Pytorch: how and when to use Module, Sequential, ModuleList and ModuleDict



Photo by Markus Spiske on Unsplash

Updated at Pytorch 4.1

You can find the code here

Pytorch is an open source deep learning frameworks that provide a smart way to create ML models. Even if the documentation is well made, I still find that most people still are able to write bad and not organized PyTorch code.

Today, we are going to see how to use the three main building blocks of PyTorch: Module, Sequential and ModuleList. We are going to start with an example and iteratively we will make it better.

All these four classes are contained into torch.nn

Module: the main building block

The Module is the main building block, it defines the base class for all neural network and you MUST subclass it.

Let’s create a classic CNN classifier as example:

MyCNNClassifier( (conv1): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bn2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (fc1): Linear(in_features=25088, out_features=1024, bias=True) (fc2): Linear(in_features=1024, out_features=10, bias=True) )

This is a very simple classifier with an encoding part that uses two layers with 3×3 convs + batchnorm + relu and a decoding part with two linear layers. If you are not new to PyTorch you may have seen this type of coding before, but there are two problems.

If we want to add a layer we have to again write lots of code in the __init__ and in the forward function. Also, if we have some common block that we want to use in another model, e.g. the 3×3 conv + batchnorm + relu, we have to write it again.

Sequential: stack and merge layers

Sequential is a container of Modules that can be stacked together and run at the same time.

You can notice that we have to store into self everything. We can use Sequential to improve our code.

MyCNNClassifier( (conv_block1): Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (conv_block2): Sequential( (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (decoder): Sequential( (0): Linear(in_features=25088, out_features=1024, bias=True) (1): Sigmoid() (2): Linear(in_features=1024, out_features=10, bias=True) ) )

Much Better uhu?

Did you notice that conv_block1 and conv_block2 looks almost the same? We could create a function that reteurns a nn.Sequential to even simplify the code!

Then we can just call this function in our Module

MyCNNClassifier( (conv_block1): Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (conv_block2): Sequential( (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (decoder): Sequential( (0): Linear(in_features=25088, out_features=1024, bias=True) (1): Sigmoid() (2): Linear(in_features=1024, out_features=10, bias=True) ) )

Even cleaner! Still conv_block1 and conv_block2 are almost the same! We can merge them using nn.Sequential

MyCNNClassifier( (encoder): Sequential( (0): Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (1): Sequential( (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) ) (decoder): Sequential( (0): Linear(in_features=25088, out_features=1024, bias=True) (1): Sigmoid() (2): Linear(in_features=1024, out_features=10, bias=True) ) )

self.encoder now holds booth conv_block. We have decoupled logic for our model and make it easier to read and reuse. Our conv_block function can be imported and used in another model.

Dynamic Sequential: create multiple layers at once

What if we can to add a new layers in self.encoder, hardcoded them is not convinient:

Would it be nice if we can define the sizes as an array and automatically create all the layers without writing each one of them? Fortunately we can create an array and pass it to Sequential

MyCNNClassifier( (encoder): Sequential( (0): Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (1): Sequential( (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) ) (decoder): Sequential( (0): Linear(in_features=25088, out_features=1024, bias=True) (1): Sigmoid() (2): Linear(in_features=1024, out_features=10, bias=True) ) )

Let’s break it down. We created an array self.enc_sizes that holds the sizes of our encoder. Then we create an array conv_blocks by iterating the sizes. Since we have to give booth a in size and an outsize for each layer we ziped the size’array with itself by shifting it by one.

Just to be clear, take a look at the following example:

1 32 32 64

Then, since Sequential does not accept a list, we decompose it by using the * operator.

Tada! Now if we just want to add a size, we can easily add a new number to the list. It is a common practice to make the size a parameter.

MyCNNClassifier( (encoder): Sequential( (0): Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (1): Sequential( (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (2): Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) ) (decoder): Sequential( (0): Linear(in_features=25088, out_features=1024, bias=True) (1): Sigmoid() (2): Linear(in_features=1024, out_features=10, bias=True) ) )

We can do the same for the decoder part

MyCNNClassifier( (encoder): Sequential( (0): Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (1): Sequential( (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) ) (decoder): Sequential( (0): Sequential( (0): Linear(in_features=25088, out_features=1024, bias=True) (1): Sigmoid() ) (1): Sequential( (0): Linear(in_features=1024, out_features=512, bias=True) (1): Sigmoid() ) ) (last): Linear(in_features=512, out_features=10, bias=True) )

We followed the same pattern, we create a new block for the decoding part, linear + sigmoid, and we pass an array with the sizes. We had to add a self.last since we do not want to activate the output

Now, we can even break down our model in two! Encoder + Decoder

MyCNNClassifier( (encoder): MyEncoder( (conv_blokcs): Sequential( (0): Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (1): Sequential( (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) ) ) (decoder): MyDecoder( (dec_blocks): Sequential( (0): Sequential( (0): Linear(in_features=1024, out_features=512, bias=True) (1): Sigmoid() ) ) (last): Linear(in_features=512, out_features=10, bias=True) ) )

Be aware that MyEncoder and MyDecoder could also be functions that returns a nn.Sequential. I prefer to use the first pattern for models and the second for building blocks.

By diving our module into submodules it is easier to share the code, debug it and test it.

ModuleList : when we need to iterate

ModuleList allows you to store Module as a list. It can be useful when you need to iterate through layer and store/use some information, like in U-net.

The main difference between Sequential is that ModuleList have not a forward method so the inner layers are not connected. Assuming we need each output of each layer in the decoder, we can store it by:

torch.Size([4, 16]) torch.Size([4, 32]) [None, None]

ModuleDict: when we need to choose

What if we want to switch to LearkyRelu in our conv_block? We can use ModuleDict to create a dictionary of Module and dynamically switch Module when we want

Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.01) ) Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() )

Final implementation

Let’s wrap it up everything!

MyCNNClassifier( (encoder): MyEncoder( (conv_blokcs): Sequential( (0): Sequential( (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.01) ) (1): Sequential( (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.01) ) ) ) (decoder): MyDecoder( (dec_blocks): Sequential( (0): Sequential( (0): Linear(in_features=1024, out_features=512, bias=True) (1): Sigmoid() ) ) (last): Linear(in_features=512, out_features=10, bias=True) ) )

Conclusion

You can find the code here

So, in summary.

  • Use Module when you have a big block compose of multiple smaller blocks
  • Use Sequential when you want to create a small block from layers
  • Use ModuleList when you need to iterate through some layers or building blocks and do something
  • Use ModuleDict when you need to parametise some blocks of your model, for example an activation function

That’s all folks!

Thank you for reading


Originally published at gist.github.com.

Source: Deep Learning on Medium