Update 1010

CIFAR/main.py

@@ -0,0 +1,139 @@
+'''Train CIFAR10 with PyTorch.'''
+from __future__ import print_function
+
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torch.nn.functional as F
+#import torch.backends.cudnn as cudnn
+
+import torchvision
+import torchvision.transforms as transforms
+
+import os
+import argparse
+
+from models import *
+from utils import progress_bar
+from torch.autograd import Variable
+
+
+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()
+
+use_cuda = torch.cuda.is_available()
+best_acc = 0  # best test accuracy
+start_epoch = 0  # start from epoch 0 or last checkpoint epoch
+
+# Data
+print('==> Preparing data..')
+transform = 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)),
+])
+
+trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform=transform)
+trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=2)
+
+testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=False, transform=transform)
+testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=2)
+
+classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
+
+# Model
+if args.resume:
+    # Load checkpoint.
+    print('==> Resuming from checkpoint..')
+    assert os.path.isdir('checkpoint'), 'Error: no checkpoint directory found!'
+    checkpoint = torch.load('./checkpoint/ckpt.t7')
+    net = checkpoint['net']
+    best_acc = checkpoint['acc']
+    start_epoch = checkpoint['epoch']
+else:
+    print('==> Building model..')
+    net = VGG('VGG19')
+    # net = ResNet18()
+    # net = GoogLeNet()
+    # net = DenseNet121()
+    # net = ResNeXt29_2x64d()
+    # net = LeNet()
+
+if use_cuda:
+    net.cuda()
+    #net = torch.nn.DataParallel(net, device_ids=[0,1,2,3])
+    #cudnn.benchmark = True
+
+criterion = nn.CrossEntropyLoss()
+optimizer = optim.SGD(net.parameters(), lr=args.lr, momentum=0.9, weight_decay=5e-4)
+
+# Training
+def train(epoch):
+
+    print('\nEpoch: %d' % epoch)
+    net.train()
+    train_loss = 0
+    correct = 0
+    total = 0
+    for batch_idx, (inputs, targets) in enumerate(trainloader):
+        if use_cuda:
+            inputs, targets = inputs.cuda(), targets.cuda()
+        optimizer.zero_grad()
+        inputs, targets = Variable(inputs), Variable(targets)
+        outputs = net(inputs)
+        loss = criterion(outputs, targets)
+        loss.backward()
+        optimizer.step()
+
+        train_loss += loss.data[0]
+        _, predicted = torch.max(outputs.data, 1)
+        total += targets.size(0)
+        correct += predicted.eq(targets.data).cpu().sum()
+
+        progress_bar(batch_idx, len(trainloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
+            % (train_loss/(batch_idx+1), 100.*correct/total, correct, total))
+
+def test(epoch):
+
+    global best_acc
+    net.eval()
+    test_loss = 0
+    correct = 0
+    total = 0
+    for batch_idx, (inputs, targets) in enumerate(testloader):
+        if use_cuda:
+            inputs, targets = inputs.cuda(), targets.cuda()
+        inputs, targets = Variable(inputs, volatile=True), Variable(targets)
+        outputs = net(inputs)
+        loss = criterion(outputs, targets)
+
+        test_loss += loss.data[0]
+        _, predicted = torch.max(outputs.data, 1)
+        total += targets.size(0)
+        correct += predicted.eq(targets.data).cpu().sum()
+
+        progress_bar(batch_idx, len(testloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
+            % (test_loss/(batch_idx+1), 100.*correct/total, correct, total))
+
+    # Save checkpoint.
+    acc = 100.*correct/total
+    if acc > best_acc:
+        print('Saving..')
+        state = {
+            #'net': net.module if use_cuda else net,
+            'net': net,
+            'acc': acc,
+            'epoch': epoch,
+        }
+        if not os.path.isdir('checkpoint'):
+            os.mkdir('checkpoint')
+        torch.save(state, './checkpoint/ckpt.t7')
+        best_acc = acc
+
+
+for epoch in range(start_epoch, start_epoch+200):
+    train(epoch)
+    test(epoch)

CIFAR/models/__init__.py

@@ -0,0 +1,6 @@
+from .vgg import *
+from .lenet import *
+from .resnet import *
+from .resnext import *
+from .densenet import *
+from .googlenet import *

CIFAR/models/densenet.py

@@ -0,0 +1,109 @@
+'''DenseNet in PyTorch.'''
+import math
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from torch.autograd import Variable
+
+
+class Bottleneck(nn.Module):
+    def __init__(self, in_planes, growth_rate):
+        super(Bottleneck, self).__init__()
+        self.bn1 = nn.BatchNorm2d(in_planes)
+        self.conv1 = nn.Conv2d(in_planes, 4*growth_rate, kernel_size=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(4*growth_rate)
+        self.conv2 = nn.Conv2d(4*growth_rate, growth_rate, kernel_size=3, padding=1, bias=False)
+
+    def forward(self, x):
+        out = self.conv1(F.relu(self.bn1(x)))
+        out = self.conv2(F.relu(self.bn2(out)))
+        out = torch.cat([out,x], 1)
+        return out
+
+
+class Transition(nn.Module):
+    def __init__(self, in_planes, out_planes):
+        super(Transition, self).__init__()
+        self.bn = nn.BatchNorm2d(in_planes)
+        self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=1, bias=False)
+
+    def forward(self, x):
+        out = self.conv(F.relu(self.bn(x)))
+        out = F.avg_pool2d(out, 2)
+        return out
+
+
+class DenseNet(nn.Module):
+    def __init__(self, block, nblocks, growth_rate=12, reduction=0.5, num_classes=10):
+        super(DenseNet, self).__init__()
+        self.growth_rate = growth_rate
+
+        num_planes = 2*growth_rate
+        self.conv1 = nn.Conv2d(3, num_planes, kernel_size=3, padding=1, bias=False)
+
+        self.dense1 = self._make_dense_layers(block, num_planes, nblocks[0])
+        num_planes += nblocks[0]*growth_rate
+        out_planes = int(math.floor(num_planes*reduction))
+        self.trans1 = Transition(num_planes, out_planes)
+        num_planes = out_planes
+
+        self.dense2 = self._make_dense_layers(block, num_planes, nblocks[1])
+        num_planes += nblocks[1]*growth_rate
+        out_planes = int(math.floor(num_planes*reduction))
+        self.trans2 = Transition(num_planes, out_planes)
+        num_planes = out_planes
+
+        self.dense3 = self._make_dense_layers(block, num_planes, nblocks[2])
+        num_planes += nblocks[2]*growth_rate
+        out_planes = int(math.floor(num_planes*reduction))
+        self.trans3 = Transition(num_planes, out_planes)
+        num_planes = out_planes
+
+        self.dense4 = self._make_dense_layers(block, num_planes, nblocks[3])
+        num_planes += nblocks[3]*growth_rate
+
+        self.bn = nn.BatchNorm2d(num_planes)
+        self.linear = nn.Linear(num_planes, num_classes)
+
+    def _make_dense_layers(self, block, in_planes, nblock):
+        layers = []
+        for i in range(nblock):
+            layers.append(block(in_planes, self.growth_rate))
+            in_planes += self.growth_rate
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        out = self.conv1(x)
+        out = self.trans1(self.dense1(out))
+        out = self.trans2(self.dense2(out))
+        out = self.trans3(self.dense3(out))
+        out = self.dense4(out)
+        out = F.avg_pool2d(F.relu(self.bn(out)), 4)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+def DenseNet121():
+    return DenseNet(Bottleneck, [6,12,24,16], growth_rate=32)
+
+def DenseNet169():
+    return DenseNet(Bottleneck, [6,12,32,32], growth_rate=32)
+
+def DenseNet201():
+    return DenseNet(Bottleneck, [6,12,48,32], growth_rate=32)
+
+def DenseNet161():
+    return DenseNet(Bottleneck, [6,12,36,24], growth_rate=48)
+
+def densenet_cifar():
+    return DenseNet(Bottleneck, [6,12,24,16], growth_rate=12)
+
+def test_densenet():
+    net = densenet_cifar()
+    x = torch.randn(1,3,32,32)
+    y = net(Variable(x))
+    print(y)
+
+# test_densenet()

CIFAR/models/googlenet.py

@@ -0,0 +1,105 @@
+'''GoogLeNet with PyTorch.'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from torch.autograd import Variable
+
+
+class Inception(nn.Module):
+    def __init__(self, in_planes, n1x1, n3x3red, n3x3, n5x5red, n5x5, pool_planes):
+        super(Inception, self).__init__()
+        # 1x1 conv branch
+        self.b1 = nn.Sequential(
+            nn.Conv2d(in_planes, n1x1, kernel_size=1),
+            nn.BatchNorm2d(n1x1),
+            nn.ReLU(True),
+        )
+
+        # 1x1 conv -> 3x3 conv branch
+        self.b2 = nn.Sequential(
+            nn.Conv2d(in_planes, n3x3red, kernel_size=1),
+            nn.BatchNorm2d(n3x3red),
+            nn.ReLU(True),
+            nn.Conv2d(n3x3red, n3x3, kernel_size=3, padding=1),
+            nn.BatchNorm2d(n3x3),
+            nn.ReLU(True),
+        )
+
+        # 1x1 conv -> 5x5 conv branch
+        self.b3 = nn.Sequential(
+            nn.Conv2d(in_planes, n5x5red, kernel_size=1),
+            nn.BatchNorm2d(n5x5red),
+            nn.ReLU(True),
+            nn.Conv2d(n5x5red, n5x5, kernel_size=3, padding=1),
+            nn.BatchNorm2d(n5x5),
+            nn.ReLU(True),
+            nn.Conv2d(n5x5, n5x5, kernel_size=3, padding=1),
+            nn.BatchNorm2d(n5x5),
+            nn.ReLU(True),
+        )
+
+        # 3x3 pool -> 1x1 conv branch
+        self.b4 = nn.Sequential(
+            nn.MaxPool2d(3, stride=1, padding=1),
+            nn.Conv2d(in_planes, pool_planes, kernel_size=1),
+            nn.BatchNorm2d(pool_planes),
+            nn.ReLU(True),
+        )
+
+    def forward(self, x):
+        y1 = self.b1(x)
+        y2 = self.b2(x)
+        y3 = self.b3(x)
+        y4 = self.b4(x)
+        return torch.cat([y1,y2,y3,y4], 1)
+
+
+class GoogLeNet(nn.Module):
+    def __init__(self):
+        super(GoogLeNet, self).__init__()
+        self.pre_layers = nn.Sequential(
+            nn.Conv2d(3, 192, kernel_size=3, padding=1),
+            nn.BatchNorm2d(192),
+            nn.ReLU(True),
+        )
+
+        self.a3 = Inception(192,  64,  96, 128, 16, 32, 32)
+        self.b3 = Inception(256, 128, 128, 192, 32, 96, 64)
+
+        self.maxpool = nn.MaxPool2d(3, stride=2, padding=1)
+
+        self.a4 = Inception(480, 192,  96, 208, 16,  48,  64)
+        self.b4 = Inception(512, 160, 112, 224, 24,  64,  64)
+        self.c4 = Inception(512, 128, 128, 256, 24,  64,  64)
+        self.d4 = Inception(512, 112, 144, 288, 32,  64,  64)
+        self.e4 = Inception(528, 256, 160, 320, 32, 128, 128)
+
+        self.a5 = Inception(832, 256, 160, 320, 32, 128, 128)
+        self.b5 = Inception(832, 384, 192, 384, 48, 128, 128)
+
+        self.avgpool = nn.AvgPool2d(8, stride=1)
+        self.linear = nn.Linear(1024, 10)
+
+    def forward(self, x):
+        out = self.pre_layers(x)
+        out = self.a3(out)
+        out = self.b3(out)
+        out = self.maxpool(out)
+        out = self.a4(out)
+        out = self.b4(out)
+        out = self.c4(out)
+        out = self.d4(out)
+        out = self.e4(out)
+        out = self.maxpool(out)
+        out = self.a5(out)
+        out = self.b5(out)
+        out = self.avgpool(out)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+# net = GoogLeNet()
+# x = torch.randn(1,3,32,32)
+# y = net(Variable(x))
+# print(y.size())

CIFAR/models/lenet.py

@@ -0,0 +1,23 @@
+'''LeNet in PyTorch.'''
+import torch.nn as nn
+import torch.nn.functional as F
+
+class LeNet(nn.Module):
+    def __init__(self):
+        super(LeNet, self).__init__()
+        self.conv1 = nn.Conv2d(3, 6, 5)
+        self.conv2 = nn.Conv2d(6, 16, 5)
+        self.fc1   = nn.Linear(16*5*5, 120)
+        self.fc2   = nn.Linear(120, 84)
+        self.fc3   = nn.Linear(84, 10)
+
+    def forward(self, x):
+        out = F.relu(self.conv1(x))
+        out = F.max_pool2d(out, 2)
+        out = F.relu(self.conv2(out))
+        out = F.max_pool2d(out, 2)
+        out = out.view(out.size(0), -1)
+        out = F.relu(self.fc1(out))
+        out = F.relu(self.fc2(out))
+        out = self.fc3(out)
+        return out