PyTorch之数据加载和处理
from __future__ import print_function, division
import os
import torch
import pandas as pd
from skimage import io, transform
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
import warnings
warnings.filterwarnings("ignore")
plt.ion()
"""
读取数据集
将csv中的标注点数据读入（N，2）数组中，其中N是特征点的数量。读取数据代码如下：
"""
landmarks_frame = pd.read_csv('data/faces/faces/face_landmarks.csv')
n = 65
img_name = landmarks_frame.iloc[n, 0]
landmarks = landmarks_frame.iloc[n, 1:].values
landmarks = landmarks.astype('float').reshape(-1, 2)
print('Image name: {}'.format(img_name))
print('Landmarks shape: {}'.format(landmarks.shape))
print('First 4 Landmarks: {}'.format(landmarks[:4]))
"""
写一个简单的函数来展示一张图片和它对应的标注点作为例子。
"""
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(5)
plt.figure()
show_landmarks(io.imread(os.path.join('data/faces/faces/', img_name)),
landmarks)
plt.show()
"""
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):
"""
csv_file（string）：带注释的csv文件的路径。
root_dir（string）：包含所有图像的目录。
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_dir
self.transform = transform
def __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
"""
数据可视化
"""
face_dataset = FaceLandmarksDataset(csv_file='data/faces/faces/face_landmarks.csv',
root_dir='data/faces/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
"""
数据变换,数据预处理
让我们创建三个转换:
* Rescale：缩放图片
* RandomCrop：对图片进行随机裁剪。这是一种数据增强操作
* ToTensor：把numpy格式图片转为torch格式图片 (我们需要交换坐标轴).
"""
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_size
def __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_size
else:
new_h, new_w = self.output_size, self.output_size * w / h
else:
new_h, new_w = self.output_size
new_h, new_w = int(new_h), int(new_w)
img = transform.resize(image, (new_h, new_w))
landmarks = 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) == 2
self.output_size = output_size
def __call__(self, sample):
image, landmarks = sample['image'], sample['landmarks']
h, w = image.shape[:2]
new_h, new_w = self.output_size
top = 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']
image = image.transpose((2, 0, 1))
return {'image': torch.from_numpy(image),
'landmarks': torch.from_numpy(landmarks)}
scale = Rescale(256)
crop = RandomCrop(128)
composed = transforms.Compose([Rescale(256),
RandomCrop(224)])
"""
应用转换
"""
fig = plt.figure()
sample = face_dataset[65]
for i, tsfrm in enumerate([scale, crop, composed]):
transformed_sample = tsfrm(sample)
ax = plt.subplot(1, 3, i + 1)
plt.tight_layout()
ax.set_title(type(tsfrm).__name__)
show_landmarks(**transformed_sample)
plt.show()
"""
torch.utils.data.DataLoader是一个提供
每次这个数据集被采样时: 及时地从文件中读取图片 * 对读取的图片应用转换 * 由于其中一步操作是随机的 (randomcrop) , 数据被增强了
功能的迭代器
"""
transformed_dataset = FaceLandmarksDataset(csv_file='data/faces/faces/face_landmarks.csv',
root_dir='data/faces/faces/',
transform=transforms.Compose([
Rescale(256),
RandomCrop(224),
ToTensor()
]))
dataloader = DataLoader(transformed_dataset, batch_size=4,
shuffle=True, num_workers=4)
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 = 2
grid = 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')
for i_batch, sample_batched in enumerate(dataloader):
print(i_batch, sample_batched['image'].size(),
sample_batched['landmarks'].size())
if i_batch == 3:
plt.figure()
show_landmarks_batch(sample_batched)
plt.axis('off')
plt.ioff()
plt.show()
break
Pytorch小试牛刀
"""
使用NumPy，手动实现网络的 前向和反向传播，来拟合随机数据
"""
import numpy as np
N, D_in, H, D_out = 64, 1000, 100, 10
x = np.random.randn(N, D_in)
y = np.random.randn(N, D_out)
w1 = np.random.randn(D_in, H)
w2 = np.random.randn(H, D_out)
learning_rate = 1e-6
for t in range(500):
h = x.dot(w1)
h_relu = np.maximum(h, 0)
y_pred = h_relu.dot(w2)
loss = np.square(y_pred - y).sum()
print(t, loss)
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)
w1 -= learning_rate * grad_w1
w2 -= learning_rate * grad_w2
"""
使用PyTorch的tensor，手动在网络中实现前向传播和反向传播
"""
import torch
dtype = torch.float
device = torch.device("cpu")
N, D_in, H, D_out = 64, 1000, 100, 10
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)
w1 = torch.randn(D_in, H, device=device, dtype=dtype)
w2 = torch.randn(H, D_out, device=device, dtype=dtype)
learning_rate = 1e-6
for t in range(500):
h = x.mm(w1)
h_relu = h.clamp(min=0)
y_pred = h_relu.mm(w2)
loss = (y_pred - y).pow(2).sum().item()
print(t, loss)
grad_y_pred = 2.0 * (y_pred - y)
grad_w2 = h_relu.t().mm(grad_y_pred)
grad_h_relu = grad_y_pred.mm(w2.t())
grad_h = grad_h_relu.clone()
grad_h[h < 0] = 0
grad_w1 = x.t().mm(grad_h)
w1 -= learning_rate * grad_w1
w2 -= learning_rate * grad_w2
"""
使用PyTorch的Tensors和autograd来实现我们的两层的神经网络
"""
import torch
dtype = torch.float
device = torch.device("cpu")
N, D_in, H, D_out = 64, 1000, 100, 10
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)
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):
y_pred = x.mm(w1).clamp(min=0).mm(w2)
loss = (y_pred - y).pow(2).sum()
print(t, loss.item())
loss.backward()
with torch.no_grad():
w1 -= learning_rate * w1.grad
w2 -= learning_rate * w2.grad
w1.grad.zero_()
w2.grad.zero_()
"""
自定义nn模块:
自定义Module的子类构建两层网络：
"""
import torch
class TwoLayerNet(torch.nn.Module):
def __init__(self, D_in, H, D_out):
"""
在构造函数中，我们实例化了两个nn.Linear模块，并将它们作为成员变量。
"""
super(TwoLayerNet, self).__init__()
self.linear1 = torch.nn.Linear(D_in, H)
self.linear2 = torch.nn.Linear(H, D_out)
def forward(self, x):
"""
在前向传播的函数中，我们接收一个输入的张量，也必须返回一个输出张量。
我们可以使用构造函数中定义的模块以及张量上的任意的（可微分的）操作。
"""
h_relu = self.linear1(x).clamp(min=0)
y_pred = self.linear2(h_relu)
return y_pred
N, D_in, H, D_out = 64, 1000, 100, 10
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
model = TwoLayerNet(D_in, H, D_out)
loss_fn = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-4)
for t in range(500):
y_pred = model(x)
loss = loss_fn(y_pred, y)
print(t, loss.item())
optimizer.zero_grad()
loss.backward()
optimizer.step()
"""
控制流和权重共享
使用普通的Python流控制来实现循环，并且我们可以通过在定义转发时多次重用同一个模块来实现最内层之间的权重共享。
"""
import random
import torch
class DynamicNet(torch.nn.Module):
def __init__(self, D_in, H, D_out):
"""
在构造函数中，我们构造了三个nn.Linear实例，它们将在前向传播时被使用。
"""
super(DynamicNet, self).__init__()
self.input_linear = torch.nn.Linear(D_in, H)
self.middle_linear = torch.nn.Linear(H, H)
self.output_linear = torch.nn.Linear(H, D_out)
def forward(self, x):
"""
对于模型的前向传播，我们随机选择0、1、2、3，
并重用了多次计算隐藏层的middle_linear模块。
由于每个前向传播构建一个动态计算图，
我们可以在定义模型的前向传播时使用常规Python控制流运算符，如循环或条件语句。
在这里，我们还看到，在定义计算图形时多次重用同一个模块是完全安全的。
这是Lua Torch的一大改进，因为Lua Torch中每个模块只能使用一次。
"""
h_relu = self.input_linear(x).clamp(min=0)
for _ in range(random.randint(0, 3)):
h_relu = self.middle_linear(h_relu).clamp(min=0)
y_pred = self.output_linear(h_relu)
return y_pred
N, D_in, H, D_out = 64, 1000, 100, 10
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
model = DynamicNet(D_in, H, D_out)
criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-4, momentum=0.9)
for t in range(500):
y_pred = model(x)
loss = criterion(y_pred, y)
print(t, loss.item())
optimizer.zero_grad()
loss.backward()
optimizer.step()
PyTorch之迁移学习
from __future__ import print_function, division
import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy
plt.ion()
"""
加载数据
"""
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
data_dir = 'data/hymenoptera_data'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
data_transforms[x])
for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
shuffle=True, num_workers=4)
for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
"""
可视化部分图像数据
"""
def imshow(inp, title=None):
"""Imshow for Tensor."""
inp = inp.numpy().transpose((1, 2, 0))
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
inp = std * inp + mean
inp = np.clip(inp, 0, 1)
plt.imshow(inp)
if title is not None:
plt.title(title)
plt.pause(1)
inputs, classes = next(iter(dataloaders['train']))
out = torchvision.utils.make_grid(inputs)
imshow(out, title=[class_names[x] for x in classes])
"""
训练模型
"""
def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
since = time.time()
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
for phase in ['train', 'val']:
if phase == 'train':
scheduler.step()
model.train()
else:
model.eval()
running_loss = 0.0
running_corrects = 0
for inputs, labels in dataloaders[phase]:
inputs = inputs.to(device)
labels = labels.to(device)
optimizer.zero_grad()
with torch.set_grad_enabled(phase == 'train'):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
if phase == 'train':
loss.backward()
optimizer.step()
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
epoch_loss = running_loss / dataset_sizes[phase]
epoch_acc = running_corrects.double() / dataset_sizes[phase]
print('{} Loss: {:.4f} Acc: {:.4f}'.format(
phase, epoch_loss, epoch_acc))
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
model.load_state_dict(best_model_wts)
return model
"""
可视化模型的预测结果
"""
def visualize_model(model, num_images=6):
was_training = model.training
model.eval()
images_so_far = 0
fig = plt.figure()
with torch.no_grad():
for i, (inputs, labels) in enumerate(dataloaders['val']):
inputs = inputs.to(device)
labels = labels.to(device)
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
for j in range(inputs.size()[0]):
images_so_far += 1
ax = plt.subplot(num_images//2, 2, images_so_far)
ax.axis('off')
ax.set_title('predicted: {}'.format(class_names[preds[j]]))
imshow(inputs.cpu().data[j])
if images_so_far == num_images:
model.train(mode=was_training)
return
model.train(mode=was_training)
"""
场景1：微调ConvNet
加载预训练模型并重置最终完全连接的图层。
"""
model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)
model_ft = model_ft.to(device)
criterion = nn.CrossEntropyLoss()
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
num_epochs=25)
visualize_model(model_ft)
"""
场景2：ConvNet作为固定特征提取器
在这里需要冻结除最后一层之外的所有网络。通过设置requires_grad == False backward()来冻结参数，这样在反向传播backward()的时候他们的梯度就不会被计算。
"""
model_conv = torchvision.models.resnet18(pretrained=True)
for param in model_conv.parameters():
param.requires_grad = False
num_ftrs = model_conv.fc.in_features
model_conv.fc = nn.Linear(num_ftrs, 2)
model_conv = model_conv.to(device)
criterion = nn.CrossEntropyLoss()
optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9)
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)
model_conv = train_model(model_conv, criterion, optimizer_conv,
exp_lr_scheduler, num_epochs=25)
visualize_model(model_conv)
plt.ioff()
plt.show()
保存和加载模型
import torch
import torch.nn as nn
import torch.functional as F
import torch.utils.data as Data
import torchvision
import torch.optim as optim
"""
什么是状态字典：state_dict?
"""
class TheModelClass(nn.Module):
def __init__(self):
super(TheModelClass, 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 x
model = TheModelClass()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
print("Model's state_dict:")
for param_tensor in model.state_dict():
print(param_tensor, "\t", model.state_dict()[param_tensor].size())
print("Optimizer's state_dict:")
for var_name in optimizer.state_dict():
print(var_name, "\t", optimizer.state_dict()[var_name])
