%matplotlib inline This is it. You have seen how to define neural networks, compute loss and make updates to the weights of the network.
Now you might be thinking,
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.
Specifically for vision, we have created a package called torchvision, that has data loaders for common datasets such as Imagenet, CIFAR10, MNIST, etc. and data transformers for images, viz., torchvision.datasets and torch.utils.data.DataLoader.
This provides a huge convenience and avoids writing boilerplate code.
For this tutorial, we will use the CIFAR10 dataset. It has the classes: ‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’. The images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels in size.
.. figure:: /_static/img/cifar10.png :alt: cifar10
cifar10
We will do the following steps in order:
Load and normalizing the CIFAR10 training and test datasets using torchvision
Define a Convolution Neural Network
Define a loss function
Train the network on the training data
Test the network on the test data
Loading and normalizing CIFAR10
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Using torchvision, it’s extremely easy to load CIFAR10.
importtorchimporttorchvisionimporttorchvision.transformsastransformsThe output of torchvision datasets are PILImage images of range [0, 1]. We transform them to Tensors of normalized range [-1, 1]
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.
importmatplotlib.pyplotaspltimportnumpyasnp# functions to show an imagedefimshow(img):img=img/2+0.5# unnormalizenpimg=img.numpy()plt.imshow(np.transpose(npimg,(1,2,0)))# get some random training imagesdataiter=iter(trainloader)images,labels=dataiter.next()# show imagesimshow(torchvision.utils.make_grid(images))# print labelsprint(' '.join('%5s'%classes[labels[j]]forjinrange(4)))^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 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).
fromtorch.autogradimportVariableimporttorch.nnasnnimporttorch.nn.functionalasFclassNet(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)defforward(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)returnxnet=Net()^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Let's use a Classification Cross-Entropy loss and SGD with momentum
importtorch.optimasoptimcriterion=nn.CrossEntropyLoss()optimizer=optim.SGD(net.parameters(),lr=0.001,momentum=0.9)^^^^^^^^^^^^^^^^^^^^
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
forepochinrange(2):# loop over the dataset multiple timesrunning_loss=0.0fori,datainenumerate(trainloader,0):# get the inputsinputs,labels=data# wrap them in Variableinputs,labels=Variable(inputs),Variable(labels)# zero the parameter gradientsoptimizer.zero_grad()# forward + backward + optimizeoutputs=net(inputs)loss=criterion(outputs,labels)loss.backward()optimizer.step()# print statisticsrunning_loss+=loss.data[0]ifi%2000==1999:# print every 2000 mini-batchesprint('[%d, %5d] loss: %.3f'%(epoch+1,i+1,running_loss/2000))running_loss=0.0print('Finished Training')^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
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 imagesimshow(torchvision.utils.make_grid(images))print('GroundTruth: ',' '.join('%5s'%classes[labels[j]]forjinrange(4)))Okay, now let us see what the neural network thinks these examples above are:
outputs=net(Variable(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:
_,predicted=torch.max(outputs.data,1)print('Predicted: ',' '.join('%5s'%classes[predicted[j]]forjinrange(4)))The results seem pretty good.
Let us look at how the network performs on the whole dataset.
correct=0total=0fordataintestloader:images,labels=dataoutputs=net(Variable(images))_,predicted=torch.max(outputs.data,1)total+=labels.size(0)correct+=(predicted==labels).sum()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.foriinrange(10))class_total=list(0.foriinrange(10))fordataintestloader:images,labels=dataoutputs=net(Variable(images))_,predicted=torch.max(outputs.data,1)c=(predicted==labels).squeeze()foriinrange(4):label=labels[i]class_correct[label]+=c[i]class_total[label]+=1foriinrange(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?
Just like how you transfer a Tensor on to the GPU, you transfer the neural net onto the GPU. This will recursively go over all modules and convert their parameters and buffers to CUDA tensors:
.. code:: python
net.cuda() Remember that you will have to send the inputs and targets at every step to the GPU too:
::
inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda()) Why dont I notice MASSIVE speedup compared to CPU? Because your network is realllly small.
Exercise: Try increasing the width of your network (argument 2 of the first nn.Conv2d, and argument 1 of the second nn.Conv2d – they need to be the same number), see what kind of speedup you get.
Goals achieved:
Train neural nets to play video games </intermediate/reinforcement_q_learning>Train a state-of-the-art ResNet network on imagenet_Train an face generator using Generative Adversarial Networks_Train a word-level language model using Recurrent LSTM networks_More examples_More tutorials_Discuss PyTorch on the Forums_Chat with other users on Slack_