = autoencoder(view_data)
fig = plt.figure(2); ax = Axes3D(fig)
X, Y, Z = encoded_data.data[:, 0].numpy(), encoded_data.data[:, 1].numpy(), encoded_data.data[:, 2].numpy()
values = train_data.train_labels[:200].numpy()
for x, y, z, s in zip(X, Y, Z, values):
c = cm.rainbow(int(255*s/9)); ax.text(x, y, z, s, backgroundcolor=c)
ax.set_xlim(X.min(), X.max()); ax.set_ylim(Y.min(), Y.max()); ax.set_zlim(Z.min(), Z.max())
plt.show()
4.DQN 强化学习
暂时略过去啦。。。。。；)
5.GAN
import torch
import torch.nn as nn
from torch.autograd import Variable
import numpy as np
import matplotlib.pyplot as plt
torch.manual_seed(1) # reproducible
np.random.seed(1)
# Hyper Parameters
BATCH_SIZE = 64
LR_G = 0.0001 # learning rate for generator
LR_D = 0.0001 # learning rate for discriminator
N_IDEAS = 5 # think of this as number of ideas for generating an art work (Generator)
ART_COMPONENTS = 15 # it could be total point G can draw in the canvas
PAINT_POINTS = np.vstack([np.linspace(-1, 1, ART_COMPONENTS) for _ in range(BATCH_SIZE)])
'''
# show our beautiful painting range
plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
plt.legend(loc='upper right')
plt.show()
'''
#生成标准“画作”，15个点画出一条线
def artist_works(): # painting from the famous artist (real target)
a = np.random.uniform(1, 2, size=BATCH_SIZE)[:, np.newaxis]
paintings = a * np.power(PAINT_POINTS, 2) + (a-1) #一元二次函数
paintings = torch.from_numpy(paintings).float() #转换成torch的形式
return Variable(paintings)
# Generator
G = nn.Sequential(
nn.Linear(N_IDEAS, 128), # random ideas (could from normal distribution)
nn.ReLU(),
nn.Linear(128, ART_COMPONENTS), # making a painting from these random ideas
)
# Discriminator
D = nn.Sequential(
nn.Linear(ART_COMPONENTS, 128), # receive art work either from the famous artist or a newbie like G
nn.ReLU(),
nn.Linear(128, 1),
nn.Sigmoid(), # tell the probability that the art work is made by artist
)
opt_D = torch.optim.Adam(D.parameters(), lr=LR_D)
opt_G = torch.optim.Adam(G.parameters(), lr=LR_G)
plt.ion() # something about continuous plotting
for step in range(10000):
artist_paintings = artist_works() # real painting from artist
G_ideas = Variable(torch.randn(BATCH_SIZE, N_IDEAS)) # random ideas
G_paintings = G(G_ideas) # fake painting from G (random ideas)
prob_artist0 = D(artist_paintings) # D try to increase this prob
prob_artist1 = D(G_paintings) # D try to reduce this prob
D_loss = - torch.mean(torch.log(prob_artist0) + torch.log(1. - prob_artist1))
G_loss = torch.mean(torch.log(1. - prob_artist1))
#取上述两种loss的最小
opt_D.zero_grad()
D_loss.backward(retain_variables=True) # retain_variables for reusing computational graph
opt_D.step()
opt_G.zero_grad()
G_loss.backward()
opt_G.step()
if step % 50 == 0: # plotting
plt.cla()
plt.plot(PAINT_POINTS[0], G_paintings.data.numpy()[0], c='#4AD631', lw=3, label='Generated painting',)
plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
plt.text(-.5, 2.3, 'D accuracy=%.2f (0.5 for D to converge)' % prob_artist0.data.numpy().mean(), fontdict={'size': 15})
plt.text(-.5, 2, 'D score= %.2f (-1.38 for G to converge)' % -D_loss.data.numpy(), fontdict={'size': 15})
plt.ylim((0, 3));plt.legend(loc='upper right', fontsize=12);plt.draw();plt.pause(0.01)
plt.ioff()
plt.show()