import torch import torchvision import torchvision.transforms as transforms 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') 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))) plt.show() # 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 Convolutional Neural Network 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 # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ import torch.optim as optim criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) ######################################################################## # 4. Train the network # ^^^^^^^^^^^^^^^^^^^^ 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; data is a list of [inputs, labels] 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') ######################################################################## # Let's quickly save our trained model: PATH = './cifar_net.pth' torch.save(net.state_dict(), PATH) 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))) ######################################################################## # Next, let's load back in our saved model (note: saving and re-loading the model # wasn't necessary here, we only did it to illustrate how to do so): net = Net() net.load_state_dict(torch.load(PATH)) ######################################################################## # 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. # The 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, 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 way 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 for i in range(10): print('Accuracy of %5s : %2d %%' % ( classes[i], 100 * class_correct[i] / class_total[i])) device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") # torch_model.eval() # # Input to the model # x = torch.randn(batch_size, 1, 224, 224, requires_grad=True) # torch_out = torch_model(x) # # Export the model # torch.onnx.export(torch_model, # model being run # x, # model input (or a tuple for multiple inputs) # "super_resolution.onnx", # where to save the model (can be a file or file-like object) # export_params=True, # store the trained parameter weights inside the model file # opset_version=10, # the ONNX version to export the model to # do_constant_folding=True, # whether to execute constant folding for optimization # input_names = ['input'], # the model's input names # output_names = ['output'], # the model's output names # dynamic_axes={'input' : {0 : 'batch_size'}, # variable lenght axes # 'output' : {0 : 'batch_size'}})