test.py

# From: https://github.com/kuangliu/pytorch-cifar/blob/master/main.py
'''Train CIFAR10 with PyTorch.'''
import os

os.environ['CUDA_VISIBLE_DEVICES'] = "0"

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F

import torchvision
import torchvision.transforms as transforms

import argparse

from ssl_eval import Evaluator, StoreEvaluator


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_planes, planes, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_planes,
                               planes,
                               kernel_size=3,
                               stride=stride,
                               padding=1,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)

        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes != self.expansion * planes:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_planes,
                          self.expansion * planes,
                          kernel_size=1,
                          stride=stride,
                          bias=False),
                nn.BatchNorm2d(self.expansion * planes))

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        out += self.shortcut(x)
        out = F.relu(out)
        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, in_planes, planes, stride=1):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, self.expansion * planes, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(self.expansion * planes)

        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes != self.expansion * planes:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_planes,
                          self.expansion * planes,
                          kernel_size=1,
                          stride=stride,
                          bias=False),
                nn.BatchNorm2d(self.expansion * planes))

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = F.relu(self.bn2(self.conv2(out)))
        out = self.bn3(self.conv3(out))
        out += self.shortcut(x)
        out = F.relu(out)
        return out


class ResNet(nn.Module):

    def __init__(self, block, num_blocks, num_classes=10):
        super(ResNet, self).__init__()
        self.in_planes = 64

        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

    def _make_layer(self, block, planes, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_planes, planes, stride))
            self.in_planes = planes * block.expansion
        return nn.Sequential(*layers)

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = F.avg_pool2d(out, 4)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out


class ResNet18(nn.Module):

    def __init__(self, num_classes=10):
        super(ResNet18, self).__init__()
        self.encoder = ResNet(BasicBlock, [2, 2, 2, 2])  # resnet18
        self.prev_dim = self.encoder.fc.weight.shape[1]
        self.encoder.fc = nn.Identity()
        self.classifier = nn.Linear(self.prev_dim, num_classes)

    def forward(self, x):
        z = self.encoder(x)
        return z, self.classifier(z)


parser = argparse.ArgumentParser(description='PyTorch CIFAR10 Training')
parser.add_argument('--lr', default=0.1, type=float, help='learning rate')
parser.add_argument('--resume', '-r', action='store_true', help='resume from checkpoint')
args = parser.parse_args()

device = 'cuda' if torch.cuda.is_available() else 'cpu'
best_acc = 0  # best test accuracy
start_epoch = 0  # start from epoch 0 or last checkpoint epoch

# Data
print('==> Preparing data..')
transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])

transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])

trainset = torchvision.datasets.CIFAR10(root='/data/shared/data/cifar10',
                                        train=True,
                                        download=True,
                                        transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=8)

testset = torchvision.datasets.CIFAR10(root='/data/shared/data/cifar10',
                                       train=False,
                                       download=True,
                                       transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=8)

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

# Model
print('==> Building model..')
net = ResNet18()
net = net.to(device)

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=args.lr, momentum=0.9, weight_decay=5e-4)

store_evaluator = StoreEvaluator(net.encoder,
                                 "cifar10",
                                 "/data/shared/data/cifar10",
                                 storage_size=3)
evaluator = Evaluator(net.encoder, "cifar10", "/data/shared/data/cifar10", n_views=3)


# Training
def train(epoch):
    print('\nEpoch: %d' % epoch)
    net.train()
    train_loss = 0
    correct = 0
    total = 0
    for inputs, targets in trainloader:
        inputs, targets = inputs.to(device), targets.to(device)
        optimizer.zero_grad()
        z, outputs = net(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()
        store_evaluator.update(z, targets)

        train_loss += loss.item()
        _, predicted = outputs.max(1)
        total += targets.size(0)
        correct += predicted.eq(targets).sum().item()
    print("acc", correct / total * 100)


def test():

    # print("Online")
    # store_evaluator.generate_embeddings()
    # store_evaluator.snn()
    # store_evaluator.snn(balance_labels=True)
    # store_evaluator.linear_eval(epochs=100, batch_size=512, lr=0.2, warm_start=False)

    print("Offline")
    evaluator.generate_embeddings()
    evaluator.knn(k=[1, 5, 20])
    # evaluator.snn()
    # evaluator.snn(balance_labels=True)
    evaluator.linear_eval(epochs=100, batch_size=512, lr=0.2, warm_start=False)


for epoch in range(2):
    train(epoch)

test()

# for epoch in range(2):
#     train(epoch)

# test()