def sepconv2d(cin, cout=None, ksize=3, stride=1, padding=None, affine=True):
if cout is None: cout = cin
if padding is None: padding = ksize // 2
layer = nn.Sequential(
nn.ReLU(inplace=False),
init_default(
nn.Conv2d(cin,
cin,
ksize,
stride=stride,
padding=padding,
groups=cin,
bias=False), nn.init.kaiming_normal_),
init_default(nn.Conv2d(cin, cin, 1, padding=0, bias=False),
nn.init.kaiming_normal_),
nn.BatchNorm2d(cin, affine=affine), nn.ReLU(inplace=False),
init_default(
nn.Conv2d(cin,
cin,
ksize,
stride=1,
padding=padding,
groups=cin,
bias=False), nn.init.kaiming_normal_),
init_default(nn.Conv2d(cin, cout, 1, padding=0, bias=False),
nn.init.kaiming_normal_),
nn.BatchNorm2d(cout, affine=affine))
return layer
def __init__(self):
super().__init__()
self.learn = None
# train_button = gui.button(self.controlArea, self, "开始训练", callback=self.train)
self.label = gui.label(self.mainArea, self, "模型结构")
#: The current evaluating task (if any)
self._task = None # type: Optional[Task]
#: An executor we use to submit learner evaluations into a thread pool
self._executor = ThreadExecutor()
self.model = nn.Sequential(
self.conv(1, 8), # 14
nn.BatchNorm2d(8),
nn.ReLU(),
self.conv(8, 16), # 7
nn.BatchNorm2d(16),
nn.ReLU(),
self.conv(16, 32), # 4
nn.BatchNorm2d(32),
nn.ReLU(),
self.conv(32, 16), # 2
nn.BatchNorm2d(16),
nn.ReLU(),
self.conv(16, 10), # 1
nn.BatchNorm2d(10),
Flatten() # remove (1,1) grid
)
def __init__(self, num_classes=10):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.fc = nn.Linear(7 * 7 * 32, num_classes)
def __init__(self,
block,
layers,
num_classes=10,
zero_init_residual=False):
super(MyResNet, self).__init__()
self.inplanes = 64
self.conv1 = nn.Conv2d(1,
64,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight,
mode='fan_out',
nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
self.classifier = nn.Sequential(
nn.Dropout(p=0.5),
nn.Linear(512 * block.expansion, 256),
nn.BatchNorm1d(256),
nn.ReLU(inplace=True),
nn.Dropout(p=0.5),
nn.Linear(256, num_classes),
)
def two_conv_pool(self, in_channels, f1, f2):
s = nn.Sequential(
nn.Conv2d(in_channels, f1, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(f1),
nn.ReLU(inplace=True),
nn.Conv2d(f1, f2, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(f2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2),
)
for m in s.children():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
return s
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def __init__(self, num_classes=10):
super(VGG, self).__init__()
self.l1 = self.two_conv_pool(1, 64, 64)
self.l2 = self.two_conv_pool(64, 128, 128)
self.l3 = self.three_conv_pool(128, 256, 256, 256)
self.l4 = self.three_conv_pool(256, 256, 256, 256)
self.classifier = nn.Sequential(
nn.Dropout(p=0.5),
nn.Linear(256, 512),
nn.BatchNorm1d(512),
nn.ReLU(inplace=True),
nn.Dropout(p=0.5),
nn.Linear(512, num_classes),
)
def __init__(self):
super().__init__()
self.learn = None
# train_button = gui.button(self.controlArea, self, "开始训练", callback=self.train)
self.label = gui.label(self.mainArea, self, "模型结构")
#: The current evaluating task (if any)
self._task = None # type: Optional[Task]
#: An executor we use to submit learner evaluations into a thread pool
self._executor = ThreadExecutor()
# Device configuration
self.device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# Hyper parameters
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001
dir_path = Path(__file__).resolve()
data_path = f'{dir_path.parent.parent.parent}/datasets/'
# MNIST dataset
self.train_dataset = torchvision.datasets.MNIST(root=data_path,
train=True,
transform=transforms.ToTensor(),
download=False)
self.test_dataset = torchvision.datasets.MNIST(root=data_path,
train=False,
transform=transforms.ToTensor())
# Data loader
self.train_loader = torch.utils.data.DataLoader(dataset=self.train_dataset,
batch_size=batch_size,
shuffle=False)
self.test_loader = torch.utils.data.DataLoader(dataset=self.test_dataset,
batch_size=batch_size,
shuffle=False)
# self.model = ConvNet(num_classes).to(self.device)
self.model = nn.Sequential(
self.conv(1, 8), # 14
nn.BatchNorm2d(8),
nn.ReLU(),
self.conv(8, 16), # 7
nn.BatchNorm2d(16),
nn.ReLU(),
self.conv(16, 32), # 4
nn.BatchNorm2d(32),
nn.ReLU(),
self.conv(32, 16), # 2
nn.BatchNorm2d(16),
nn.ReLU(),
self.conv(16, 10), # 1
nn.BatchNorm2d(10),
Flatten() # remove (1,1) grid
).to(self.device)
# Loss and optimizer
self.criterion = nn.CrossEntropyLoss()
self.optimizer = torch.optim.Adam(self.model.parameters(), lr=learning_rate)