pytorch學習_官方turtorial理解(二)
阿新 • • 發佈:2018-12-19
一、處理各型別資料的一些python packages Generally, when you have to deal with image, text, audio or video data, you can use standard python packages that load data into a numpy array. Then you can convert this array into a torch.*Tensor.
- For images, packages such as Pillow, OpenCV are useful
- For audio, packages such as scipy and librosa
- For text, either raw Python or Cython based loading, or NLTK and SpaCy are useful 二、訓練一個分類器的步驟 We will do the following steps in order: 1、Load and normalizing the CIFAR10 training and test datasets using torchvision(資料預處理) 2、Define a Convolution Neural Network 3、Define a loss function 4、Train the network on the training data 5、Test the network on the test data
# -*- coding: utf-8 -*- import torch import torchvision import torchvision.transforms as transforms ######################################################################## # The output of torchvision datasets are PILImage images of range [0, 1]. # We transform them to Tensors of normalized range [-1, 1]. #transforms.Compose()將引數裡的操作進行組合,並對資料依次執行這些操作 transform = transforms.Compose( [transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform) trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2) testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform) testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2) classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck') ######################################################################## # Let us show some of the training images, for fun. import matplotlib.pyplot as plt import numpy as np # functions to show an image def imshow(img): img = img / 2 + 0.5 # unnormalize npimg = img.numpy() plt.imshow(np.transpose(npimg, (1, 2, 0))) # get some random training images dataiter = iter(trainloader) images, labels = dataiter.next() # show images imshow(torchvision.utils.make_grid(images)) # print labels print(' '.join('%5s' % classes[labels[j]] for j in range(4))) ######################################################################## # 2. Define a Convolution Neural Network # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # Copy the neural network from the Neural Networks section before and modify it to # take 3-channel images (instead of 1-channel images as it was defined). #定義網路結構:層數以及每一層的結構、activitation function import torch.nn as nn import torch.nn.functional as F class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(3, 6, 5) self.pool = nn.MaxPool2d(2, 2) self.conv2 = nn.Conv2d(6, 16, 5) self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = x.view(-1, 16 * 5 * 5) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x net = Net() ######################################################################## # 3. Define a Loss function and optimizer # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # Let's use a Classification Cross-Entropy loss and SGD with momentum. import torch.optim as optim #計算loss函式,採用隨機梯度下降法進行優化 criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) ######################################################################## # 4. Train the network # ^^^^^^^^^^^^^^^^^^^^ # # This is when things start to get interesting. # We simply have to loop over our data iterator, and feed the inputs to the # network and optimize. #enumerate() 函式用於將一個可遍歷的資料物件(如列表、元組或字串)組合為一個索引序列,同時列出資料和資料下標,第一個引數表示序列及其他支援迭代物件,第二個是下標起始位置 for epoch in range(2): # loop over the dataset multiple times running_loss = 0.0 for i, data in enumerate(trainloader, 0): # get the inputs inputs, labels = data # zero the parameter gradients optimizer.zero_grad() # forward + backward + optimize outputs = net(inputs) loss = criterion(outputs, labels) loss.backward() optimizer.step() # print statistics running_loss += loss.item() if i % 2000 == 1999: # print every 2000 mini-batches print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000)) running_loss = 0.0 print('Finished Training') ######################################################################## # 5. Test the network on the test data # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # # We have trained the network for 2 passes over the training dataset. # But we need to check if the network has learnt anything at all. # # We will check this by predicting the class label that the neural network # outputs, and checking it against the ground-truth. If the prediction is # correct, we add the sample to the list of correct predictions. # # Okay, first step. Let us display an image from the test set to get familiar. dataiter = iter(testloader) images, labels = dataiter.next() # print images imshow(torchvision.utils.make_grid(images)) print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4))) ######################################################################## # Okay, now let us see what the neural network thinks these examples above are: outputs = net(images) ######################################################################## # The outputs are energies for the 10 classes. # Higher the energy for a class, the more the network # thinks that the image is of the particular class. # So, let's get the index of the highest energy:(測試的輸出是概率,可能性最大的一個分類被輸出) _, predicted = torch.max(outputs, 1) print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4))) ######################################################################## # The results seem pretty good. # # Let us look at how the network performs on the whole dataset. correct = 0 total = 0 with torch.no_grad(): for data in testloader: images, labels = data outputs = net(images) _, predicted = torch.max(outputs.data, 1) total += labels.size(0) correct += (predicted == labels).sum().item() print('Accuracy of the network on the 10000 test images: %d %%' % ( 100 * correct / total)) ######################################################################## # That looks waaay better than chance, which is 10% accuracy (randomly picking # a class out of 10 classes). # Seems like the network learnt something. # # Hmmm, what are the classes that performed well, and the classes that did # not perform well: class_correct = list(0. for i in range(10)) class_total = list(0. for i in range(10)) with torch.no_grad(): for data in testloader: images, labels = data outputs = net(images) _, predicted = torch.max(outputs, 1) c = (predicted == labels).squeeze() for i in range(4): label = labels[i] class_correct[label] += c[i].item() class_total[label] += 1 #squeeze 函式:從陣列的形狀中刪除單維度條目,即把shape中為1的維度去掉 for i in range(10): print('Accuracy of %5s : %2d %%' % ( classes[i], 100 * class_correct[i] / class_total[i])) ######################################################################## # Okay, so what next? # # How do we run these neural networks on the GPU? # # Training on GPU # ---------------- # Just like how you transfer a Tensor on to the GPU, you transfer the neural # net onto the GPU. # # Let's first define our device as the first visible cuda device if we have # CUDA available: device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") # Assume that we are on a CUDA machine, then this should print a CUDA device: print(device)