GoogleNet的inception

最新推荐文章于 2023-05-12 01:07:40 发布

m0_50903443

最新推荐文章于 2023-05-12 01:07:40 发布

阅读量283

点赞数

分类专栏： CV基础初学文章标签：卷积深度学习卷积神经网络

本文链接：https://blog.csdn.net/m0_50903443/article/details/110285133

版权

GoogleNet V3采用非对称卷积、卷积池化融合等策略减少计算量，保持信息完整。通过1*1卷积进行通道融合，用3*3卷积替代5*5，以减小计算成本。分辨率下降时，它使用池化和增加步长，避免过度信息损失。此外，1xn和nx1的卷积方式也用于降低计算量，同时保持特征的有效提取。

摘要由CSDN通过智能技术生成

V3具体结构
V3版本很重就是后面几个inception，包含了卷积分解：非对称卷积，卷积池化融合，减少计算量，同时损失信息不大，利用步长等于2代替池化，利用小卷积核融合代替大卷积核得到相同感受野，利用1*1分解为几个卷积一起计算融合，减少计算量，又不损失信息

lass Inception3(nn.Module):

    def __init__(self, num_classes=1000, aux_logits=True, transform_input=False,
                 inception_blocks=None, init_weights=None):
        super(Inception3, self).__init__()
        if inception_blocks is None:
            inception_blocks = [
                BasicConv2d, InceptionA, InceptionB, InceptionC,
                InceptionD, InceptionE, InceptionAux
            ]
        if init_weights is None:
            warnings.warn('The default weight initialization of inception_v3 will be changed in future releases of '
                          'torchvision. If you wish to keep the old behavior (which leads to long initialization times'
                          ' due to scipy/scipy#11299), please set init_weights=True.', FutureWarning)
            init_weights = True
        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.transform_input = transform_input
        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.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2)
        self.Conv2d_3b_1x1 = conv_block(64, 80, kernel_size=1)
        self.Conv2d_4a_3x3 = conv_block(80, 192, kernel_size=3)
        self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=2)
        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.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.dropout = nn.Dropout()
        self.fc = nn.Linear(2048, num_classes)
        if init_weights:
            for m in self.modules():
                if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
                    import scipy.stats as stats
                    stddev = m.stddev if hasattr(m, 'stddev') else 0.1
                    X = stats.truncnorm(-2, 2, scale=stddev)
                    values = torch.as_tensor(X.rvs(m