即仿射变换的6个参数用网络来学
import torch import torch.nn as nn import torch.nn.functional as F import torch.optim as optim import torchvision from torchvision import datasets, transforms import matplotlib.pyplot as plt import numpy as np class TPSNet(nn.Module): def __init__(self): super(TPSNet, self).__init__() self.conv1 = nn.Conv2d(1, 10, kernel_size=5) self.conv2 = nn.Conv2d(10, 20, kernel_size=5) self.conv2_drop = nn.Dropout2d() self.fc1 = nn.Linear(320, 50) self.fc2 = nn.Linear(50, 10) # Spatial transformer localization-network self.localization = nn.Sequential( nn.Conv2d(in_channels=1, out_channels=8, kernel_size=7), nn.MaxPool2d(kernel_size=2, stride=2), nn.ReLU(True), nn.Conv2d(in_channels=8, out_channels=10, kernel_size=5), nn.MaxPool2d(kernel_size=2, stride=2), nn.ReLU(True) ) # Regressor for the 3 * 2 affine matrix self.fc_loc = nn.Sequential( nn.Linear(10 * 3 * 3, 32), nn.ReLU(True), nn.Linear(32, 3 * 2) ) # Initialize the weights/bias with identity transformation self.fc_loc[2].weight.data.fill_(0) self.fc_loc[2].bias.data = torch.FloatTensor([1, 0, 0, 0, 1, 0]) # Spatial transformer network forward function def stn(self, x): #x是[b,1,28,28] xs = self.localization(x) #xs是[b,10,3,3] xs = xs.view(-1, 10 * 3 * 3) #xs是[b,90] theta = self.fc_loc(xs) #theta是[b,6] theta = theta.view(-1, 2, 3) grid = F.affine_grid(theta, x.size()) x = F.grid_sample(x, grid) #x是[b,1,28,28] return x def forward(self, x): # transform the input #x是[b,1,28,28] x = self.stn(x) #x是[b,1,28,28] # Perform the usual forward pass x = F.relu(F.max_pool2d(self.conv1(x), 2)) x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2)) x = x.view(-1, 320) x = F.relu(self.fc1(x)) x = F.dropout(x, training=self.training) x = self.fc2(x) return F.log_softmax(x, dim=1) def train(epoch): model.train() for batch_idx, (data, target) in enumerate(train_loader): if use_cuda: data, target = data.cuda(), target.cuda() optimizer.zero_grad() output = model(data) loss = F.nll_loss(output, target) #和TPSNet中的log_softmax搭配，就是CE loss loss.backward() optimizer.step() if batch_idx % 500 == 0: print('Train Epoch: {} [{}/{} ({:.0f}%)]tLoss: {:.6f}'.format( epoch, batch_idx * len(data), len(train_loader.dataset), 100. * batch_idx / len(train_loader), loss.item())) # A simple test procedure to measure STN the performances on MNIST. def test(): with torch.no_grad(): model.eval() test_loss = 0 correct = 0 for data, target in test_loader: if use_cuda: data, target = data.cuda(), target.cuda() # data, target = Variable(data, volatile=True), Variable(target) output = model(data) # sum up batch loss test_loss = F.nll_loss(output, target, size_average=False).item() # get the index of the max log-probability pred = output.data.max(1, keepdim=True)[1] correct = pred.eq(target.data.view_as(pred)).cpu().sum() test_loss /= len(test_loader.dataset) print('nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)n' .format(test_loss, correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset))) #可视化STN效果 def convert_image_np(inp): """Convert a Tensor to numpy image.""" inp = inp.numpy().transpose((1, 2, 0)) mean = np.array([0.485, 0.456, 0.406]) std = np.array([0.229, 0.224, 0.225]) inp = std * inp mean inp = np.clip(inp, 0, 1) return inp # We want to visualize the output of the spatial transformers layer # after the training, we visualize a batch of input images and # the corresponding transformed batch using STN. def visualize_stn(): with torch.no_grad(): # Get a batch of training data data, _ = next(iter(test_loader)) # data = Variable(data, volatile=True) if use_cuda: data = data.cuda() input_tensor = data.cpu().data transformed_input_tensor = model.stn(data).cpu().data in_grid = convert_image_np( torchvision.utils.make_grid(input_tensor)) out_grid = convert_image_np( torchvision.utils.make_grid(transformed_input_tensor)) # Plot the results side-by-side f, axarr = plt.subplots(1, 2) axarr[0].imshow(in_grid) axarr[0].set_title('Dataset Images') axarr[1].imshow(out_grid) axarr[1].set_title('Transformed Images') plt.ion() # interactive mode #加载数据 use_cuda = torch.cuda.is_available() # Training dataset train_loader = torch.utils.data.DataLoader( datasets.MNIST(root='data/', train=True, download=True, transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,)) ])), batch_size=64, shuffle=True, num_workers=4) # Test dataset test_loader = torch.utils.data.DataLoader( datasets.MNIST(root='data/', train=False, transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,)) ])), batch_size=64, shuffle=True, num_workers=4) model = TPSNet() if use_cuda: model.cuda() #训练模型 optimizer = optim.SGD(model.parameters(), lr=0.01) for epoch in range(1, 20 1): train(epoch) test() # Visualize the STN transformation on some input batch visualize_stn() plt.ioff() plt.show() 参考 Spatial Transformer Networks Tutorial — PyTorch Tutorials 1.10.1 cu102 documentation
版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 举报，一经查实，本站将立刻删除。
发布者：全栈程序员栈长，转载请注明出处：https://javaforall.cn/180457.html原文链接：https://javaforall.cn
