Activation modules

class torch_lattice.nn.modules.activation.GELU(approximate='none')

Bases: GELU

Parameters:

approximate (str)

forward(input)

Runs the forward pass.

Return type:

SparseTensor

Parameters:

input (SparseTensor)

class torch_lattice.nn.modules.activation.LeakyReLU(negative_slope=0.01, inplace=False)

Bases: LeakyReLU

Parameters:

• negative_slope (float)

• inplace (bool)

forward(input)

Run forward pass.

Return type:

SparseTensor

Parameters:

input (SparseTensor)

class torch_lattice.nn.modules.activation.ReLU(inplace=False)

Bases: ReLU

Parameters:

inplace (bool)

forward(input)

Runs the forward pass.

Return type:

SparseTensor

Parameters:

input (SparseTensor)

class torch_lattice.nn.modules.activation.SiLU(inplace=False)

Bases: SiLU

Parameters:

inplace (bool)

forward(input)

Runs the forward pass.

Return type:

SparseTensor

Parameters:

input (SparseTensor)

class torch_lattice.nn.modules.activation.Sigmoid(*args, **kwargs)

Bases: Sigmoid

Parameters:

• args (Any)

• kwargs (Any)

forward(input)

Runs the forward pass.

Return type:

SparseTensor

Parameters:

input (SparseTensor)

class torch_lattice.nn.modules.activation.Softplus(beta=1.0, threshold=20.0)

Bases: Softplus

Parameters:

• beta (float)

• threshold (float)

forward(input)

Run forward pass.

Return type:

SparseTensor

Parameters:

input (SparseTensor)

class torch_lattice.nn.modules.activation.Tanh(*args, **kwargs)

Bases: Tanh

Parameters:

• args (Any)

• kwargs (Any)

forward(input)

Runs the forward pass.

Return type:

SparseTensor

Parameters:

input (SparseTensor)