model-constructor 0.1.1

Constructor for pytorch models.

model_constructor

Constructor to create pytorch model.

_

Install

pip install model-constructor

Or instll from repo:

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

How to use

It can be used two ways.
Classic - create model from function with parameters.
And by creating constructor object, then modify it and then create model.

Class Net

First import constructor class, then create model constructor oject.

from model_constructor.net import *

model = Net()

model

 constr Net

Now we have model consructor, defoult setting as xresnet18. And we can get model after call it.

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)
  )
)

If you want to change model, just change constructor parameters.
Lets create xresnet50.

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

Now we can look at model body and if we call constructor - we have pytorch model!

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

[16, 64, 128, 256, 512]

More modification.

Main purpose of this module - fast and easy modify model. And here is the link to more modification to beat Imagenette leaderboard with add MaxBlurPool and modification to ResBlock https://github.com/ayasyrev/imagenette_experiments/blob/master/ResnetTrick_create_model_fit.ipynb

But now lets create model as mxresnet50 from fastai forums tread https://forums.fast.ai/t/how-we-beat-the-5-epoch-imagewoof-leaderboard-score-some-new-techniques-to-consider

Lets create mxresnet constructor.

mxresnet = Net()

Then lets modify stem.

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

Now lets change activation function to Mish. Here is link to forum disscussion 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'

Now we have mxresnet50 constructor.
We can inspect some parts of it.
And after call it we got model.

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

ResBlock(
  (convs): Sequential(
    (conv_0): ConvLayer(
      (conv): Conv2d(64, 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): Mish()
    )
    (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): Mish()
    )
    (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)
    )
  )
  (idconv): 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): Mish()
)

Now lets change Resblock. NewResBlock (stiil not own name yet) is in lib from version 0.1.0

mxresnet.block = NewResBlock

That all. Let see what we have.

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()
)

Classic way

Usual way to get model - call constructor with parametrs.

from model_constructor.constructor import *

Default is resnet18.

model = Net()

You cant modify model after call constructor, so define model with parameters.
For example, resnet34:

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

Predefined Resnet models - 18, 34, 50.

from model_constructor.resnet import *

model = resnet34(num_classes=10)

model = resnet50(num_classes=10)

Predefined Xresnet from fastai 1.

This ie simplified version from fastai v1. I did refactoring for better understand and experiment with models. For example, it's very simple to change activation funtions, different stems, batchnorm and activation order etc. In v2 much powerfull realisation.

from model_constructor.xresnet import *

model = xresnet50()

Some examples.

We can experiment with models by changing some parts of model. Here only base functionality, but it can be easily extanded.

Here is some examples:

Custom stem

Stem with 3 conv layers

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)
)

Activation function before Normalization

model = Net(bn_1st=False)

model.stem

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

Change activation function

new_act_fn = nn.LeakyReLU(inplace=True)

model = Net(act_fn=new_act_fn)

model.stem

Stem(
  sizes: [3, 64]
  (conv_0): ConvLayer(
    (conv): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), 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)
  )
  (pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
)

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)
)