1、简单torch的使用
# -*- coding: utf-8 -*-
from __future__ import print_function
import torch
x = torch.rand(5, 3)
print(x)
x = torch.zeros(5, 3, dtype=torch.long)
print(x)x = torch.tensor([5.5, 3])
print(x)x = x.new_ones(5, 3, dtype=torch.double)
# new_* methods take in sizes
print(x)x = torch.randn_like(x, dtype=torch.float)
# override dtype!
print(x)
# result has the same size
print(x.size())y = torch.rand(5, 3)
print(x + y)
print(torch.add(x, y))result = torch.empty(5, 3)
torch.add(x, y, out=result)
print("result:\n", result)# add: in-place
# adds x to y
y.add_(x)
print("y:\n", y)print(x[:, 1])# 改变tensor大小或形状
x = torch.randn(4, 4)
y = x.view(16)
z = x.view(-1, 8) # the size -1 is inferred from other dimensions
print(x.size(), y.size(), z.size())x = torch.randn(1)
print(x)
print(x.item())
2、torch的简单运算
import torchx = torch.ones(2, 2, requires_grad=True)
print(x)y = x + 2
print(y)
print(y.grad_fn)z = y * y * 3
out = z.mean()
print(z, out)a = torch.randn(2, 2)
a = ((a * 3) / (a - 1))
print(a.requires_grad)a.requires_grad_(True)
print(a.requires_grad)
b = (a * a).sum()
print(b.grad_fn)
out.backward()
print(x.grad)x = torch.randn(3, requires_grad=True)
y = x * 2
while y.data.norm() < 1000:y = y * 2print(y)v = torch.tensor([0.1, 1.0, 0.0001], dtype=torch.float)
y.backward(v)
print(x.grad)print(x.requires_grad)
print((x**2).requires_grad)with torch.no_grad():print((x**2).requires_grad)
3、torch组织简单网络
import torch
import torch.nn as nn
import torch.nn.functional as Fclass Net(nn.Module):def __init__(self):super(Net, self).__init__()# 1 input image channel, 6 output, 5×5 square convolution# kernelself.conv1 = nn.Conv2d(1, 6, 5)self.conv2 = nn.Conv2d(6, 16, 5)# an affine operation: y = Wx + bself.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) windowx = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))# If the size is a square you can only specify a single numberx = 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 xdef num_flat_features(self, x):size = x.size()[1:] # all dimensions except the batch dimensionnum_features = 1for s in size:num_features *= sreturn num_featuresnet = Net()
print(net)
params = list(net.parameters())
print(len(params))
print(params[0].size())
input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)
net.zero_grad()
out.backward(torch.randn(1, 10))output = net(input)
target = torch.randn(10) # a dummy target, for example
target = target.view(1, -1) # make it the same shape as output
criterion = nn.MSELoss()loss = criterion(output, target)
print("loss", loss)
print(loss.grad_fn) # MSELoss
print(loss.grad_fn.next_functions[0][0]) # Linear
print(loss.grad_fn.next_functions[0][0].next_functions[0][0])net.zero_grad() # zeros the gradient buffers of all parametersprint('conv1.bias.grad before backward')
print(net.conv1.bias.grad)loss.backward()print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)learning_rate = 0.01
for f in net.parameters():f.data.sub_(f.grad.data * learning_rate)import torch.optim as optim# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)# in your training loop:
optimizer.zero_grad() # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step() # Does the update
4、加载图像数据
import torch
import torchvision
import torchvision.transforms as transformstransform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'trunk')import matplotlib.pyplot as plt
import numpy as np
# functions to show an imagedef imshow(img):img = img / 2 + 0.5npimg = img.numpy()plt.imshow(np.transpose(npimg, (1, 2, 0)))plt.show()if __name__ == '__main__':# get some random training imagesdataiter = iter(trainloader)images, labels = dataiter.next()# show imagesimshow(torchvision.utils.make_grid(images))# print labelsprint(' '.join('%5s' % classes[labels[j]] for j in range(4)))
5、简单训练
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import matplotlib.pyplot as plt
import numpy as nptransform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=False, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'trunk')# functions to show an imagedef imshow(img):img = img / 2 + 0.5 # unnormalizenpimg = img.numpy()plt.imshow(np.transpose(npimg, (1, 2, 0)))plt.show()class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(3, 6, 5)self.pool = nn.MaxPool2d(2, 2)self.conv2 = nn.Conv2d(6, 16, 5)self.fc1 = nn.Linear(16 * 5 * 5, 120)self.fc2 = nn.Linear(120, 84)self.fc3 = nn.Linear(84, 10)def forward(self, x):x = self.pool(F.relu(self.conv1(x)))x = self.pool(F.relu(self.conv2(x)))x = x.view(-1, 16 * 5 * 5)x = F.relu(self.fc1(x))x = F.relu(self.fc2(x))x = self.fc3(x)return xif __name__ == '__main__':net = Net()criterion = nn.CrossEntropyLoss()optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)for epoch in range(2): # loop over the dataset multiplerunning_loss = 0.0for i, data in enumerate(trainloader, 0):# get the inputsinputs, labels = data# zero the parameter grasentsoptimizer.zero_grad()# forward + backward + optimizeoutputs = net(inputs)loss = criterion(outputs, labels)loss.backward()optimizer.step()# print statisticsrunning_loss += loss.item()if i % 2000 == 1999: # print every 2000 mini_batchesprint('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000))running_loss = 0.0print('Finished Training')dataiter = iter(testloader)images, labels = dataiter.next()# print imagesimshow(torchvision.utils.make_grid(images))print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))outputs = net(images)_, predicted = torch.max(outputs, 1)print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))correct = 0total = 0with torch.no_grad():for data in testloader:images, labels = dataoutputs = net(images)_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))class_correct = list(0. for i in range(10))class_total = list(0. for i in range(10))with torch.no_grad():for data in testloader:images, labels = dataoutputs = net(images)_, predicted = torch.max(outputs, 1)c = (predicted == labels).squeeze()for i in range(4):label = labels[i]class_correct[label] += c[i].item()class_total[label] += 1for i in range(10):print('Accuracy of %5s : %2d %%' % (classes[i], 100 * class_correct[i] / class_total[i]))device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")print(device)
6、数据并行
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoaderinput_size = 5
output_size = 2batch_size = 30
data_size = 100device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")class RandomDataset(Dataset):def __init__(self, size, length):self.len = lengthself.data = torch.randn(length, size)def __getitem__(self, index):return self.data[index]def __len__(self):return self.lenrand_loader = DataLoader(dataset=RandomDataset(input_size, data_size), batch_size=batch_size, shuffle=True)class Model(nn.Module):# Our modeldef __init__(self, input_size, output_size):super(Model, self).__init__()self.fc = nn.Linear(input_size, output_size)def forward(self, input):output = self.fc(input)print("\t In Model: input_size", input.size(), "output_size", output.size())return outputmodel = Model(input_size, output_size)
if torch.cuda.device_count() > 0:print("Let's use", torch.cuda.device_count(), "GPUs!")# dim = 0 [30, xxx] ->[10, ...], [10, ...],[10, ...] on 3 GPUsmodel = nn.DataParallel(model)model.to(device)for data in rand_loader:input = data.to(device)output = model(input)print("Outside: input_size", input.size(), "output_size", output.size())
7、Pytorch之数据加载和处理
from __future__ import print_function, division
import os
import torch
import pandas as pd # 用于更容易地进行csv解析
from skimage import io, transform # 用于图像的IO和变换
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils# 忽略警告
import warnings
warnings.filterwarnings("ignore")plt.ion() # interactive modelandmarks_frame = pd.read_csv('data/faces/face_landmarks.csv')n = 65
img_name = landmarks_frame.iloc[n, 0]
landmarks = landmarks_frame.iloc[n, 1:].as_matrix()
landmarks = landmarks.astype('float').reshape(-1, 2)print('Image name: {}'.format(img_name))
print('Landmark shape: []'.format(landmarks.shape))
print('First 4 Landmarks: {}'.format(landmarks[:4]))# 4 编写函数def show_landmarks(image, landmarks):"""显示带有地标的图片"""plt.imshow(image)plt.scatter(landmarks[:, 0], landmarks[:, 1], s=10, marker='.', c='r')plt.pause(0.001) # pause a bit so that plots are updatedplt.figure()
show_landmarks(io.imread(os.path.join('data/faces/', img_name)), landmarks)
plt.show()# 5 建立数据集类class FaceLandmarksDataset(Dataset):"""面部标记数据集。"""def __init__(self, csv_file, root_dir, transform=None):""":param csv_file[string]: 带注释的csv文件的路径。:param root_dir[string]: 包含所有图片的目录。:param transform[callable, optional]: 一个样本上的可用的可选变换"""self.landmarks_frame = pd.read_csv(csv_file)self.root_dir = root_dirself.transform = transformdef __len__(self):return len(self.landmarks_frame)def __getitem__(self, idx):img_name = os.path.join(self.root_dir, self.landmarks_frame.iloc[idx, 0])image = io.imread(img_name)landmarks = self.landmarks_frame.iloc[idx, 1:]landmarks = np.array([landmarks])landmarks = landmarks.astype('float').reshape(-1, 2)sample = {'image': image, 'landmarks': landmarks}if self.transform:sample = self.transform(sample)return sample# 6 数据可视化
face_dataset = FaceLandmarksDataset(csv_file='data/faces/face_landmarks.csv', root_dir='data/faces')
fig = plt.figure()
for i in range(len(face_dataset)):sample = face_dataset[i]print(i, sample['image'].shape, sample['landmarks'].shape)ax = plt.subplot(1, 4, i + 1)plt.tight_layout()ax.set_title('Sample #{}'.format(i))ax.axis('off')show_landmarks(**sample)if i == 3:plt.show()break# 7 数据变换
# tsfm = transform(params)
# transformed_sample = tsfm(sample)
class Rescale(object):""""将样本中的图像重新缩放到给定大小Args:output_size (tuple或int):所需的输出大小。如果是元组，则输出为与output_size匹配。如果是int，则匹配较小的图像边缘到output_size保持纵横比相同."""def __init__(self, output_size):assert isinstance(output_size, (int, tuple))self.output_size = output_sizedef __call__(self, sample):image, landmarks = sample['image'], sample['landmarks']h, w = image.shape[:2]if isinstance(self.output_size, int):if h > w:new_h, new_w = self.output_size * h / w, self.output_sizeelse:new_h, new_w = self.output_size, self.output_size * w / helse:new_h, new_w = self.output_sizenew_h, new_w = int(new_h), int(new_w)img = transform.resize(image, (new_h, new_w))# h and w are swapped for landmarks because for images.# x and y axes are axis 1 and 0 respectivelylandmarks = landmarks * [new_w / w, new_h / h]return {'image':img, 'landmarks':landmarks}class RandomCrop(object):"""随机裁剪样本中的图像Args：output_size(tuple或int):所需的输出大小。如果是int，方形裁剪是。"""def __init__(self, output_size):assert isinstance(output_size, (int, tuple))if isinstance(output_size, int):self.output_size = (output_size, output_size)else:assert len(output_size) == 2self.output_size = output_sizedef __call__(self, sample):image, landmarks = sample['image'], sample['landmarks']h, w = image.shape[:2]new_h, new_w = self.output_sizetop = np.random.randint(0, h - new_h)left = np.random.randint(0, w - new_w)image = image[top: top + new_h, left: left + new_w]landmarks = landmarks - [left, top]return {'image': image, 'landmarks': landmarks}class ToTensor(object):"""将样本中的ndarrays转换为Tensors. """def __call__(self, sample):image, landmarks = sample['image'], sample['landmarks']# 交换颜色轴，因为# numpy包的图片是：H * W * C# torch包的图片是：C * H * Wimage = image.transpose((2, 0, 1))return {'image': torch.from_numpy(image), 'landmarks': torch.from_numpy(landmarks)}# 8 组合转换scale = Rescale(256)
crop = RandomCrop(128)
composed = transforms.Compose([Rescale(256), RandomCrop(224)])# 在样本上应用上述的每个变换
fig = plt.figure()
sample = face_dataset[65]
for i, tsfm in enumerate([scale, crop, composed]):transformed_sample = tsfm(sample)ax = plt.subplot(1, 3, i + 1)plt.tight_layout()ax.set_title(type(tsfm).__name__)show_landmarks(**transformed_sample)plt.show()# input() # 仅用来等待# 9 迭代数据集transformed_dataset = FaceLandmarksDataset(csv_file='data/faces/face_landmarks.csv', root_dir='data/faces/',transform=transforms.Compose([Rescale(256), RandomCrop(224), ToTensor()]))
for i in range(len(transformed_dataset)):sample = transformed_dataset[i]print(i, sample['image'].size(), sample['landmarks'].size())if i == 3:break# input()dataloader = DataLoader(transformed_dataset, batch_size=4, shuffle=True, num_workers=4)# 辅助功能：显示批次
def show_landmarks_batch(sample_batched):""" Show image with landmarks for a batch of samples."""images_batch, landmarks_batch = sample_batched['image'], sample_batched['landmarks']batch_size = len(images_batch)im_size = images_batch.size(2)grid_border_size = 2grid = utils.make_grid(images_batch)plt.imshow(grid.numpy().transpose((1, 2, 0)))for i in range(batch_size):plt.scatter(landmarks_batch[i, :, 0].numpy() + i * im_size + (i + 1) * grid_border_size,landmarks_batch[i, :, 1].numpy() + grid_border_size, s=10, marker='.', c='r')plt.title('Batch from dataloader')if __name__ == '__main__':for i_batch, sample_batched in enumerate(dataloader):print(i_batch, sample_batched['image'].size(), sample_batched['landmarks'].size())# 观察第4批次并停止if i_batch == 3:plt.figure()show_landmarks_batch(sample_batched)plt.axis('off')plt.ioff()plt.show()break