jittor.models.inception 源代码


import jittor as jt
from jittor import nn
__all__ = ['Inception3', 'inception_v3']

[文档]def inception_v3(pretrained=False, progress=True, **kwargs): model = Inception3(**kwargs) if pretrained: model.load("jittorhub://inception_v3.pkl") return model
[文档]class Inception3(nn.Module): """ Inceptionv3 model architecture. Args: * num_classes: Number of classes. Default: 1000. * aux_logits: If True, add an auxiliary branch that can improve training. Default: True * inception_blocks: List of seven blocks, [conv_block, inception_a, inception_b, inception_c, inception_d, inception_e, inception_aux]. If None, will use [BasicConv2d, InceptionA, InceptionB, InceptionC, InceptionD, InceptionE, InceptionAux] instead. Default: None. * init_weights: Defualt: True. """ def __init__(self, num_classes=1000, aux_logits=True, inception_blocks=None, init_weights=True): super(Inception3, self).__init__() if (inception_blocks is None): inception_blocks = [BasicConv2d, InceptionA, InceptionB, InceptionC, InceptionD, InceptionE, InceptionAux] assert (len(inception_blocks) == 7) conv_block = inception_blocks[0] inception_a = inception_blocks[1] inception_b = inception_blocks[2] inception_c = inception_blocks[3] inception_d = inception_blocks[4] inception_e = inception_blocks[5] inception_aux = inception_blocks[6] self.aux_logits = aux_logits self.Conv2d_1a_3x3 = conv_block(3, 32, kernel_size=3, stride=2) self.Conv2d_2a_3x3 = conv_block(32, 32, kernel_size=3) self.Conv2d_2b_3x3 = conv_block(32, 64, kernel_size=3, padding=1) self.Conv2d_3b_1x1 = conv_block(64, 80, kernel_size=1) self.Conv2d_4a_3x3 = conv_block(80, 192, kernel_size=3) self.Mixed_5b = inception_a(192, pool_features=32) self.Mixed_5c = inception_a(256, pool_features=64) self.Mixed_5d = inception_a(288, pool_features=64) self.Mixed_6a = inception_b(288) self.Mixed_6b = inception_c(768, channels_7x7=128) self.Mixed_6c = inception_c(768, channels_7x7=160) self.Mixed_6d = inception_c(768, channels_7x7=160) self.Mixed_6e = inception_c(768, channels_7x7=192) if aux_logits: self.AuxLogits = inception_aux(768, num_classes) self.Mixed_7a = inception_d(768) self.Mixed_7b = inception_e(1280) self.Mixed_7c = inception_e(2048) self.fc = nn.Linear(2048, num_classes) def _forward(self, x): x = self.Conv2d_1a_3x3(x) x = self.Conv2d_2a_3x3(x) x = self.Conv2d_2b_3x3(x) x = nn.pool(x, 3, "maximum", stride=2) x = self.Conv2d_3b_1x1(x) x = self.Conv2d_4a_3x3(x) x = nn.pool(x, 3, "maximum", stride=2) x = self.Mixed_5b(x) x = self.Mixed_5c(x) x = self.Mixed_5d(x) x = self.Mixed_6a(x) x = self.Mixed_6b(x) x = self.Mixed_6c(x) x = self.Mixed_6d(x) x = self.Mixed_6e(x) aux_defined = self.aux_logits if aux_defined: aux = self.AuxLogits(x) else: aux = None x = self.Mixed_7a(x) x = self.Mixed_7b(x) x = self.Mixed_7c(x) x = nn.AdaptiveAvgPool2d(1)(x) x = nn.Dropout()(x) x = jt.reshape(x, (x.shape[0], (- 1))) x = self.fc(x) return (x, aux)
[文档] def eager_outputs(self, x, aux): return x
[文档] def execute(self, x): (x, aux) = self._forward(x) aux_defined = self.aux_logits return self.eager_outputs(x, aux)
class InceptionA(nn.Module): def __init__(self, in_channels, pool_features, conv_block=None): super(InceptionA, self).__init__() if (conv_block is None): conv_block = BasicConv2d self.branch1x1 = conv_block(in_channels, 64, kernel_size=1) self.branch5x5_1 = conv_block(in_channels, 48, kernel_size=1) self.branch5x5_2 = conv_block(48, 64, kernel_size=5, padding=2) self.branch3x3dbl_1 = conv_block(in_channels, 64, kernel_size=1) self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1) self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, padding=1) self.branch_pool = conv_block(in_channels, pool_features, kernel_size=1) def _forward(self, x): branch1x1 = self.branch1x1(x) branch5x5 = self.branch5x5_1(x) branch5x5 = self.branch5x5_2(branch5x5) branch3x3dbl = self.branch3x3dbl_1(x) branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl) branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl) branch_pool = nn.pool(x, 3, "mean", stride=1, padding=1) branch_pool = self.branch_pool(branch_pool) outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool] return outputs def execute(self, x): outputs = self._forward(x) return jt.concat(outputs, dim=1) class InceptionB(nn.Module): def __init__(self, in_channels, conv_block=None): super(InceptionB, self).__init__() if (conv_block is None): conv_block = BasicConv2d self.branch3x3 = conv_block(in_channels, 384, kernel_size=3, stride=2) self.branch3x3dbl_1 = conv_block(in_channels, 64, kernel_size=1) self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1) self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, stride=2) def _forward(self, x): branch3x3 = self.branch3x3(x) branch3x3dbl = self.branch3x3dbl_1(x) branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl) branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl) branch_pool = nn.pool(x, 3, "maximum", stride=2) outputs = [branch3x3, branch3x3dbl, branch_pool] return outputs def execute(self, x): outputs = self._forward(x) return jt.concat(outputs, dim=1) class InceptionC(nn.Module): def __init__(self, in_channels, channels_7x7, conv_block=None): super(InceptionC, self).__init__() if (conv_block is None): conv_block = BasicConv2d self.branch1x1 = conv_block(in_channels, 192, kernel_size=1) c7 = channels_7x7 self.branch7x7_1 = conv_block(in_channels, c7, kernel_size=1) self.branch7x7_2 = conv_block(c7, c7, kernel_size=(1, 7), padding=(0, 3)) self.branch7x7_3 = conv_block(c7, 192, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7dbl_1 = conv_block(in_channels, c7, kernel_size=1) self.branch7x7dbl_2 = conv_block(c7, c7, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7dbl_3 = conv_block(c7, c7, kernel_size=(1, 7), padding=(0, 3)) self.branch7x7dbl_4 = conv_block(c7, c7, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7dbl_5 = conv_block(c7, 192, kernel_size=(1, 7), padding=(0, 3)) self.branch_pool = conv_block(in_channels, 192, kernel_size=1) def _forward(self, x): branch1x1 = self.branch1x1(x) branch7x7 = self.branch7x7_1(x) branch7x7 = self.branch7x7_2(branch7x7) branch7x7 = self.branch7x7_3(branch7x7) branch7x7dbl = self.branch7x7dbl_1(x) branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl) branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl) branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl) branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl) branch_pool = nn.pool(x, kernel_size=3, op="mean", stride=1, padding=1) branch_pool = self.branch_pool(branch_pool) outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool] return outputs def execute(self, x): outputs = self._forward(x) return jt.concat(outputs, dim=1) class InceptionD(nn.Module): def __init__(self, in_channels, conv_block=None): super(InceptionD, self).__init__() if (conv_block is None): conv_block = BasicConv2d self.branch3x3_1 = conv_block(in_channels, 192, kernel_size=1) self.branch3x3_2 = conv_block(192, 320, kernel_size=3, stride=2) self.branch7x7x3_1 = conv_block(in_channels, 192, kernel_size=1) self.branch7x7x3_2 = conv_block(192, 192, kernel_size=(1, 7), padding=(0, 3)) self.branch7x7x3_3 = conv_block(192, 192, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7x3_4 = conv_block(192, 192, kernel_size=3, stride=2) def _forward(self, x): branch3x3 = self.branch3x3_1(x) branch3x3 = self.branch3x3_2(branch3x3) branch7x7x3 = self.branch7x7x3_1(x) branch7x7x3 = self.branch7x7x3_2(branch7x7x3) branch7x7x3 = self.branch7x7x3_3(branch7x7x3) branch7x7x3 = self.branch7x7x3_4(branch7x7x3) branch_pool = nn.pool(x, kernel_size=3, op="maximum", stride=2) outputs = [branch3x3, branch7x7x3, branch_pool] return outputs def execute(self, x): outputs = self._forward(x) return jt.concat(outputs, dim=1) class InceptionE(nn.Module): def __init__(self, in_channels, conv_block=None): super(InceptionE, self).__init__() if (conv_block is None): conv_block = BasicConv2d self.branch1x1 = conv_block(in_channels, 320, kernel_size=1) self.branch3x3_1 = conv_block(in_channels, 384, kernel_size=1) self.branch3x3_2a = conv_block(384, 384, kernel_size=(1, 3), padding=(0, 1)) self.branch3x3_2b = conv_block(384, 384, kernel_size=(3, 1), padding=(1, 0)) self.branch3x3dbl_1 = conv_block(in_channels, 448, kernel_size=1) self.branch3x3dbl_2 = conv_block(448, 384, kernel_size=3, padding=1) self.branch3x3dbl_3a = conv_block(384, 384, kernel_size=(1, 3), padding=(0, 1)) self.branch3x3dbl_3b = conv_block(384, 384, kernel_size=(3, 1), padding=(1, 0)) self.branch_pool = conv_block(in_channels, 192, kernel_size=1) def _forward(self, x): branch1x1 = self.branch1x1(x) branch3x3 = self.branch3x3_1(x) branch3x3 = [self.branch3x3_2a(branch3x3), self.branch3x3_2b(branch3x3)] branch3x3 = jt.concat(branch3x3, dim=1) branch3x3dbl = self.branch3x3dbl_1(x) branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl) branch3x3dbl = [self.branch3x3dbl_3a(branch3x3dbl), self.branch3x3dbl_3b(branch3x3dbl)] branch3x3dbl = jt.concat(branch3x3dbl, dim=1) branch_pool = nn.pool(x, kernel_size=3, op="mean", stride=1, padding=1) branch_pool = self.branch_pool(branch_pool) outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool] return outputs def execute(self, x): outputs = self._forward(x) return jt.concat(outputs, dim=1) class InceptionAux(nn.Module): def __init__(self, in_channels, num_classes, conv_block=None): super(InceptionAux, self).__init__() if (conv_block is None): conv_block = BasicConv2d self.conv0 = conv_block(in_channels, 128, kernel_size=1) self.conv1 = conv_block(128, 768, kernel_size=5) self.conv1.stddev = 0.01 self.fc = nn.Linear(768, num_classes) self.fc.stddev = 0.001 def execute(self, x): x = nn.pool(x, kernel_size=5, op="mean", stride=3) x = self.conv0(x) x = self.conv1(x) x = nn.AdaptiveAvgPool2d(1)(x) x = jt.reshape(x, (x.shape[0], (- 1))) x = self.fc(x) return x class BasicConv2d(nn.Module): def __init__(self, in_channels, out_channels, **kwargs): super(BasicConv2d, self).__init__() self.conv = nn.Conv(in_channels, out_channels, bias=False, **kwargs) self.bn = nn.BatchNorm(out_channels, eps=0.001) def execute(self, x): x = self.conv(x) x = self.bn(x) return nn.relu(x)