深度学习----DenseNet

1. 结构图

Input Shape : (3, 7, 7) — Output Shape : (2, 3, 3) — K : (3, 3) — P : (1, 1) — S : (2, 2) — D : (2, 2) — G : 1 

The parts of this post will be divided according to the following arguments. These arguments can be found in the Pytorch documentation of the Conv2d module :

• in_channels (int) — Number of channels in the input image
• out_channels (int) — Number of channels produced by the convolution
• kernel_size (int or tuple) — Size of the convolving kernel
• stride (int or tuple, optional) — Stride of the convolution. Default: 1
• padding (int or tuple, optional) — Zero-padding added to both sides of the input. Default: 0
• dilation (int or tuple, optional) — Spacing between kernel elements. Default: 1
• groups (int, optional) — Number of blocked connections from input channels to output channels. Default: 1
• bias (bool, optional) — If True, adds a learnable bias to the output. Default: True

 

1.  在Fig 1中, the last layer  is called the translation layer. this layer is responsible for the reducing of the dimension (如图 2, pooling)
2. 尽管该技术可以阻断identity backpropagation, 但是这仅仅发生在DenseNet block中的部分layers, 并不影响梯度流
3. DenseNet 的代码结构主要分为以下三块

                #. DenseLayer: 其主要在 DenseBlock 中完成一个单个的layer

                #. DenseBlock:

               #. TransitionLayer

2. 建立模型

class DenseLayer(nn.Module)
    def __init__(self, c_in,bn_size, growth_rate, act_fn):
        super().__init__()
        self.net = nn.sequential(
            nn.BatchNorm2d(c_in),
            act_fn(),
            nn.Con