PyTorch使用高頻代碼段分享

本文是PyTorch常用代碼段合集，涵蓋基本配置、張量處理、模型定義與操作、數(shù)據(jù)處理、模型訓(xùn)練與測試等5個方面，還給出了多個值得注意的Tips，內(nèi)容非常全面。

PyTorch最好的資料是官方文檔。本文是PyTorch常用代碼段，在參考資料[1](張皓：PyTorch Cookbook)的基礎(chǔ)上做了一些修補，方便使用時查閱。

基本配置

導(dǎo)入包和版本查詢

import torch
import torch.nn as nn
import torchvision
print(torch.__version__)
print(torch.version.cuda)
print(torch.backends.cudnn.version())
print(torch.cuda.get_device_name(0))

可復(fù)現(xiàn)性

在硬件設(shè)備（CPU、GPU）不同時，完全的可復(fù)現(xiàn)性無法保證，即使隨機種子相同。但是，在同一個設(shè)備上，應(yīng)該保證可復(fù)現(xiàn)性。具體做法是，在程序開始的時候固定torch的隨機種子，同時也把numpy的隨機種子固定。

np.random.seed(0)
torch.manual_seed(0)
torch.cuda.manual_seed_all(0)


torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False

顯卡設(shè)置

如果只需要一張顯卡。

# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

importosos.environ['CUDA_VISIBLE_DEVICES']='0,1'

也可以在命令行運行代碼時設(shè)置顯卡：

CUDA_VISIBLE_DEVICES=0,1pythontrain.py

清除顯存：

torch.cuda.empty_cache()

也可以使用在命令行重置GPU的指令：

nvidia-smi--gpu-reset-i[gpu_id]

張量(Tensor)處理

張量的數(shù)據(jù)類型

PyTorch有9種CPU張量類型和9種GPU張量類型。

張量基本信息

tensor = torch.randn(3,4,5)print(tensor.type()) # 數(shù)據(jù)類型print(tensor.size()) # 張量的shape，是個元組print(tensor.dim()) # 維度的數(shù)量

命名張量

張量命名是一個非常有用的方法，這樣可以方便地使用維度的名字來做索引或其他操作，大大提高了可讀性、易用性，防止出錯。

# 在PyTorch 1.3之前，需要使用注釋
# Tensor[N, C, H, W]
images = torch.randn(32, 3, 56, 56)
images.sum(dim=1)
images.select(dim=1, index=0)


# PyTorch 1.3之后
NCHW = [‘N’, ‘C’, ‘H’, ‘W’]
images = torch.randn(32, 3, 56, 56, names=NCHW)
images.sum('C')
images.select('C', index=0)
# 也可以這么設(shè)置
tensor = torch.rand(3,4,1,2,names=('C', 'N', 'H', 'W'))
# 使用align_to可以對維度方便地排序
tensor=tensor.align_to('N','C','H','W')

數(shù)據(jù)類型轉(zhuǎn)換

# 設(shè)置默認(rèn)類型，pytorch中的FloatTensor遠(yuǎn)遠(yuǎn)快于DoubleTensor
torch.set_default_tensor_type(torch.FloatTensor)


# 類型轉(zhuǎn)換
tensor = tensor.cuda()
tensor = tensor.cpu()
tensor = tensor.float()
tensor = tensor.long()

torch.Tensor與np.ndarray轉(zhuǎn)換

除了CharTensor，其他所有CPU上的張量都支持轉(zhuǎn)換為numpy格式然后再轉(zhuǎn)換回來。

ndarray = tensor.cpu().numpy()
tensor = torch.from_numpy(ndarray).float()
tensor = torch.from_numpy(ndarray.copy()).float() # If ndarray has negative stride.

Torch.tensor與PIL.Image轉(zhuǎn)換

# pytorch中的張量默認(rèn)采用[N, C, H, W]的順序，并且數(shù)據(jù)范圍在[0,1]，需要進(jìn)行轉(zhuǎn)置和規(guī)范化
# torch.Tensor -> PIL.Image
image = PIL.Image.fromarray(torch.clamp(tensor*255, min=0, max=255).byte().permute(1,2,0).cpu().numpy())
image = torchvision.transforms.functional.to_pil_image(tensor)  # Equivalently way


# PIL.Image -> torch.Tensor
path = r'./figure.jpg'
tensor = torch.from_numpy(np.asarray(PIL.Image.open(path))).permute(2,0,1).float() / 255
tensor = torchvision.transforms.functional.to_tensor(PIL.Image.open(path)) # Equivalently way

np.ndarray與PIL.Image的轉(zhuǎn)換

image = PIL.Image.fromarray(ndarray.astype(np.uint8))
ndarray = np.asarray(PIL.Image.open(path))

從只包含一個元素的張量中提取值

value=torch.rand(1).item()

張量形變

# 在將卷積層輸入全連接層的情況下通常需要對張量做形變處理，
# 相比torch.view，torch.reshape可以自動處理輸入張量不連續(xù)的情況


tensor = torch.rand(2,3,4)
shape = (6, 4)
tensor = torch.reshape(tensor, shape)

打亂順序

tensor=tensor[torch.randperm(tensor.size(0))]#打亂第一個維度

水平翻轉(zhuǎn)

# pytorch不支持tensor[::-1]這樣的負(fù)步長操作，水平翻轉(zhuǎn)可以通過張量索引實現(xiàn)
# 假設(shè)張量的維度為[N, D, H, W].


tensor = tensor[:,:,:,torch.arange(tensor.size(3) - 1, -1, -1).long()]

復(fù)制張量

# Operation                 |  New/Shared memory | Still in computation graph |
tensor.clone()            # |        New         |          Yes               |
tensor.detach()           # |      Shared        |          No                |
tensor.detach.clone()()#|New|No|

張量拼接

'''
注意torch.cat和torch.stack的區(qū)別在于torch.cat沿著給定的維度拼接，
而torch.stack會新增一維。例如當(dāng)參數(shù)是3個10x5的張量，torch.cat的結(jié)果是30x5的張量，
而torch.stack的結(jié)果是3x10x5的張量。
'''
tensor = torch.cat(list_of_tensors, dim=0)
tensor = torch.stack(list_of_tensors, dim=0)

將整數(shù)標(biāo)簽轉(zhuǎn)為one-hot編碼

# pytorch的標(biāo)記默認(rèn)從0開始
tensor = torch.tensor([0, 2, 1, 3])
N = tensor.size(0)
num_classes = 4
one_hot = torch.zeros(N, num_classes).long()
one_hot.scatter_(dim=1, index=torch.unsqueeze(tensor, dim=1), src=torch.ones(N, num_classes).long())

得到非零元素

torch.nonzero(tensor)               # index of non-zero elements
torch.nonzero(tensor==0)            # index of zero elements
torch.nonzero(tensor).size(0)       # number of non-zero elements
torch.nonzero(tensor == 0).size(0)  # number of zero elements

判斷兩個張量相等

torch.allclose(tensor1, tensor2)  # float tensor
torch.equal(tensor1, tensor2)     # int tensor

張量擴展

# Expand tensor of shape 64*512 to shape 64*512*7*7.
tensor = torch.rand(64,512)
torch.reshape(tensor, (64, 512, 1, 1)).expand(64, 512, 7, 7)

矩陣乘法

# Matrix multiplcation: (m*n) * (n*p) * -> (m*p).
result = torch.mm(tensor1, tensor2)


# Batch matrix multiplication: (b*m*n) * (b*n*p) -> (b*m*p)
result = torch.bmm(tensor1, tensor2)


# Element-wise multiplication.
result = tensor1 * tensor2

計算兩組數(shù)據(jù)之間的兩兩歐式距離

利用廣播機制

dist = torch.sqrt(torch.sum((X1[:,None,:] - X2) ** 2, dim=2))

模型定義和操作

一個簡單兩層卷積網(wǎng)絡(luò)的示例：

# convolutional neural network (2 convolutional layers)
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(7*7*32, num_classes)


    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out


model = ConvNet(num_classes).to(device)

雙線性匯合（bilinear pooling）

X = torch.reshape(N, D, H * W)                        # Assume X has shape N*D*H*W
X = torch.bmm(X, torch.transpose(X, 1, 2)) / (H * W)  # Bilinear pooling
assert X.size() == (N, D, D)
X = torch.reshape(X, (N, D * D))
X = torch.sign(X) * torch.sqrt(torch.abs(X) + 1e-5)   # Signed-sqrt normalization
X = torch.nn.functional.normalize(X)                  # L2 normalization

多卡同步 BN（Batch normalization）

當(dāng)使用 torch.nn.DataParallel 將代碼運行在多張 GPU 卡上時，PyTorch 的 BN 層默認(rèn)操作是各卡上數(shù)據(jù)獨立地計算均值和標(biāo)準(zhǔn)差，同步 BN 使用所有卡上的數(shù)據(jù)一起計算 BN 層的均值和標(biāo)準(zhǔn)差，緩解了當(dāng)批量大小（batch size）比較小時對均值和標(biāo)準(zhǔn)差估計不準(zhǔn)的情況，是在目標(biāo)檢測等任務(wù)中一個有效的提升性能的技巧。

sync_bn = torch.nn.SyncBatchNorm(num_features,

                                 eps=1e-05, 
                                 momentum=0.1, 
                                 affine=True, 
                                 track_running_stats=True)

將已有網(wǎng)絡(luò)的所有BN層改為同步BN層

def convertBNtoSyncBN(module, process_group=None):
    '''Recursively replace all BN layers to SyncBN layer.


    Args:
        module[torch.nn.Module]. Network
    '''
    if isinstance(module, torch.nn.modules.batchnorm._BatchNorm):
        sync_bn = torch.nn.SyncBatchNorm(module.num_features, module.eps, module.momentum, 
                                         module.affine, module.track_running_stats, process_group)
        sync_bn.running_mean = module.running_mean
        sync_bn.running_var = module.running_var
        if module.affine:
            sync_bn.weight = module.weight.clone().detach()
            sync_bn.bias = module.bias.clone().detach()
        return sync_bn
    else:
        for name, child_module in module.named_children():
            setattr(module, name) = convert_syncbn_model(child_module, process_group=process_group))
        return module

類似 BN 滑動平均

如果要實現(xiàn)類似 BN 滑動平均的操作，在 forward 函數(shù)中要使用原地（inplace）操作給滑動平均賦值。

class BN(torch.nn.Module)
    def __init__(self):
        ...
        self.register_buffer('running_mean', torch.zeros(num_features))


    def forward(self, X):
        ...
        self.running_mean += momentum * (current - self.running_mean)

計算模型整體參數(shù)量

num_parameters=sum(torch.numel(parameter)forparameterinmodel.parameters())

查看網(wǎng)絡(luò)中的參數(shù)

可以通過model.state_dict()或者model.named_parameters()函數(shù)查看現(xiàn)在的全部可訓(xùn)練參數(shù)（包括通過繼承得到的父類中的參數(shù)）

params = list(model.named_parameters())
(name, param) = params[28]
print(name)
print(param.grad)
print('-------------------------------------------------')
(name2, param2) = params[29]
print(name2)
print(param2.grad)
print('----------------------------------------------------')
(name1, param1) = params[30]
print(name1)
print(param1.grad)

模型可視化（使用pytorchviz）

szagoruyko/pytorchvizgithub.com

類似 Keras 的 model.summary() 輸出模型信息，使用pytorch-summary。

sksq96/pytorch-summarygithub.com

模型權(quán)重初始化

注意 model.modules() 和 model.children() 的區(qū)別：model.modules() 會迭代地遍歷模型的所有子層，而 model.children() 只會遍歷模型下的一層。

# Common practise for initialization.
for layer in model.modules():
    if isinstance(layer, torch.nn.Conv2d):
        torch.nn.init.kaiming_normal_(layer.weight, mode='fan_out',
                                      nonlinearity='relu')
        if layer.bias is not None:
            torch.nn.init.constant_(layer.bias, val=0.0)
    elif isinstance(layer, torch.nn.BatchNorm2d):
        torch.nn.init.constant_(layer.weight, val=1.0)
        torch.nn.init.constant_(layer.bias, val=0.0)
    elif isinstance(layer, torch.nn.Linear):
        torch.nn.init.xavier_normal_(layer.weight)
        if layer.bias is not None:
            torch.nn.init.constant_(layer.bias, val=0.0)


# Initialization with given tensor.
layer.weight = torch.nn.Parameter(tensor)

提取模型中的某一層

modules()會返回模型中所有模塊的迭代器，它能夠訪問到最內(nèi)層，比如self.layer1.conv1這個模塊，還有一個與它們相對應(yīng)的是name_children()屬性以及named_modules(),這兩個不僅會返回模塊的迭代器，還會返回網(wǎng)絡(luò)層的名字。

# 取模型中的前兩層
new_model = nn.Sequential(*list(model.children())[:2] 
# 如果希望提取出模型中的所有卷積層，可以像下面這樣操作：
for layer in model.named_modules():
    if isinstance(layer[1],nn.Conv2d):
         conv_model.add_module(layer[0],layer[1])

部分層使用預(yù)訓(xùn)練模型

注意如果保存的模型是 torch.nn.DataParallel，則當(dāng)前的模型也需要是：

model.load_state_dict(torch.load('model.pth'), strict=False)

將在 GPU 保存的模型加載到 CPU

model.load_state_dict(torch.load('model.pth', map_location='cpu'))

導(dǎo)入另一個模型的相同部分到新的模型

模型導(dǎo)入?yún)?shù)時，如果兩個模型結(jié)構(gòu)不一致，則直接導(dǎo)入?yún)?shù)會報錯。用下面方法可以把另一個模型的相同的部分導(dǎo)入到新的模型中。

# model_new代表新的模型
# model_saved代表其他模型，比如用torch.load導(dǎo)入的已保存的模型
model_new_dict = model_new.state_dict()
model_common_dict = {k:v for k, v in model_saved.items() if k in model_new_dict.keys()}
model_new_dict.update(model_common_dict)
model_new.load_state_dict(model_new_dict)

數(shù)據(jù)處理

計算數(shù)據(jù)集的均值和標(biāo)準(zhǔn)差

import os
import cv2
import numpy as np
from torch.utils.data import Dataset
from PIL import Image


def compute_mean_and_std(dataset):
    # 輸入PyTorch的dataset，輸出均值和標(biāo)準(zhǔn)差
    mean_r = 0
    mean_g = 0
    mean_b = 0


    for img, _ in dataset:
        img = np.asarray(img) # change PIL Image to numpy array
        mean_b += np.mean(img[:, :, 0])
        mean_g += np.mean(img[:, :, 1])
        mean_r += np.mean(img[:, :, 2])


    mean_b /= len(dataset)
    mean_g /= len(dataset)
    mean_r /= len(dataset)


    diff_r = 0
    diff_g = 0
    diff_b = 0


    N = 0


    for img, _ in dataset:
        img = np.asarray(img)


        diff_b += np.sum(np.power(img[:, :, 0] - mean_b, 2))
        diff_g += np.sum(np.power(img[:, :, 1] - mean_g, 2))
        diff_r += np.sum(np.power(img[:, :, 2] - mean_r, 2))


        N += np.prod(img[:, :, 0].shape)


    std_b = np.sqrt(diff_b / N)
    std_g = np.sqrt(diff_g / N)
    std_r = np.sqrt(diff_r / N)


    mean = (mean_b.item() / 255.0, mean_g.item() / 255.0, mean_r.item() / 255.0)
    std = (std_b.item() / 255.0, std_g.item() / 255.0, std_r.item() / 255.0)
    return mean, std

得到視頻數(shù)據(jù)基本信息

import cv2
video = cv2.VideoCapture(mp4_path)
height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
num_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
fps = int(video.get(cv2.CAP_PROP_FPS))
video.release()

TSN 每段（segment）采樣一幀視頻

K = self._num_segments
if is_train:
    if num_frames > K:
        # Random index for each segment.
        frame_indices = torch.randint(
            high=num_frames // K, size=(K,), dtype=torch.long)
        frame_indices += num_frames // K * torch.arange(K)
    else:
        frame_indices = torch.randint(
            high=num_frames, size=(K - num_frames,), dtype=torch.long)
        frame_indices = torch.sort(torch.cat((
            torch.arange(num_frames), frame_indices)))[0]
else:
    if num_frames > K:
        # Middle index for each segment.
        frame_indices = num_frames / K // 2
        frame_indices += num_frames // K * torch.arange(K)
    else:
        frame_indices = torch.sort(torch.cat((                              
            torch.arange(num_frames), torch.arange(K - num_frames))))[0]
assert frame_indices.size() == (K,)
return [frame_indices[i] for i in range(K)]

常用訓(xùn)練和驗證數(shù)據(jù)預(yù)處理

其中 ToTensor 操作會將 PIL.Image 或形狀為 H×W×D，數(shù)值范圍為 [0, 255] 的 np.ndarray 轉(zhuǎn)換為形狀為 D×H×W，數(shù)值范圍為 [0.0, 1.0] 的 torch.Tensor。

train_transform = torchvision.transforms.Compose([
    torchvision.transforms.RandomResizedCrop(size=224,
                                             scale=(0.08, 1.0)),
    torchvision.transforms.RandomHorizontalFlip(),
    torchvision.transforms.ToTensor(),
    torchvision.transforms.Normalize(mean=(0.485, 0.456, 0.406),
                                     std=(0.229, 0.224, 0.225)),
 ])
 val_transform = torchvision.transforms.Compose([
    torchvision.transforms.Resize(256),
    torchvision.transforms.CenterCrop(224),
    torchvision.transforms.ToTensor(),
    torchvision.transforms.Normalize(mean=(0.485, 0.456, 0.406),
                                     std=(0.229, 0.224, 0.225)),
])

模型訓(xùn)練和測試

分類模型訓(xùn)練代碼

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)


# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i ,(images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)


        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)


        # Backward and optimizer
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()


        if (i+1) % 100 == 0:
            print('Epoch: [{}/{}], Step: [{}/{}], Loss: {}'
                  .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

分類模型測試代碼

# Test the model
model.eval()  # eval mode(batch norm uses moving mean/variance 
              #instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()


    print('Test accuracy of the model on the 10000 test images: {} %'
          .format(100 * correct / total))

自定義loss

繼承torch.nn.Module類寫自己的loss。

class MyLoss(torch.nn.Moudle):
    def __init__(self):
        super(MyLoss, self).__init__()


    def forward(self, x, y):
        loss = torch.mean((x - y) ** 2)
        return loss

標(biāo)簽平滑（label smoothing）

寫一個label_smoothing.py的文件，然后在訓(xùn)練代碼里引用，用LSR代替交叉熵?fù)p失即可。label_smoothing.py內(nèi)容如下：

import torch
import torch.nn as nn

class LSR(nn.Module):


    def __init__(self, e=0.1, reduction='mean'):
        super().__init__()


        self.log_softmax = nn.LogSoftmax(dim=1)
        self.e = e
        self.reduction = reduction


    def _one_hot(self, labels, classes, value=1):
        """
            Convert labels to one hot vectors


        Args:
            labels: torch tensor in format [label1, label2, label3, ...]
            classes: int, number of classes
            value: label value in one hot vector, default to 1


        Returns:
            return one hot format labels in shape [batchsize, classes]
        """


        one_hot = torch.zeros(labels.size(0), classes)


        #labels and value_added  size must match
        labels = labels.view(labels.size(0), -1)
        value_added = torch.Tensor(labels.size(0), 1).fill_(value)


        value_added = value_added.to(labels.device)
        one_hot = one_hot.to(labels.device)


        one_hot.scatter_add_(1, labels, value_added)


        return one_hot


    def _smooth_label(self, target, length, smooth_factor):
        """convert targets to one-hot format, and smooth
        them.
        Args:
            target: target in form with [label1, label2, label_batchsize]
            length: length of one-hot format(number of classes)
            smooth_factor: smooth factor for label smooth


        Returns:
            smoothed labels in one hot format
        """
        one_hot = self._one_hot(target, length, value=1 - smooth_factor)
        one_hot += smooth_factor / (length - 1)


        return one_hot.to(target.device)


    def forward(self, x, target):


        if x.size(0) != target.size(0):
            raise ValueError('Expected input batchsize ({}) to match target batch_size({})'
                    .format(x.size(0), target.size(0)))


        if x.dim() < 2:
            raise ValueError('Expected input tensor to have least 2 dimensions(got {})'
                    .format(x.size(0)))


        if x.dim() != 2:
            raise ValueError('Only 2 dimension tensor are implemented, (got {})'
                    .format(x.size()))




        smoothed_target = self._smooth_label(target, x.size(1), self.e)
        x = self.log_softmax(x)
        loss = torch.sum(- x * smoothed_target, dim=1)


        if self.reduction == 'none':
            return loss


        elif self.reduction == 'sum':
            return torch.sum(loss)


        elif self.reduction == 'mean':
            return torch.mean(loss)


        else:
            raise ValueError('unrecognized option, expect reduction to be one of none, mean, sum')

for images, labels in train_loader:
    images, labels = images.cuda(), labels.cuda()
    N = labels.size(0)
    # C is the number of classes.
    smoothed_labels = torch.full(size=(N, C), fill_value=0.1 / (C - 1)).cuda()
    smoothed_labels.scatter_(dim=1, index=torch.unsqueeze(labels, dim=1), value=0.9)


    score = model(images)
    log_prob = torch.nn.functional.log_softmax(score, dim=1)
    loss = -torch.sum(log_prob * smoothed_labels) / N
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

Mixup訓(xùn)練

beta_distribution = torch.distributions.beta.Beta(alpha, alpha)
for images, labels in train_loader:
    images, labels = images.cuda(), labels.cuda()


    # Mixup images and labels.
    lambda_ = beta_distribution.sample([]).item()
    index = torch.randperm(images.size(0)).cuda()
    mixed_images = lambda_ * images + (1 - lambda_) * images[index, :]
    label_a, label_b = labels, labels[index]


    # Mixup loss.
    scores = model(mixed_images)
    loss = (lambda_ * loss_function(scores, label_a)
            + (1 - lambda_) * loss_function(scores, label_b))
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

L1 正則化

l1_regularization = torch.nn.L1Loss(reduction='sum')
loss = ...  # Standard cross-entropy loss


for param in model.parameters():
    loss += torch.sum(torch.abs(param))
loss.backward()

不對偏置項進(jìn)行權(quán)重衰減（weight decay)

pytorch里的weight decay相當(dāng)于l2正則：

bias_list = (param for name, param in model.named_parameters() if name[-4:] == 'bias')
others_list = (param for name, param in model.named_parameters() if name[-4:] != 'bias')
parameters = [{'parameters': bias_list, 'weight_decay': 0},                
              {'parameters': others_list}]
optimizer = torch.optim.SGD(parameters, lr=1e-2, momentum=0.9, weight_decay=1e-4)

梯度裁剪（gradient clipping）

torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=20)

# If there is one global learning rate (which is the common case).
lr = next(iter(optimizer.param_groups))['lr']


# If there are multiple learning rates for different layers.
all_lr = []
for param_group in optimizer.param_groups:
    all_lr.append(param_group['lr'])

學(xué)習(xí)率衰減

# Reduce learning rate when validation accuarcy plateau.
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', patience=5, verbose=True)
for t in range(0, 80):
    train(...)
    val(...)
    scheduler.step(val_acc)


# Cosine annealing learning rate.
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=80)
# Reduce learning rate by 10 at given epochs.
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=[50, 70], gamma=0.1)
for t in range(0, 80):
    scheduler.step()    
    train(...)
    val(...)


# Learning rate warmup by 10 epochs.
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda t: t / 10)
for t in range(0, 10):
    scheduler.step()
    train(...)
    val(...)

優(yōu)化器鏈?zhǔn)礁?/strong>

import torch
from torch.optim import SGD
from torch.optim.lr_scheduler import ExponentialLR, StepLR
model = [torch.nn.Parameter(torch.randn(2, 2, requires_grad=True))]
optimizer = SGD(model, 0.1)
scheduler1 = ExponentialLR(optimizer, gamma=0.9)
scheduler2 = StepLR(optimizer, step_size=3, gamma=0.1)
for epoch in range(4):
    print(epoch, scheduler2.get_last_lr()[0])
    optimizer.step()
    scheduler1.step()
    scheduler2.step()

pip install tensorboard
tensorboard --logdir=runs

from torch.utils.tensorboard import SummaryWriter
import numpy as np


writer = SummaryWriter()


for n_iter in range(100):
    writer.add_scalar('Loss/train', np.random.random(), n_iter)
    writer.add_scalar('Loss/test', np.random.random(), n_iter)
    writer.add_scalar('Accuracy/train', np.random.random(), n_iter)
    writer.add_scalar('Accuracy/test', np.random.random(), n_iter)

start_epoch = 0
# Load checkpoint.
if resume: # resume為參數(shù)，第一次訓(xùn)練時設(shè)為0，中斷再訓(xùn)練時設(shè)為1
    model_path = os.path.join('model', 'best_checkpoint.pth.tar')
    assert os.path.isfile(model_path)
    checkpoint = torch.load(model_path)
    best_acc = checkpoint['best_acc']
    start_epoch = checkpoint['epoch']
    model.load_state_dict(checkpoint['model'])
    optimizer.load_state_dict(checkpoint['optimizer'])
    print('Load checkpoint at epoch {}.'.format(start_epoch))
    print('Best accuracy so far {}.'.format(best_acc))


# Train the model
for epoch in range(start_epoch, num_epochs): 
    ... 

    # Test the model
    ...


    # save checkpoint
    is_best = current_acc > best_acc
    best_acc = max(current_acc, best_acc)
    checkpoint = {
        'best_acc': best_acc,
        'epoch': epoch + 1,
        'model': model.state_dict(),
        'optimizer': optimizer.state_dict(),
    }
    model_path = os.path.join('model', 'checkpoint.pth.tar')
    best_model_path = os.path.join('model', 'best_checkpoint.pth.tar')
    torch.save(checkpoint, model_path)
    if is_best:
        shutil.copy(model_path, best_model_path)

# VGG-16 relu5-3 feature.
model = torchvision.models.vgg16(pretrained=True).features[:-1]
# VGG-16 pool5 feature.
model = torchvision.models.vgg16(pretrained=True).features
# VGG-16 fc7 feature.
model = torchvision.models.vgg16(pretrained=True)
model.classifier = torch.nn.Sequential(*list(model.classifier.children())[:-3])
# ResNet GAP feature.
model = torchvision.models.resnet18(pretrained=True)
model = torch.nn.Sequential(collections.OrderedDict(
    list(model.named_children())[:-1]))


with torch.no_grad():
    model.eval()
    conv_representation = model(image)

class FeatureExtractor(torch.nn.Module):
    """Helper class to extract several convolution features from the given
    pre-trained model.


    Attributes:
        _model, torch.nn.Module.
        _layers_to_extract, list or set


    Example:
        >>> model = torchvision.models.resnet152(pretrained=True)
        >>> model = torch.nn.Sequential(collections.OrderedDict(
                list(model.named_children())[:-1]))
        >>> conv_representation = FeatureExtractor(
                pretrained_model=model,
                layers_to_extract={'layer1', 'layer2', 'layer3', 'layer4'})(image)
    """
    def __init__(self, pretrained_model, layers_to_extract):
        torch.nn.Module.__init__(self)
        self._model = pretrained_model
        self._model.eval()
        self._layers_to_extract = set(layers_to_extract)


    def forward(self, x):
        with torch.no_grad():
            conv_representation = []
            for name, layer in self._model.named_children():
                x = layer(x)
                if name in self._layers_to_extract:
                    conv_representation.append(x)
            return conv_representation

model = torchvision.models.resnet18(pretrained=True)
for param in model.parameters():
    param.requires_grad = False
model.fc = nn.Linear(512, 100)  # Replace the last fc layer
optimizer=torch.optim.SGD(model.fc.parameters(),lr=1e-2,momentum=0.9,weight_decay=1e-4)

以較大學(xué)習(xí)率微調(diào)全連接層，較小學(xué)習(xí)率微調(diào)卷積層：

model = torchvision.models.resnet18(pretrained=True)
finetuned_parameters = list(map(id, model.fc.parameters()))
conv_parameters = (p for p in model.parameters() if id(p) not in finetuned_parameters)
parameters = [{'params': conv_parameters, 'lr': 1e-3}, 
              {'params': model.fc.parameters()}]
optimizer = torch.optim.SGD(parameters, lr=1e-2, momentum=0.9, weight_decay=1e-4)

x=torch.nn.functional.relu(x,inplace=True)

減少 CPU 和 GPU 之間的數(shù)據(jù)傳輸。例如如果你想知道一個 epoch 中每個 mini-batch 的 loss 和準(zhǔn)確率，先將它們累積在 GPU 中等一個 epoch 結(jié)束之后一起傳輸回 CPU 會比每個 mini-batch 都進(jìn)行一次 GPU 到 CPU 的傳輸更快。

  ...print(profile)# 或者在命令行運行python -m torch.utils.bottleneck main.py

# pip install torchsnooper
import torchsnooper# 對于函數(shù)，使用修飾器@torchsnooper.snoop()


# 如果不是函數(shù)，使用 with 語句來激活 TorchSnooper，把訓(xùn)練的那個循環(huán)裝進(jìn) with 語句中去。
with torchsnooper.snoop():    
  原本的代碼