examples/image/test1.py

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 numpy as np


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, 10)

    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 % 10 == 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(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.argmax(dim=1, keepdim=True)  # 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)))




torch.manual_seed(100)
device = torch.device("cuda")


train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=True, download=True,
                 transform=transforms.Compose([transforms.ToTensor(),
                 transforms.Normalize((0.1307,), (0.3081,))])),
    batch_size=64,
    shuffle=True)

test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=False,
                transform=transforms.Compose([transforms.ToTensor(),
                transforms.Normalize((0.1307,), (0.3081,))])),
    batch_size=1000,
    shuffle=True)

model = Net().to(device)
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)


save_model = True
for epoch in range(1, 5 + 1):     ## 5 batches
    train( model, device, train_loader, optimizer, epoch)
    test( model, device, test_loader)

    if (save_model):
        torch.save(model.state_dict(), "mnist_cnn.pt")




############################################################## test

xx = datasets.MNIST('../data').data[0:10]
xx = xx.unsqueeze_(1).float()/255

yy = datasets.MNIST('../data', download=True).targets[0:10]


from fgsm import FGM


fgsm_params = {
    'epsilon': 0.1,
    'order': np.inf,
    'clip_max': None,
    'clip_min': None
}

F1 = FGM(model, device = "cpu")       ### or cuda
aa = F1.generate(x=xx, y=yy, **fgsm_params)

import matplotlib.pyplot as plt
plt.imsave('test.jpg', aa[0,0])