PyTorch_Template

pytorch_template.py

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision.datasets.mnist import MNIST
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
import visdom
from collections import OrderedDict

class LeNet5(nn.Module):
    def __init__(self):
        super(LeNet5, self).__init__()

        self.convnet = nn.Sequential(OrderedDict([
            ('c1', nn.Conv2d(1, 6, kernel_size=(5, 5))),
            ('relu1', nn.ReLU()),
            ('s2', nn.MaxPool2d(kernel_size=(2, 2), stride=2)),
            ('c3', nn.Conv2d(6, 16, kernel_size=(5, 5))),
            ('relu3', nn.ReLU()),
            ('s4', nn.MaxPool2d(kernel_size=(2, 2), stride=2)),
            ('c5', nn.Conv2d(16, 120, kernel_size=(5, 5))),
            ('relu5', nn.ReLU())
        ]))

        self.fc = nn.Sequential(OrderedDict([
            ('f6', nn.Linear(120, 84)),
            ('relu6', nn.ReLU()),
            ('f7', nn.Linear(84, 10)),
            ('sig7', nn.LogSoftmax(dim=-1))
        ]))

    def forward(self, img):
        output = self.convnet(img)
        output = output.view(img.size(0), -1)
        output = self.fc(output)
        return F.log_softmax(output, dim=1)
	
#================================== TRAIN TEST FUNCS ==================================
device = 'cpu' #/gpu

def train(epoch, vis_interval=500):
    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 % vis_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()))
			
def test():
    with torch.no_grad():
        model.eval()
        test_loss = 0
        correct = 0
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            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.max(1, keepdim=True)[1]
            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)))

# ================================== DATA LOADING ==================================

data_train = MNIST('./data/mnist',
                   download=True,
                   transform=transforms.Compose([
                       transforms.Resize((32, 32)),
                       transforms.ToTensor()]))
data_test = MNIST('./data/mnist',
                  train=False,
                  download=True,
                  transform=transforms.Compose([
                      transforms.Resize((32, 32)),
                      transforms.ToTensor()]))

data_train_loader = DataLoader(data_train, batch_size=256, shuffle=True, num_workers=8)
data_test_loader = DataLoader(data_test, batch_size=1024, num_workers=8)

net = LeNet5()

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=2e-3)


for e in range(1, 16):
	train(e)
	test()