MIDAA-checkpoint

Module Contents

Classes

MIDAA

Base class for all neural network modules.

class MIDAA-checkpoint.MIDAA(n_dim_input, input_types, n_dim_input_side=None, input_types_side=None, batch_size=5120, hidden_dims_dec_common=[128, 256], hidden_dims_dec_last=[1024], hidden_dims_dec_last_side=None, hidden_dims_enc_ind=[512], hidden_dims_enc_common=[256, 128], hidden_dims_enc_pre_Z=[128, 64], layers_independent_types=None, layers_independent_types_side=None, output_types_side=None, image_size=[256, 256], theta_bounds=(1e-05, 10000), init_loc=0.1, init_theta=1, prior_loc=10, narchetypes=10, fix_Z=False, Z_fix_norm=None, Z_fix_release=False, initialization_mode_step1=False, initialization_mode_step2=False, just_VAE=False, linearize_encoder=False, linearize_decoder=False, kernel_size=3, stride=1, padding=1, pool_size=2, pool_stride=2)

Bases: midaa.Decoder.nn.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 to(), etc.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

model(input_matrix, model_matrix, norm_factors, input_matrix_side, loss_weights_reconstruction=None, loss_weights_side=None, initialization_input=None, initialization_B_weight=None)

guide(input_matrix, model_matrix, norm_factors, input_matrix_side, loss_weights_reconstruction=None, loss_weights_side=None, initialization_input=None, initialization_B_weight=None)