NN Module - selenecodes/IPASS GitHub Wiki

Classes

class  NN(stackSize=4)

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.

Source Code: From Github with ❤️ - NN.py

Parameters

stackSize : int

  • the count of frames per state to run the network on.

Ancestors

torch.nn.modules.module.Module

Static Methods

def initWeights(m)

Neural Network Weights Initialiser

Parameters

m : NN

  • Reference to the NN module itself
Source code 
@staticmethod
def  initWeights(m):
    """ Neural Network Weights Initialiser

        Parameters
        -------
        m : NN
            Reference to the NN module itself
    """

    if  isinstance(m, nn.Conv2d):
        nn.init.xavier_uniform_(m.weight, gain=nn.init.calculate_gain('relu'))
        nn.init.constant_(m.bias, 0.1)

Methods

def forward(self, x)

Feed forward function

Parameters

x

  • The network's input

Returns

alpha : int

  • The network's alpha value

beta : int

  • The network's beta value

v

  • The predicted value
Source code 
def  forward(self, x):
    """ Feed forward function

    Parameters
    -------
    x
        The network's input

    Returns
    -------
    alpha : int
        The network's alpha value
    beta : int
        The network's beta value
    v
        The predicted value
    """

    x =  self.cnn(x).view(-1, 256)
    v =  self.v(x)
    x =  self.fc(x)
    alpha =  self.alpha(x) +  1
    beta =  self.beta(x) +  1

    return (alpha, beta), v
⚠️ **GitHub.com Fallback** ⚠️