--- title: DSSM keywords: fastai sidebar: home_sidebar summary: "An implementation of DSSM, Deep Structured Semantic Model." description: "An implementation of DSSM, Deep Structured Semantic Model." nb_path: "nbs/models/dssm.ipynb" ---
{% raw %}
{% endraw %} {% raw %}
{% endraw %} {% raw %}

class DSSM[source]

DSSM(main_embed_size, feat_embed_size, n_users, n_items, hidden_size, feat_map, static_feat, dynamic_feat, use_bn=True) :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}
model = DSSM(main_embed_size=2, feat_embed_size=2, n_users=5, n_items=5, hidden_size=[5,3], feat_map={'a_vocab':2,'b_vocab':2}, static_feat=['a'], dynamic_feat=['b'], use_bn=True)
model
DSSM(
  (embed_user): Embedding(6, 2, padding_idx=5)
  (embed_item): Embedding(6, 2, padding_idx=5)
  (embed_feat): ModuleDict(
    (a): Embedding(3, 2, padding_idx=2)
    (b): Embedding(3, 2, padding_idx=2)
  )
  (fcu1): Linear(in_features=4, out_features=5, bias=True)
  (fcu2): Linear(in_features=5, out_features=3, bias=True)
  (fcu3): Linear(in_features=3, out_features=2, bias=True)
  (fci1): Linear(in_features=4, out_features=5, bias=True)
  (fci2): Linear(in_features=5, out_features=3, bias=True)
  (fci3): Linear(in_features=3, out_features=2, bias=True)
  (bnu1): BatchNorm1d(5, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (bnu2): BatchNorm1d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (bni1): BatchNorm1d(5, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (bni2): BatchNorm1d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
{% endraw %}