domainlab.compos.nn_zoo package

Submodules

domainlab.compos.nn_zoo.net_adversarial module

class domainlab.compos.nn_zoo.net_adversarial.AutoGradFunMultiply(*args, **kwargs)

Bases: Function

static backward(ctx, grad_output)

Defines a formula for differentiating the operation with backward mode automatic differentiation (alias to the vjp function).

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by as many outputs as the forward() returned (None will be passed in for non tensor outputs of the forward function), and it should return as many tensors, as there were inputs to forward(). Each argument is the gradient w.r.t the given output, and each returned value should be the gradient w.r.t. the corresponding input. If an input is not a Tensor or is a Tensor not requiring grads, you can just pass None as a gradient for that input.

The context can be used to retrieve tensors saved during the forward pass. It also has an attribute ctx.needs_input_grad as a tuple of booleans representing whether each input needs gradient. E.g., backward() will have ctx.needs_input_grad[0] = True if the first input to forward() needs gradient computated w.r.t. the output.

static forward(ctx, x, alpha)

Performs the operation.

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by any number of arguments (tensors or other types).

The context can be used to store arbitrary data that can be then retrieved during the backward pass. Tensors should not be stored directly on ctx (though this is not currently enforced for backward compatibility). Instead, tensors should be saved either with ctx.save_for_backward() if they are intended to be used in backward (equivalently, vjp) or ctx.save_for_forward() if they are intended to be used for in jvp.

class domainlab.compos.nn_zoo.net_adversarial.AutoGradFunReverseMultiply(*args, **kwargs)

Bases: Function

https://pytorch.org/docs/stable/autograd.html https://pytorch.org/docs/stable/notes/extending.html#extending-autograd

static backward(ctx, grad_output)

Defines a formula for differentiating the operation with backward mode automatic differentiation (alias to the vjp function).

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by as many outputs as the forward() returned (None will be passed in for non tensor outputs of the forward function), and it should return as many tensors, as there were inputs to forward(). Each argument is the gradient w.r.t the given output, and each returned value should be the gradient w.r.t. the corresponding input. If an input is not a Tensor or is a Tensor not requiring grads, you can just pass None as a gradient for that input.

The context can be used to retrieve tensors saved during the forward pass. It also has an attribute ctx.needs_input_grad as a tuple of booleans representing whether each input needs gradient. E.g., backward() will have ctx.needs_input_grad[0] = True if the first input to forward() needs gradient computated w.r.t. the output.

static forward(ctx, x, alpha)

Performs the operation.

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by any number of arguments (tensors or other types).

The context can be used to store arbitrary data that can be then retrieved during the backward pass. Tensors should not be stored directly on ctx (though this is not currently enforced for backward compatibility). Instead, tensors should be saved either with ctx.save_for_backward() if they are intended to be used in backward (equivalently, vjp) or ctx.save_for_forward() if they are intended to be used for in jvp.

class domainlab.compos.nn_zoo.net_adversarial.Flatten

Bases: Module

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

domainlab.compos.nn_zoo.net_classif module

Classifier

class domainlab.compos.nn_zoo.net_classif.ClassifDropoutReluLinear(z_dim, target_dim)

Bases: Module

first apply dropout, then relu, then linearly fully connected, without activation

forward(z_vec)

Parameters:

z_vec –

domainlab.compos.nn_zoo.net_conv_conv_bn_pool_2 module

In PyTorch, images are represented as [channels, height, width]

class domainlab.compos.nn_zoo.net_conv_conv_bn_pool_2.NetConvBnReluPool2L(isize, conv_stride, dim_out_h)

Bases: Module

forward(tensor_x)

Parameters:

tensor_x – image

class domainlab.compos.nn_zoo.net_conv_conv_bn_pool_2.NetConvDense(isize, conv_stride, dim_out_h, args, dense_layer=None)

Bases: Module

• For direct topic inference

• For custom erm, which is extracting the path of VAE from encoder until classifier. note in encoder, there is extra layer of hidden to mean and scale, in this component, it is replaced with another hidden layer.

forward(tensor_x)

Parameters:

tensor_x – image

domainlab.compos.nn_zoo.net_conv_conv_bn_pool_2.mk_conv_bn_relu_pool(i_channel, conv_stride=1, max_pool_stride=2)

Convolution, batch norm, maxpool_2d Convolution with maxpool_2d as last operation :param i_channel: :param conv_stride: :param max_pool_stride:

domainlab.compos.nn_zoo.net_gated module

class domainlab.compos.nn_zoo.net_gated.Conv2d(input_channels, output_channels, kernel_size, stride, padding, dilation=1, activation=None, bias=True)

Bases: Module

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class domainlab.compos.nn_zoo.net_gated.GatedConv2d(input_channels, output_channels, kernel_size, stride, padding, dilation=1, activation=None)

Bases: Module

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class domainlab.compos.nn_zoo.net_gated.GatedDense(input_size, output_size, activation=None)

Bases: Module

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

domainlab.compos.nn_zoo.nn module

class domainlab.compos.nn_zoo.nn.DenseNet(input_flat_size, out_hidden_size=1024, last_feat_dim=4096, p_dropout=0.5)

Bases: Module

(input)-dropout-linear-relu-dropout-linear-relu(output)

forward(tensor_x)

Parameters:

x –

class domainlab.compos.nn_zoo.nn.LayerId

Bases: Module

used to delete layers

forward(x)

Parameters:

x –

domainlab.compos.nn_zoo.nn_alex module

class domainlab.compos.nn_zoo.nn_alex.Alex4DeepAll(flag_pretrain, dim_y)

Bases: AlexNetBase

change the last layer output of AlexNet to the dimension of the

class domainlab.compos.nn_zoo.nn_alex.AlexNetBase(flag_pretrain)

Bases: NetTorchVisionBase

AlexNet(
(features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
    (1): ReLU(inplace=True)
    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (4): ReLU(inplace=True)
    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU(inplace=True)
    (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (9): ReLU(inplace=True)
    (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace=True)
    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(6, 6))
(classifier): Sequential(
    (0): Dropout(p=0.5, inplace=False)
    (1): Linear(in_features=9216, out_features=4096, bias=True)
    (2): ReLU(inplace=True)
    (3): Dropout(p=0.5, inplace=False)
    (4): Linear(in_features=4096, out_features=4096, bias=True)
    (5): ReLU(inplace=True)
    (6): Linear(in_features=4096, out_features=7, bias=True)
)
)

fetch_net(flag_pretrain)

class domainlab.compos.nn_zoo.nn_alex.AlexNetNoLastLayer(flag_pretrain)

Bases: AlexNetBase

Change the last layer of AlexNet with identity layer, the classifier from VAE can then have the same layer depth as erm model so it is fair for comparison

domainlab.compos.nn_zoo.nn_torchvision module

class domainlab.compos.nn_zoo.nn_torchvision.NetTorchVisionBase(flag_pretrain)

Bases: Module

fetch model from torchvision

fetch_net(flag_pretrain)

forward(tensor)

delegate forward operation to self.net_torchvision

show()

print out which layer will be optimized

Module contents