前端自從出現(xiàn)了MVVM架構(gòu)之后,一直火爆到現(xiàn)在,據(jù)說(shuō)阿里巴巴當(dāng)時(shí)不管有用沒(méi)用的前端都招過(guò)來(lái)了,說(shuō)實(shí)在不管是vue、還是react他們的核心語(yǔ)言也是JavaScript,而技術(shù)的進(jìn)階的話還是要看基本功就是對(duì)JavaScript的了解程度,所以你會(huì)發(fā)現(xiàn)一些程序編程大牛,到最后還是會(huì)回頭看JavaScript的基礎(chǔ),因?yàn)榧軜?gòu)可能發(fā)生改變但是原生基礎(chǔ)是改變不了的。
那么想要深入了解JavaScript的話,就必須對(duì)瀏覽器中的調(diào)式工具應(yīng)用的熟練,瀏覽器中擁有一個(gè)神一樣的調(diào)式工具,這通常是前端程序員進(jìn)階的分水嶺。那就是"斷點(diǎn)調(diào)式",千萬(wàn)別小瞧這個(gè),很多公司通過(guò)一個(gè)項(xiàng)目的bug來(lái)看程序員是如何打斷點(diǎn)并且找到解決方案,來(lái)判斷前端程序員的水平的。
以chorme瀏覽器調(diào)式為例子:
快捷鍵F12或者通過(guò)設(shè)置打開開發(fā)者工具看到sources就是斷點(diǎn)調(diào)式的入口
首先在實(shí)例之前的話我要介紹下斷點(diǎn)的類型:
普通斷點(diǎn):
這種藍(lán)色的就是普通的斷點(diǎn)
條件斷點(diǎn):
通過(guò)打完斷點(diǎn)之后右鍵選擇Edit Breakpoint...”可以設(shè)置觸發(fā)斷點(diǎn)的條件,就是寫一個(gè)表達(dá)式,表達(dá)式為 true 時(shí)才觸發(fā)斷點(diǎn)。
斷點(diǎn)要怎么打才合適?
雖然說(shuō)打斷點(diǎn)的操作是比較簡(jiǎn)單的,但是打斷點(diǎn)到底應(yīng)該如何打呢?通常來(lái)說(shuō)一個(gè)程序擁有bugs時(shí)我們運(yùn)用到斷點(diǎn)是比較多的,比如下圖所示:
本來(lái)點(diǎn)擊加載更多完之后會(huì)有更多的數(shù)據(jù)
有經(jīng)驗(yàn)的程序員看到這種情況一般來(lái)說(shuō)要么是后端的接口產(chǎn)生問(wèn)題了,要么自己的ajax出現(xiàn)了問(wèn)題,這個(gè)時(shí)候就可以用斷點(diǎn)進(jìn)行調(diào)式。其實(shí)可以現(xiàn)用postman調(diào)式一下后端的數(shù)據(jù)是否出現(xiàn)問(wèn)題了,如果后端訪問(wèn)的是正常的,那么基本是我們的前端代碼出現(xiàn)問(wèn)題了。前端點(diǎn)擊無(wú)效果如果細(xì)分的話也有很多因素(選擇器錯(cuò)誤,語(yǔ)法錯(cuò)誤,被選擇的元素是后生成),這些的話,就需要程序員通過(guò)采用console來(lái)配合基本功來(lái)慢慢調(diào)式。最終找到問(wèn)題所在,然后來(lái)改掉bug!
源:關(guān)于數(shù)據(jù)分析與可視化
本文約8000字,建議閱讀10+分鐘
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(cè)試等5個(gè)方面,還給出了多個(gè)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(bǔ),方便使用時(shí)查閱。
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))
在硬件設(shè)備(CPU、GPU)不同時(shí),完全的可復(fù)現(xiàn)性無(wú)法保證,即使隨機(jī)種子相同。但是,在同一個(gè)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(shí)候固定torch的隨機(jī)種子,同時(shí)也把numpy的隨機(jī)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
如果只需要一張顯卡。
# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
如果需要指定多張顯卡,比如0,1號(hào)顯卡。
import osos.environ['CUDA_VISIBLE_DEVICES'] = '0,1'
也可以在命令行運(yùn)行代碼時(shí)設(shè)置顯卡:
CUDA_VISIBLE_DEVICES=0,1 python train.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
PyTorch有9種CPU張量類型和9種GPU張量類型。
tensor = torch.randn(3,4,5)print(tensor.type()) # 數(shù)據(jù)類型print(tensor.size()) # 張量的shape,是個(gè)元組print(tensor.dim()) # 維度的數(shù)量
張量命名是一個(gè)非常有用的方法,這樣可以方便地使用維度的名字來(lái)做索引或其他操作,大大提高了可讀性、易用性,防止出錯(cuò)。
# 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(duì)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()
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(lái)。
ndarray = tensor.cpu().numpy()
tensor = torch.from_numpy(ndarray).float()
tensor = torch.from_numpy(ndarray.copy()).float() # If ndarray has negative stride.
# 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
image = PIL.Image.fromarray(ndarray.astype(np.uint8))
ndarray = np.asarray(PIL.Image.open(path))
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(duì)張量做形變處理,
# 相比torch.view,torch.reshape可以自動(dòng)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)
tensor = tensor[torch.randperm(tensor.size(0))] # 打亂第一個(gè)維度
水平翻轉(zhuǎn)
# pytorch不支持tensor[::-1]這樣的負(fù)步長(zhǎng)操作,水平翻轉(zhuǎn)可以通過(guò)張量索引實(shí)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()]
# 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(huì)新增一維。例如當(dāng)參數(shù)是3個(gè)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)
# 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())
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
torch.allclose(tensor1, tensor2) # float tensor
torch.equal(tensor1, tensor2) # int tensor
# 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)
# 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
利用廣播機(jī)制
dist = torch.sqrt(torch.sum((X1[:,None,:] - X2) ** 2, dim=2))
# 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)
卷積層的計(jì)算和展示可以用這個(gè)網(wǎng)站輔助。
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
當(dāng)使用 torch.nn.DataParallel 將代碼運(yùn)行在多張 GPU 卡上時(shí),PyTorch 的 BN 層默認(rèn)操作是各卡上數(shù)據(jù)獨(dú)立地計(jì)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(jì)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(shí)對(duì)均值和標(biāo)準(zhǔn)差估計(jì)不準(zhǔn)的情況,是在目標(biāo)檢測(cè)等任務(wù)中一個(gè)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)
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
如果要實(shí)現(xiàn)類似 BN 滑動(dòng)平均的操作,在 forward 函數(shù)中要使用原地(inplace)操作給滑動(dòng)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)
num_parameters = sum(torch.numel(parameter) for parameter in model.parameters())
查看網(wǎng)絡(luò)中的參數(shù)
可以通過(guò)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(guò)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)
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(huì)迭代地遍歷模型的所有子層,而 model.children() 只會(huì)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)
modules()會(huì)返回模型中所有模塊的迭代器,它能夠訪問(wèn)到最內(nèi)層,比如self.layer1.conv1這個(gè)模塊,還有一個(gè)與它們相對(duì)應(yīng)的是name_children()屬性以及named_modules(),這兩個(gè)不僅會(huì)返回模塊的迭代器,還會(huì)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])
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)
model.load_state_dict(torch.load('model.pth', map_location='cpu'))
模型導(dǎo)入?yún)?shù)時(shí),如果兩個(gè)模型結(jié)構(gòu)不一致,則直接導(dǎo)入?yún)?shù)會(huì)報(bào)錯(cuò)。用下面方法可以把另一個(gè)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)
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
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()
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)]
其中 ToTensor 操作會(huì)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)),
])
# 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()))
# 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))
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
寫一個(gè)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')
或者直接在訓(xùn)練文件里做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()
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_regularization = torch.nn.L1Loss(reduction='sum')
loss = ... # Standard cross-entropy loss
for param in model.parameters():
loss += torch.sum(torch.abs(param))
loss.backward()
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)
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'])
另一種方法,在一個(gè)batch訓(xùn)練代碼里,當(dāng)前的lr是optimizer.param_groups[0]['lr']
# 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(...)
從1.4版本開始,torch.optim.lr_scheduler 支持鏈?zhǔn)礁拢╟haining),即用戶可以定義兩個(gè) schedulers,并交替在訓(xùn)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()
PyTorch可以使用tensorboard來(lái)可視化訓(xùn)練過(guò)程。
安裝和運(yùn)行TensorBoard。
pip install tensorboard
tensorboard --logdir=runs
使用SummaryWriter類來(lái)收集和可視化相應(yīng)的數(shù)據(jù),放了方便查看,可以使用不同的文件夾,比如'Loss/train'和'Loss/test'。
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)
注意為了能夠恢復(fù)訓(xùn)練,我們需要同時(shí)保存模型和優(yōu)化器的狀態(tài),以及當(dāng)前的訓(xùn)練輪數(shù)。
start_epoch = 0
# Load checkpoint.
if resume: # resume為參數(shù),第一次訓(xùn)練時(shí)設(shè)為0,中斷再訓(xùn)練時(shí)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<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
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(gè) epoch 中每個(gè) mini-batch 的 loss 和準(zhǔn)確率,先將它們累積在 GPU 中等一個(gè) epoch 結(jié)束之后一起傳輸回 CPU 會(huì)比每個(gè) mini-batch 都進(jìn)行一次 GPU 到 CPU 的傳輸更快。
使用半精度浮點(diǎn)數(shù) half() 會(huì)有一定的速度提升,具體效率依賴于 GPU 型號(hào)。需要小心數(shù)值精度過(guò)低帶來(lái)的穩(wěn)定性問(wèn)題。
時(shí)常使用 assert tensor.size() == (N, D, H, W) 作為調(diào)試手段,確保張量維度和你設(shè)想中一致。
除了標(biāo)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(jì)算結(jié)果。
統(tǒng)計(jì)代碼各部分耗時(shí):
with torch.autograd.profiler.profile(enabled=True, use_cuda=False) as profile:
...print(profile)# 或者在命令行運(yùn)行python -m torch.utils.bottleneck main.py
使用TorchSnooper來(lái)調(diào)試PyTorch代碼,程序在執(zhí)行的時(shí)候,就會(huì)自動(dòng) print 出來(lái)每一行的執(zhí)行結(jié)果的 tensor 的形狀、數(shù)據(jù)類型、設(shè)備、是否需要梯度的信息。
# pip install torchsnooper
import torchsnooper# 對(duì)于函數(shù),使用修飾器@torchsnooper.snoop()
# 如果不是函數(shù),使用 with 語(yǔ)句來(lái)激活 TorchSnooper,把訓(xùn)練的那個(gè)循環(huán)裝進(jìn) with 語(yǔ)句中去。
with torchsnooper.snoop():
原本的代碼
https://github.com/zasdfgbnm/TorchSnoopergithub.com
模型可解釋性,使用captum庫(kù):https://captum.ai/captum.ai
學(xué)術(shù)分享,來(lái)源丨h(huán)ttps://zhuanlan.zhihu.com/p/104019160
文件上傳如何做斷點(diǎn)續(xù)傳?全端+后端結(jié)合開發(fā),VUE實(shí)現(xiàn)文件上傳(單文件、多文件、分片上傳),JS中實(shí)現(xiàn)文件上傳下載的三種解決方案(推薦),JS實(shí)現(xiàn)大文件上傳——分片上傳方法,完美解決WEB無(wú)法上傳大文件方法,HTML大文件上傳源碼,WEBUPLOAD組件實(shí)現(xiàn)文件上傳功能和下載功能,js大文件上傳下載解決方案,vue大文件上傳下載解決方案,asp.net大文件上傳下載解決方案,.net大文件上傳下載解決方案,webform大文件上傳下載解決方案,jsp大文件上傳下載解決方案,java大文件上傳下載解決方案,JAVASCRIPT 大文件上傳下載切片解決方案,JAVASCRIPT 大文件上傳下載切割解決方案,JAVASCRIPT 大文件上傳下載分割解決方案,JAVASCRIPT 大文件上傳下載分塊解決方案,JAVASCRIPT 大文件上傳下載分片解決方案,web大文件上傳下載解決方案,網(wǎng)頁(yè)大文件上傳下載解決方案,前端大文件上傳下載解決方案,html5大文件上傳下載解決方案,JAVASCRIPT 大文件上傳下載解決方案,支持HTML5,VUE2,VUE3,React,javascript等常用前端UI框架,JS框架,網(wǎng)上找的方案大多數(shù)都只是一些代碼片段,沒(méi)有提供完整的前后端代碼。
跟項(xiàng)目經(jīng)理溝通過(guò),這塊網(wǎng)上搜到的文章能用的幾乎沒(méi)有。
之前項(xiàng)目上面用Flash比較多一點(diǎn),現(xiàn)在基本上都是HTML5,斷點(diǎn)續(xù)傳除了頁(yè)面級(jí)以外最好還能夠提供離線支持。
支持IE,Chrome和信創(chuàng)國(guó)產(chǎn)化環(huán)境,比如銀河麒麟,統(tǒng)信UOS,龍芯,
支持分片,分塊,分段,切片,分割上傳。能夠突破chrome每域名的5個(gè)TCP連接限制,能夠突破chrome重啟,關(guān)閉瀏覽器續(xù)傳的限制。
支持10G,20G,50G,100G文件上傳和續(xù)傳,支持秒傳,支持文件夾上傳,重復(fù)文件檢測(cè),重復(fù)文件校驗(yàn)
支持文件下載,批量下載,下載斷點(diǎn)續(xù)傳,加密下載,端到端加密,加密算法支持國(guó)密SM4,多線程下載
支持在服務(wù)端保存文件夾層級(jí)結(jié)構(gòu),支持將文件夾層級(jí)結(jié)構(gòu)信息保存到數(shù)據(jù)庫(kù)中,支持下載時(shí)能夠?qū)⑽募A層級(jí)結(jié)構(gòu)下載下來(lái),支持下載文件夾,下載文件夾支持?jǐn)帱c(diǎn)續(xù)傳,
支持加密傳輸,包括加密上傳,加密下載,加密算法支持國(guó)密SM4,
支持云對(duì)象存儲(chǔ),比如華為云,阿里云,騰訊云,七牛云,AWS,MinIO,FastDFS,
提供手機(jī),QQ,微信,郵箱等聯(lián)系方式,提供7*24小時(shí)技術(shù)支持,提供長(zhǎng)期技術(shù)支持和維護(hù)服務(wù),提供遠(yuǎn)程1對(duì)1技術(shù)指導(dǎo),提供二次開發(fā)指導(dǎo),提供文檔教程,提供視頻教程。
最新版本:6.5.40
在線代碼:https://gitee.com/xproer/up6-asp-net/tree/6.5.40/
NOSQL
NOSQL無(wú)需任何配置可直接訪問(wèn)頁(yè)面進(jìn)行測(cè)試
SQL
使用IIS
大文件上傳測(cè)試推薦使用IIS以獲取更高性能。
使用IIS Express
小文件上傳測(cè)試可以使用IIS Express
創(chuàng)建數(shù)據(jù)庫(kù)
配置數(shù)據(jù)庫(kù)連接信息
訪問(wèn)頁(yè)面進(jìn)行測(cè)試
相關(guān)參考:
文件保存位置,
源碼工程文檔:https://drive.weixin.qq.com/s?k=ACoAYgezAAw1dWofra
源碼報(bào)價(jià)單:https://drive.weixin.qq.com/s?k=ACoAYgezAAwoiul8gl
OEM版報(bào)價(jià)單:https://drive.weixin.qq.com/s?k=ACoAYgezAAwuzp4W0a
控件源碼下載:https://drive.weixin.qq.com/s?k=ACoAYgezAAwbdKCskc
*請(qǐng)認(rèn)真填寫需求信息,我們會(huì)在24小時(shí)內(nèi)與您取得聯(lián)系。