BP算法实现26个字母识别

from __future__ import print_function import argparse import torch import torch.nn as nn import torch.nn.functional as F import torch.optim as optim from torchvision import datasets, transforms import matplotlib.pyplot as plt import numpy as np import torchvision.utils as vutils from visdom_utils import Visualizer batch_size = 64 test_batch_size = 1000 epochs = 1 lr = 0.01 momentum = 0.5 no_cuda = False seed = 1 log_interval = 400 save_model = False use_cuda = not no_cuda and torch.cuda.is_available() vis = Visualizer() class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 20, 5, 1) self.conv2 = nn.Conv2d(20, 50, 5, 1) self.fc1 = nn.Linear(4 * 4 * 50, 500) self.fc2 = nn.Linear(500, 27) def forward(self, x): x = F.relu(self.conv1(x)) x = F.max_pool2d(x, 2, 2) x = F.relu(self.conv2(x)) x = F.max_pool2d(x, 2, 2) x = x.view(-1, 4 * 4 * 50) x = F.relu(self.fc1(x)) x = self.fc2(x) return F.log_softmax(x, dim=1) def train(model, device, train_loader, optimizer, epoch): model.train() for batch_idx, (data, target) in enumerate(train_loader): data, target = data.to(device), target.to(device) optimizer.zero_grad() output = model(data) loss = F.nll_loss(output, target) loss.backward() optimizer.step() if batch_idx % log_interval == 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())) vis.plot_train_val(loss_train=loss.item()) def test(model, device, test_loader): model.eval() test_loss = 0 correct = 0 with torch.no_grad(): for data, target in test_loader: data, target = data.to(device), target.to(device) output = model(data) test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability correct += pred.eq(target.view_as(pred)).sum().item() 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))) # Training settings torch.manual_seed(seed) device = torch.device("cuda" if use_cuda else "cpu") kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {} train_loader = torch.utils.data.DataLoader( datasets.EMNIST('./emnist_data',split='letters', train=True, download=True,transform=transforms.ToTensor()), batch_size=batch_size, shuffle=True, **kwargs) test_loader = torch.utils.data.DataLoader( datasets.EMNIST('./emnist_data',split='letters', train=False, transform=transforms.ToTensor()), batch_size=test_batch_size, shuffle=True, **kwargs) model = Net().to(device) optimizer = optim.SGD(model.parameters(), lr=lr, momentum=momentum) for epoch in range(1, epochs + 1): train(model, device, train_loader, optimizer, epoch) test(model, device, test_loader) if (save_model): torch.save(model.state_dict(), "emnist_cnn.pt")