• 來源：機器學習演算法與自然語言處理

基本配置

匯入包和版本查詢

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))

可復現性

在硬體裝置（CPU、GPU）不同時，完全的可復現性無法保證，即使隨機種子相同。但是，在同一個裝置上，應該保證可復現性。具體做法是，在程式開始的時候固定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

顯示卡設定

如果只需要一張顯示卡

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

如果需要指定多張顯示卡，比如0，1號顯示卡。

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

也可以在命令列執行程式碼時設定顯示卡：

CUDA_VISIBLE_DEVICES=0,1 python train.py
清除視訊記憶體

torch.cuda.empty_cache()
也可以使用在命令列重置GPU的指令

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

張量（Tensor）處理

張量的資料型別

PyTorch有9種CPU張量型別和9種GPU張量型別。

張量基本資訊

tensor = torch.randn(3,4,5)
print(tensor.type())  # 資料型別
print(tensor.size())  # 張量的shape，是個元組
print(tensor.dim())   # 維度的數量
 

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，需要使用註釋
# 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之後
NCHW = [‘N’, ‘C’, ‘H’, ‘W’]
images = torch.randn(32, 3, 56, 56, names=NCHW)
images.sum('C')
images.select('C', index=0)

# 也可以這麼設定
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')

資料型別轉換

# 設定預設型別，pytorch中的FloatTensor遠遠快於DoubleTensor
torch.set_default_tensor_type(torch.FloatTensor)

# 型別轉換
tensor = tensor.cuda()
tensor = tensor.cpu()
tensor = tensor.float()
tensor = tensor.long()

torch.Tensor與np.ndarray轉換

除了CharTensor，其他所有CPU上的張量都支援轉換為numpy格式然後再轉換回來。

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轉換

# pytorch中的張量預設採用[N, C, H, W]的順序，並且資料範圍在[0,1]，需要進行轉置和規範化
# 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線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

# pytorch不支援tensor[::-1]這樣的負步長操作，水平翻轉可以通過張量索引實現# 假設張量的維度為[N, D, H, W].tensor = tensor[:,:,:,torch.arange(tensor.size(3) - 1, -1, -1).long()]

## 複製張量
# 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的區別在於torch.cat沿著給定的維度拼接，
# 而torch.stack會新增一維。例如當引數是3個10x5的張量，torch.cat的結果是30x5的張量，
# 而torch.stack的結果是3x10x5的張量。

tensor = torch.cat(list_of_tensors, dim=0)
tensor = torch.stack(list_of_tensors, dim=0)

將整數標籤轉為one-hot編碼

# pytorch的標記預設從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

張量擴充套件

# 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

計算兩組資料之間的兩兩歐式距離

利用broadcast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路的示例

# 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）

當使用 torch.nn.DataParallel 將程式碼執行在多張 GPU 卡上時，PyTorch 的 BN 層預設操作是各卡上資料獨立地計算均值和標準差，同步 BN 使用所有卡上的資料一起計算 BN 層的均值和標準差，緩解了當批量大小（batch size）比較小時對均值和標準差估計不準的情況，是在目標檢測等任務中一個有效的提升效能的技巧。

sync_bn = torch.nn.SyncBatchNorm(num_features, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)

將已有網路的所有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

如果要實現類似 BN 滑動平均的操作，在 forward 函式中要使用原地（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)

計算模型整體引數量

num_parameters = sum(torch.numel(parameter) for parameter in model.parameters())

檢視網路中的引數

可以通過model.state_dict()或者model.named_parameters()函式檢視現在的全部可訓練引數（包括通過繼承得到的父類中的引數）

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)

模型視覺化（使用pytorchviz）

szagoruyko/pytorchvizgithub.com

類似 Keras 的 model.summary() 輸出模型資訊，使用pytorch-summary
sksq96/pytorch-summarygithub.com

模型權重初始化

注意 model.modules() 和 model.children() 的區別：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組的迭代器，它能夠訪問到最內層，比如self.layer1.conv1這個模組，還有一個與它們相對應的是name_children()屬性以及named_modules(),這兩個不僅會返回模組的迭代器，還會返回網路層的名字。

# 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])

部分層使用預訓練模型

注意如果儲存的模型是 torch.nn.DataParallel，則當前的模型也需要是

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

將在 GPU 儲存的模型載入到 CPU

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

匯入另一個模型的相同部分到新的模型

模型匯入引數時，如果兩個模型結構不一致，則直接匯入引數會報錯。用下面方法可以把另一個模型的相同的部分匯入到新的模型中。

# model_new代表新的模型
# model_saved代表其他模型，比如用torch.load匯入的已儲存的模型
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)```
# 資料處理
## 計算資料集的均值和標準差

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，輸出均值和標準差
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

## 得到視訊資料基本資訊

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）取樣一幀視訊

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)]

## 常用訓練和驗證資料預處理

其中 ToTensor 操作會將 PIL.Image 或形狀為 H×W×D，數值範圍為 [0, 255] 的 np.ndarray 轉換為形狀為 D×H×W，數值範圍為 [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)),
])

模型訓練和測試

分類模型訓練程式碼

# 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()))```
## 分類模型測試程式碼

```# 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

## 標籤平滑（label smoothing）

寫一個`label_smoothing.py`的檔案，然後在訓練程式碼裡引用，用**LSR**代替交叉熵損失即可。label_smoothing.py內容如下：

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')

或者**直接在訓練檔案**裡做**label smoothing**

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()

## 不對偏置項進行權重衰減（weight decay）

pytorch裡的weight decay相當於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)```
## 得到當前學習率

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'])

另一種方法，在一個`batch`訓練程式碼裡，當前的`lr`是`optimizer.param_groups[0]['lr']`

## 學習率衰減

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(...)

## 優化器鏈式更新
從1.4版本開始，`torch.optim.lr_scheduler` 支援鏈式更新（chaining），即使用者可以定義兩個 `schedulers`，並交替在訓練中使用。

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()

## 模型訓練視覺化

PyTorch可以使用tensorboard來視覺化訓練過程。

安裝和執行TensorBoard。

pip install tensorboard
tensorboard --logdir=runs```
使用SummaryWriter類來收集和視覺化相應的資料，放了方便檢視，可以使用不同的資料夾，比如'Loss/train'和'Loss/test'。

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)

儲存與載入斷點

注意為了能夠恢復訓練，我們需要同時儲存模型和優化器的狀態，以及當前的訓練輪數。

start_epoch = 0
# Load checkpoint.
if resume: # resume為引數，第一次訓練時設為0，中斷再訓練時設為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)

提取 ImageNet 預訓練模型某層的卷積特徵

# 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)

提取 ImageNet 預訓練模型多層的卷積特徵

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<str> or set<str>

    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

微調全連線層

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)

以較大學習率微調全連線層，較小學習率微調卷積層

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)

其他注意事項

• 不要使用太大的線性層。因為nn.Linear(m,n)使用的是O(mn)的記憶體，線性層太大很容易超出現有視訊記憶體。

• 不要在太長的序列上使用RNN。因為RNN反向傳播使用的是BPTT演算法，其需要的記憶體和輸入序列的長度呈線性關係。

• model(x) 前用 model.train() 和 model.eval() 切換網路狀態。

• 不需要計算梯度的程式碼塊用 with torch.no_grad() 包含起來。

• model.eval() 和 torch.no_grad() 的區別在於，model.eval() 是將網路切換為測試狀態，例如 BN 和dropout在訓練和測試階段使用不同的計算方法。torch.no_grad() 是關閉 PyTorch 張量的自動求導機制，以減少儲存使用和加速計算，得到的結果無法進行 loss.backward()。

• model.zero_grad()會把整個模型的引數的梯度都歸零, 而optimizer.zero_grad()只會把傳入其中的引數的梯度歸零.

• torch.nn.CrossEntropyLoss 的輸入不需要經過 Softmax。

• torch.nn.CrossEntropyLoss 等價於 torch.nn.functional.log_softmax + torch.nn.NLLLoss。

• loss.backward() 前用 optimizer.zero_grad() 清除累積梯度。

• torch.utils.data.DataLoader 中儘量設定 pin_memory=True，對特別小的資料集如 MNIST 設定 pin_memory=False 反而更快一些。num_workers 的設定需要在實驗中找到最快的取值。

• 用 del 及時刪除不用的中間變數，節約 GPU 儲存。

• 使用 inplace 操作可節約 GPU 儲存，如
  x = torch.nn.functional.relu(x, inplace=True)

• 減少 CPU 和 GPU 之間的資料傳輸。例如如果你想知道一個 epoch 中每個 mini-batch 的 loss 和準確率，先將它們累積在 GPU 中等一個 epoch 結束之後一起傳輸回 CPU 會比每個 mini-batch 都進行一次 GPU 到 CPU 的傳輸更快。

• 使用半精度浮點數 half() 會有一定的速度提升，具體效率依賴於 GPU 型號。需要小心數值精度過低帶來的穩定性問題。

• 時常使用 assert tensor.size() == (N, D, H, W) 作為除錯手段，確保張量維度和你設想中一致。

• 除了標記 y 外，儘量少使用一維張量，使用 n*1 的二維張量代替，可以避免一些意想不到的一維張量計算結果。

• 統計程式碼各部分耗時
  with torch.autograd.profiler.profile(enabled=True, use_cuda=False) as profile: ...print(profile)# 或者在命令列執行python -m torch.utils.bottleneck main.py

• 使用TorchSnooper來除錯PyTorch程式碼，程式在執行的時候，就會自動 print 出來每一行的執行結果的 tensor 的形狀、資料型別、裝置、是否需要梯度的資訊。
  # pip install torchsnooperimport torchsnooper# 對於函式，使用修飾器@torchsnooper.snoop()# 如果不是函式，使用 with 語句來啟用 TorchSnooper，把訓練的那個迴圈裝進 with 語句中去。with torchsnooper.snoop(): 原本的代
  https://github.com/zasdfgbnm/TorchSnoopergithub.com
  模型可解釋性，使用captum庫：https://captum.ai/captum.ai
  參考資料
  張皓：PyTorch Cookbook（常用程式碼段整理合集），https://zhuanlan.zhihu.com/p/59205847?
  PyTorch官方文件和示例
  https://pytorch.org/docs/stable/notes/faq.html
  https://github.com/szagoruyko/pytorchviz
  https://github.com/sksq96/pytorch-summary