本文代碼基于PyTorch 1.0版本，需要用到以下包

import collections import os import shutil import tqdmimport numpy as np import PIL.Image import torch import torchvision

1. 基礎配置

檢查PyTorch版本

torch.__version__ # PyTorch version torch.version.cuda # Corresponding CUDA version torch.backends.cudnn.version() # Corresponding cuDNN version torch.cuda.get_device_name(0) # GPU type

更新PyTorch

PyTorch將被安裝在anaconda3/lib/python3.7/site-packages/torch/目錄下。

conda update pytorch torchvision -c pytorch

固定隨機種子

def set_seeds(seed, cuda):""" Set Numpy and PyTorch seeds."""np.random.seed(seed)torch.manual_seed(seed)if cuda:torch.cuda.manual_seed_all(seed)print ("==> Set NumPy and PyTorch seeds.")

指定程序運行在特定GPU卡上

在命令行指定環境變量

CUDA_VISIBLE_DEVICES=0,1 python train.py

或在代碼中指定

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

判斷是否有CUDA支持

torch.cuda.is_available()

設置為cuDNN benchmark模式

Benchmark模式會提升計算速度，但是由于計算中有隨機性，每次網絡前饋結果略有差異。

torch.backends.cudnn.benchmark = True

如果想要避免這種結果波動，設置

torch.backends.cudnn.deterministic = True

清除GPU存儲

有時Control-C中止運行后GPU存儲沒有及時釋放，需要手動清空。在PyTorch內部可以

torch.cuda.empty_cache()

或在命令行可以先使用ps找到程序的PID，再使用kill結束該進程

ps aux | grep python kill -9 [pid]

或者直接重置沒有被清空的GPU

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

2. 張量處理

張量基本信息

tensor.type() # Data type tensor.size() # Shape of the tensor. It is a subclass of Python tuple tensor.dim() # Number of dimensions.

數據類型轉換

# Set default tensor type. Float in PyTorch is much faster than double. torch.set_default_tensor_type(torch.FloatTensor)# Type convertions. tensor = tensor.cuda() tensor = tensor.cpu() tensor = tensor.float() tensor = tensor.long()

torch.Tensor與np.ndarray轉換

# torch.Tensor -> np.ndarray. ndarray = tensor.cpu().numpy()# np.ndarray -> torch.Tensor. 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中的張量默認采用N×D×H×W的順序，并且數據范圍在[0, 1]，需要進行轉置和規范化。

# 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. 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轉換

# np.ndarray -> PIL.Image. image = PIL.Image.fromarray(ndarray.astypde(np.uint8))# PIL.Image -> np.ndarray. ndarray = np.asarray(PIL.Image.open(path))

從只包含一個元素的張量中提取值

這在訓練時統計loss的變化過程中特別有用。否則這將累積計算圖，使GPU存儲占用量越來越大。

value = tensor.item()

張量形變

張量形變常常需要用于將卷積層特征輸入全連接層的情形。相比torch.view，torch.reshape可以自動處理輸入張量不連續的情況。

tensor = torch.reshape(tensor, shape)

打亂順序

tensor = tensor[torch.randperm(tensor.size(0))] # Shuffle the first dimension

水平翻轉

PyTorch不支持tensor[::-1]這樣的負步長操作，水平翻轉可以用張量索引實現。

# Assume tensor has shape N*D*H*W. tensor = tensor[:, :, :, torch.arange(tensor.size(3) - 1, -1, -1).long()]

復制張量

有三種復制的方式，對應不同的需求。

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

拼接張量

注意torch.cat和torch.stack的區別在于torch.cat沿著給定的維度拼接，而torch.stack會新增一維。例如當參數是3個10×5的張量，torch.cat的結果是30×5的張量，而torch.stack的結果是3×10×5的張量。

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

將整數標記轉換成獨熱（one-hot）編碼

PyTorch中的標記默認從0開始。

N = tensor.size(0) 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())

得到非零/零元素

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

張量擴展

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

矩陣乘法

# Matrix multiplication: (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

計算兩組數據之間的兩兩歐式距離

# X1 is of shape m*d. X1 = torch.unsqueeze(X1, dim=1).expand(m, n, d) # X2 is of shape n*d. X2 = torch.unsqueeze(X2, dim=0).expand(m, n, d) # dist is of shape m*n, where dist[i][j] = sqrt(|X1[i, :] - X[j, :]|^2) dist = torch.sqrt(torch.sum((X1 - X2) ** 2, dim=2))

3. 模型定義

卷積層

最常用的卷積層配置是

conv = torch.nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=True) conv = torch.nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0, bias=True)

如果卷積層配置比較復雜，不方便計算輸出大小時，可以利用如下可視化工具輔助?Convolution Visualizer

GAP（Global average pooling）層

gap = torch.nn.AdaptiveAvgPool2d(output_size=1)

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將代碼運行在多張GPU卡上時，PyTorch的BN層默認操作是各卡上數據獨立地計算均值和標準差，同步BN使用所有卡上的數據一起計算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性能的技巧。

vacancy/Synchronized-BatchNorm-PyTorch?

類似BN滑動平均

如果要實現類似BN滑動平均的操作，在forward函數中要使用原地（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)

計算模型整體參數量

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

類似Keras的model.summary()輸出模型信息

sksq96/pytorch-summary?

模型權值初始化

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)

部分層使用預訓練模型

注意如果保存的模型是torch.nn.DataParallel，則當前的模型也需要是torch.nn.DataParallel。torch.nn.DataParallel(model).module == model。

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'))

4. 數據準備、特征提取與微調

得到視頻數據基本信息

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 // 2frame_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)]

提取ImageNet預訓練模型某層的卷積特征

# 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征

class FeatureExtractor(torch.nn.Module):"""Helper class to extract several convolution features from the givenpre-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_modelself._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

其他預訓練模型

Cadene/pretrained-models.pytorch?

微調全連接層

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接層，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)

5. 模型訓練

常用訓練和驗證數據預處理

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

訓練基本代碼框架

for t in epoch(80):for images, labels in tqdm.tqdm(train_loader, desc='Epoch %3d' % (t + 1)):images, labels = images.cuda(), labels.cuda()scores = model(images)loss = loss_function(scores, labels)optimizer.zero_grad()loss.backward()optimizer.step()

標記平滑（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) / Noptimizer.zero_grad()loss.backward()optimizer.step()

Mixup

beta_distribution = torch.distributions.beta.Beta(alpha, alpha) for images, labels in train_loader:images, labels = images.cuda(), labels.cuda()# Mixup images.lambda_ = beta_distribution.sample([]).item()index = torch.randperm(images.size(0)).cuda()mixed_images = lambda_ * images + (1 - lambda_) * images[index, :]# Mixup loss. scores = model(mixed_images)loss = (lambda_ * loss_function(scores, labels) + (1 - lambda_) * loss_function(scores, labels[index]))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 += lambda_ * torch.sum(torch.abs(param)) loss.backward()

不對偏置項進行L2正則化/權值衰減（weight decay）

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)

計算Softmax輸出的準確率

score = model(images) prediction = torch.argmax(score, dim=1) num_correct = torch.sum(prediction == labels).item() accuruacy = num_correct / labels.size(0)

可視化模型前饋的計算圖

szagoruyko/pytorchviz?

可視化學習曲線

有Facebook自己開發的Visdom和Tensorboard兩個選擇。

facebookresearch/visdom?

lanpa/tensorboardX

# Example using Visdom. vis = visdom.Visdom(env='Learning curve', use_incoming_socket=False) assert self._visdom.check_connection() self._visdom.close() options = collections.namedtuple('Options', ['loss', 'acc', 'lr'])(loss={'xlabel': 'Epoch', 'ylabel': 'Loss', 'showlegend': True},acc={'xlabel': 'Epoch', 'ylabel': 'Accuracy', 'showlegend': True},lr={'xlabel': 'Epoch', 'ylabel': 'Learning rate', 'showlegend': True})for t in epoch(80):tran(...)val(...)vis.line(X=torch.Tensor([t + 1]), Y=torch.Tensor([train_loss]),name='train', win='Loss', update='append', opts=options.loss)vis.line(X=torch.Tensor([t + 1]), Y=torch.Tensor([val_loss]),name='val', win='Loss', update='append', opts=options.loss)vis.line(X=torch.Tensor([t + 1]), Y=torch.Tensor([train_acc]),name='train', win='Accuracy', update='append', opts=options.acc)vis.line(X=torch.Tensor([t + 1]), Y=torch.Tensor([val_acc]),name='val', win='Accuracy', update='append', opts=options.acc)vis.line(X=torch.Tensor([t + 1]), Y=torch.Tensor([lr]),win='Learning rate', update='append', opts=options.lr)

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'])

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(...)

保存與加載斷點

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

# Save checkpoint. is_best = current_acc > best_acc best_acc = max(best_acc, current_acc) checkpoint = {'best_acc': best_acc, 'epoch': t + 1,'model': model.state_dict(),'optimizer': optimizer.state_dict(), } model_path = os.path.join('model', 'checkpoint.pth.tar') torch.save(checkpoint, model_path) if is_best:shutil.copy('checkpoint.pth.tar', model_path)# Load checkpoint. if resume:model_path = os.path.join('model', '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 %d.' % start_epoch)

計算準確率、查準率（precision）、查全率（recall）

# data['label'] and data['prediction'] are groundtruth label and prediction # for each image, respectively. accuracy = np.mean(data['label'] == data['prediction']) * 100# Compute recision and recall for each class. for c in range(len(num_classes)):tp = np.dot((data['label'] == c).astype(int),(data['prediction'] == c).astype(int))tp_fp = np.sum(data['prediction'] == c)tp_fn = np.sum(data['label'] == c)precision = tp / tp_fp * 100recall = tp / tp_fn * 100

6. PyTorch其他注意事項

模型定義

• 建議有參數的層和匯合（pooling）層使用torch.nn模塊定義，激活函數直接使用torch.nn.functional。torch.nn模塊和torch.nn.functional的區別在于，torch.nn模塊在計算時底層調用了torch.nn.functional，但torch.nn模塊包括該層參數，還可以應對訓練和測試兩種網絡狀態。使用torch.nn.functional時要注意網絡狀態，如

def forward(self, x):...x = torch.nn.functional.dropout(x, p=0.5, training=self.training)

• model(x)前用model.train()和model.eval()切換網絡狀態。
• 不需要計算梯度的代碼塊用with torch.no_grad()包含起來。model.eval()和torch.no_grad()的區別在于，model.eval()是將網絡切換為測試狀態，例如BN和隨機失活（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，以減少存儲使用和加速計算，得到的結果無法進行loss.backward()。
• torch.nn.CrossEntropyLoss的輸入不需要經過Softmax。torch.nn.CrossEntropyLoss等價于torch.nn.functional.log_softmax + torch.nn.NLLLoss。
• loss.backward()前用optimizer.zero_grad()清除累積梯度。optimizer.zero_grad()和model.zero_grad()效果一樣。

PyTorch性能與調試

• torch.utils.data.DataLoader中盡量設置pin_memory=True，對特別小的數據集如MNIST設置pin_memory=False反而更快一些。num_workers的設置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量，節約GPU存儲。
• 使用inplace操作可節約GPU存儲，如

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

• 減少CPU和GPU之間的數據傳輸。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結束之后一起傳輸回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，具體效率依賴于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)作為調試手段，確保張量維度和你設想中一致。
• 除了標記y外，盡量少使用一維張量，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。
• 統計代碼各部分耗時

with torch.autograd.profiler.profile(enabled=True, use_cuda=False) as profile:... print(profile)

或者在命令行運行

python -m torch.utils.bottleneck main.py

?

參考資料

• PyTorch官方代碼：pytorch/examples
• PyTorch論壇：PyTorch Forums
• PyTorch文檔：http://pytorch.org/docs/stable/index.html
• 其他基于PyTorch的公開實現代碼，無法一一列舉

?

轉：?https://zhuanlan.zhihu.com/p/59205847?

創作挑戰賽新人創作獎勵來咯，堅持創作打卡瓜分現金大獎

總結

以上是生活随笔為你收集整理的PyTorch常用代码段整理合集的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。