model-constructor 0.1.1

模型建造师

Constructor to create pytorch model.

安装

pip install model-constructor

或回购指令：

pip install git+https://github.com/ayasyrev/model_constructor.git

如何使用

它有两种用法。
经典-从带参数的函数创建模型。
通过创建构造函数对象，然后修改它，然后创建模型。在

类网络

首先导入构造函数类，然后创建模型构造函数项目。在

from model_constructor.net import *

^{pr2}$

model

 constr Net

现在我们有模型构造器，默认设置为xresnet18。我们可以在打电话后得到模型。在

model.c_in

3

model.c_out

1000

model.stem_sizes

[3, 32, 32, 64]

model.layers

[2, 2, 2, 2]

model.expansion

1

model()

Sequential(
  model Net
  (stem): Sequential(
    (conv_0): ConvLayer(
      (conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act_fn): ReLU(inplace=True)
    )
    (conv_1): ConvLayer(
      (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act_fn): ReLU(inplace=True)
    )
    (conv_2): ConvLayer(
      (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act_fn): ReLU(inplace=True)
    )
    (stem_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  )
  (body): Sequential(
    (l_0): Sequential(
      (bl_0): ResBlock(
        (convs): Sequential(
          (conv_0): ConvLayer(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (act_fn): ReLU(inplace=True)
          )
          (conv_1): ConvLayer(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (act_fn): ReLU(inplace=True)
      )
      (bl_1): ResBlock(
        (convs): Sequential(
          (conv_0): ConvLayer(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (act_fn): ReLU(inplace=True)
          )
          (conv_1): ConvLayer(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (act_fn): ReLU(inplace=True)
      )
    )
    (l_1): Sequential(
      (bl_0): ResBlock(
        (convs): Sequential(
          (conv_0): ConvLayer(
            (conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (act_fn): ReLU(inplace=True)
          )
          (conv_1): ConvLayer(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
        (idconv): ConvLayer(
          (conv): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (act_fn): ReLU(inplace=True)
      )
      (bl_1): ResBlock(
        (convs): Sequential(
          (conv_0): ConvLayer(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (act_fn): ReLU(inplace=True)
          )
          (conv_1): ConvLayer(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (act_fn): ReLU(inplace=True)
      )
    )
    (l_2): Sequential(
      (bl_0): ResBlock(
        (convs): Sequential(
          (conv_0): ConvLayer(
            (conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (act_fn): ReLU(inplace=True)
          )
          (conv_1): ConvLayer(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
        (idconv): ConvLayer(
          (conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (act_fn): ReLU(inplace=True)
      )
      (bl_1): ResBlock(
        (convs): Sequential(
          (conv_0): ConvLayer(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (act_fn): ReLU(inplace=True)
          )
          (conv_1): ConvLayer(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (act_fn): ReLU(inplace=True)
      )
    )
    (l_3): Sequential(
      (bl_0): ResBlock(
        (convs): Sequential(
          (conv_0): ConvLayer(
            (conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (act_fn): ReLU(inplace=True)
          )
          (conv_1): ConvLayer(
            (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
        (idconv): ConvLayer(
          (conv): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (act_fn): ReLU(inplace=True)
      )
      (bl_1): ResBlock(
        (convs): Sequential(
          (conv_0): ConvLayer(
            (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (act_fn): ReLU(inplace=True)
          )
          (conv_1): ConvLayer(
            (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (act_fn): ReLU(inplace=True)
      )
    )
  )
  (head): Sequential(
    (pool): AdaptiveAvgPool2d(output_size=1)
    (flat): Flatten()
    (fc): Linear(in_features=512, out_features=1000, bias=True)
  )
)

如果要更改模型，只需更改构造函数参数。
让我们创建xresnet50。在

model.expansion = 4
model.layers = [3,4,6,3]

现在我们可以看一下模型体，如果我们调用构造函数-我们有pytorch模型！在

model.body

Sequential(
  (l_0): Sequential(
    (bl_0): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_1): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_2): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
  )
  (l_1): Sequential(
    (bl_0): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
      (idconv): ConvLayer(
        (conv): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_1): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_2): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_3): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
  )
  (l_2): Sequential(
    (bl_0): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
      (idconv): ConvLayer(
        (conv): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_1): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_2): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_3): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_4): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_5): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
  )
  (l_3): Sequential(
    (bl_0): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
      (idconv): ConvLayer(
        (conv): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_1): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
    (bl_2): ResBlock(
      (convs): Sequential(
        (conv_0): ConvLayer(
          (conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_1): ConvLayer(
          (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act_fn): ReLU(inplace=True)
        )
        (conv_2): ConvLayer(
          (conv): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (act_fn): ReLU(inplace=True)
    )
  )
)

model.block_szs

^{pr21}$

更多的修改

本模块的主要目的是快速方便的修改模型。 这里有一个链接，可以通过add MaxBlurPool和ResBlockhttps://github.com/ayasyrev/imagenette_experiments/blob/master/ResnetTrick_create_model_fit.ipynb修改击败Imagenette排行榜

但现在让我们从fastai论坛创建mxresnet50模型https://forums.fast.ai/t/how-we-beat-the-5-epoch-imagewoof-leaderboard-score-some-new-techniques-to-consider

让我们创建mxresnet构造函数。在

mxresnet = Net()

然后让我们修改茎。在

mxresnet.stem_sizes = [3,32,64,64]

现在让我们把激活函数改成Mish。 这里是论坛讨论的链接https://forums.fast.ai/t/meet-mish-new-activation-function-possible-successor-to-relu

class Mish(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, x):  
        return x *( torch.tanh(F.softplus(x))) 

mxresnet.expansion = 4
mxresnet.layers = [3,4,6,3]
mxresnet.act_fn = Mish()
mxresnet.name = 'mxresnet50'

现在我们有了mxresnet50构造函数。
我们可以检查它的某些部分。
打电话后我们找到了模特。在

mxresnet

 constr mxresnet50

mxresnet.stem.conv_1

ConvLayer(
  (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (act_fn): Mish()
)

mxresnet.body.l_0.bl_0

^{pr31}$

现在让我们改变Resblock。NewResBlock（stiil not own name yet）位于0.1.0版本的lib中

mxresnet.block = NewResBlock

就这些。让我们看看我们有什么。在

mxresnet.body.l_1.bl_0

NewResBlock(
  (reduce): AvgPool2d(kernel_size=2, stride=2, padding=0)
  (convs): Sequential(
    (conv_0): ConvLayer(
      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act_fn): Mish()
    )
    (conv_1): ConvLayer(
      (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act_fn): Mish()
    )
    (conv_2): ConvLayer(
      (conv): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (idconv): ConvLayer(
    (conv): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
    (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  )
  (merge): Mish()
)

经典的方式

通常用tr参数调用构造函数。在

^{pr35}$

默认值为resnet18。在

^{pr2}$

不能在调用构造函数后修改模型，请使用参数定义模型。
例如，resnet34：

resnet34 = Net(block=BasicBlock, blocks=[3, 4, 6, 3])

预定义的Resnet模型-18，34，50

from model_constructor.resnet import *

model = resnet34(num_classes=10)

model = resnet50(num_classes=10)

来自fastai 1的预定义Xresnet

这个ie简化版来自fastai v1。为了更好地理解和试验模型，我进行了重构。例如，在v2中更改激活函数、不同的词干、批处理规范和激活顺序等非常简单，实现起来非常强大。在

from model_constructor.xresnet import *

model = xresnet50()

一些例子

我们可以通过改变模型的某些部分来试验模型。这里只有基本功能，但可以很容易地扩展。在

以下是一些示例：

自定义阀杆

带3层转换层的阀杆

model = Net(stem=partial(Stem, stem_sizes=[32, 32]))

model.stem

Stem(
  sizes: [3, 32, 32, 64]
  (conv_0): ConvLayer(
    (conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act_fn): ReLU(inplace=True)
  )
  (conv_1): ConvLayer(
    (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act_fn): ReLU(inplace=True)
  )
  (conv_2): ConvLayer(
    (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act_fn): ReLU(inplace=True)
  )
  (pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
)

model = Net(stem_sizes=[32, 64])

model.stem

Stem(
  sizes: [3, 32, 64, 64]
  (conv_0): ConvLayer(
    (conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act_fn): ReLU(inplace=True)
  )
  (conv_1): ConvLayer(
    (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act_fn): ReLU(inplace=True)
  )
  (conv_2): ConvLayer(
    (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act_fn): ReLU(inplace=True)
  )
  (pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
)

正常化前激活函数

model = Net(bn_1st=False)

model.stem

^{pr51}$

更改激活功能

new_act_fn = nn.LeakyReLU(inplace=True)

^{pr53}$

model.stem

^{pr55}$

model.body.layer_0.block_0

BasicBlock(
  (conv): Sequential(
    (conv_0): ConvLayer(
      (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act_fn): LeakyReLU(negative_slope=0.01, inplace=True)
    )
    (conv_1): ConvLayer(
      (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (merge): Noop()
  (act_conn): LeakyReLU(negative_slope=0.01, inplace=True)
)

标签：

• 项目

欢迎加入QQ群-->： 979659372

推荐PyPI第三方库

• git-wrapper

  围绕gitpython的python商品包装

• WSME

  简化restapi的编写，并用附加协议扩展它们。

• nose-logpertest

  记录nose插件以创建每个测试的日志

• omikuji

  python绑定到omikuji，一种有效的分区标签树实现及其在极端多标签分类中的变化

• descr

  python结构的html漂亮打印

• odoo11-addon-donation-recurring

  管理经常性捐赠

• simsim

  简单的python代码相似性检查器

• pserver.mailer

  没有项目描述

• coexecutor

  与threadpoolexecutor和processpoolexecutor兼容的coroutiepoolexecutor

• helloworld2019

  Hello World测试设置工具

• aliyun-python-sdk-release-test

  阿里云sdk发布测试模块，请不要使用

• fluentcms-campaign

  django fluent页面的基本新闻稿应用程序

• fpstimer

  一种时钟计时器，在Python2和3中提供与sleep（）类似的特性，用于保持特定的“每秒帧数”（fps）帧速率。

• etao

  简单密码分析库

• fir

  时间序列分析的有限脉冲响应包。