------------------optimizer-----------------------------------------------
Python中Zip() 函数
>>>a = [1,2,3]
>>> b = [4,5,6]
>>> c = [4,5,6,7,8]
>>> zipped = zip(a,b) # 打包为元组的列表 [(1, 4), (2, 5), (3, 6)]
>>> zip(a,c) # 元素个数与最短的列表一致 [(1, 4), (2, 5), (3, 6)]
>>> zip(*zipped) # 与 zip 相反,*zipped 可理解为解压,返回二维矩阵式 [(1, 2, 3), (4, 5, 6)]
import torch
import torch.utils.data as Data
import torch.nn.functional as F
import matplotlib.pyplot as plt
# torch.manual_seed(1) # reproducible
LR = 0.01
BATCH_SIZE = 32
EPOCH = 12
# fake dataset
x = torch.unsqueeze(torch.linspace(-1, 1, 1000), dim=1)
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size()))
# plot dataset
# plt.scatter(x.numpy(), y.numpy())
# plt.show()
# put dateset into torch dataset
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)
# default network
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.hidden = torch.nn.Linear(1, 20) # hidden layer
self.predict = torch.nn.Linear(20, 1) # output layer
def forward(self, x):
x = F.relu(self.hidden(x)) # activation function for hidden layer
x = self.predict(x) # linear output
return x
if __name__ == '__main__':
# different nets
net_SGD = Net()
net_Momentum = Net()
net_RMSprop = Net()
net_Adam = Net()
nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]
# different optimizers
opt_SGD = torch.optim.SGD(net_SGD.parameters(), lr=LR)
opt_Momentum = torch.optim.SGD(net_Momentum.parameters(), lr=LR, momentum=0.8)
opt_RMSprop = torch.optim.RMSprop(net_RMSprop.parameters(), lr=LR, alpha=0.9)
opt_Adam = torch.optim.Adam(net_Adam.parameters(), lr=LR, betas=(0.9, 0.99))
optimizers = [opt_SGD, opt_Momentum, opt_RMSprop, opt_Adam]
loss_func = torch.nn.MSELoss()
losses_his = [[], [], [], []] # record loss
# training
for epoch in range(EPOCH):
print('Epoch: ', epoch)
for step, (b_x, b_y) in enumerate(loader): # for each training step
for net, opt, l_his in zip(nets, optimizers, losses_his):
output = net(b_x) # get output for every net
loss = loss_func(output, b_y) # compute loss for every net
opt.zero_grad() # clear gradients for next train
loss.backward() # backpropagation, compute gradients
opt.step() # apply gradients
l_his.append(loss.data.numpy()) # loss recoder
labels = ['SGD', 'Momentum', 'RMSprop', 'Adam']
for i, l_his in enumerate(losses_his):
plt.plot(l_his, label=labels[i])
plt.legend(loc='best')
plt.xlabel('Steps')
plt.ylabel('Loss')
plt.ylim((0, 0.2))
plt.show()
----------------------------CNN--------------------------------------------
################################################################
实现mnist 手写数字识别 及 预测
完整代码:
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "1" #设定GPU cuda运行 与下面选一即可
import torch
###########################检查pytorch是否正在使用cuda
# a = torch.cuda.is_available()
# print(a)
# ngpu= 1
# # Decide which device we want to run on
# device = torch.device("cuda:0" if (torch.cuda.is_available() and ngpu > 0) else "cpu")
# print(device)
# print(torch.cuda.get_device_name(0))
# print(torch.rand(3,3).cuda())
###################################################
# third-party library
#import torch
import torch.nn as nn
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
LR = 0.001 # learning rate
DOWNLOAD_MNIST = False
# Mnist digits dataset
if not(os.path.exists('./mnist/')) or not os.listdir('./mnist/'):
# not mnist dir or mnist is empyt dir
DOWNLOAD_MNIST = True
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]
# 将图像的像素值(0,255)压缩为(0,1)区间
download=DOWNLOAD_MNIST,
)
# 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') # 显示出第一张图片
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)
# pick 2000 samples to speed up testing
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255. # 手动压缩 # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
test_y = test_data.test_labels[:2000]
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Sequential( # input shape (1, 28, 28)
nn.Conv2d(
in_channels=1, # input height 灰度图只有一个通道
out_channels=16, # n_filters 卷积核的数量
kernel_size=5, # filter size 卷积核的大小
stride=1, # filter movement/step
padding=2, # if want same width and length of this image after Conv2d, 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) 降维一半
)
self.conv2 = nn.Sequential( # input shape (16, 14, 14)
nn.Conv2d(16, 32, 5, 1, 2), # output shape (32, 14, 14)
nn.ReLU(), # activation
nn.MaxPool2d(2), # output shape (32, 7, 7)
)
self.out = nn.Linear(32 * 7 * 7, 10) # fully connected layer, output 10 classes 全连接层,将上一步所有的feature map 铺平 将三维数据变为2维
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x) # (batch,32, 7, 7)
x = x.view(x.size(0), -1) # 将batch维度保留,其他地方合并 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, (b_x, b_y) in enumerate(train_loader): # gives batch data, normalize x when iterate train_loader
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.numpy()
accuracy = float((pred_y == test_y.data.numpy()).astype(int).sum()) / float(test_y.size(0))
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| 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()
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')
pytorch 设置GPU 的三种方式
# 1:
torch.cuda.set_device(1)
# 2:
device = torch.device("cuda:1")
# 3:(官方推荐)<br>import os
os.environ["CUDA_VISIBLE_DEVICES"] = '1'
(同时调用两块GPU的话)
os.environ["CUDA_VISIBLE_DEVICES"] = '1,2'