brainpy.layers.ConvTranspose2d#

class brainpy.layers.ConvTranspose2d(in_channels, out_channels, kernel_size, stride=1, padding='SAME', w_initializer=XavierNormal(scale=1.0, mode=fan_avg, in_axis=-1, out_axis=-2, distribution=truncated_normal, rng=[ 502048944 3206891239]), b_initializer=ZeroInit, mask=None, precision=None, mode=None, name=None)[source]#

Two dimensional transposed convolution (aka. deconvolution).

__init__(in_channels, out_channels, kernel_size, stride=1, padding='SAME', w_initializer=XavierNormal(scale=1.0, mode=fan_avg, in_axis=-1, out_axis=-2, distribution=truncated_normal, rng=[ 502048944 3206891239]), b_initializer=ZeroInit, mask=None, precision=None, mode=None, name=None)[source]#

Initializes the module.

Parameters:

  • output_channels – Number of output channels.

  • kernel_shape – The shape of the kernel. Either an integer or a sequence of length 2.

  • stride (Union[int, Tuple[int, ...]]) – Optional stride for the kernel. Either an integer or a sequence of length 2. Defaults to 1.

  • output_shape – Output shape of the spatial dimensions of a transpose convolution. Can be either an integer or an iterable of integers. If a None value is given, a default shape is automatically calculated.

  • padding (Union[str, int, Tuple[int, int], Sequence[Tuple[int, int]]]) – Optional padding algorithm. Either VALID or SAME. Defaults to SAME. See: https://www.tensorflow.org/xla/operation_semantics#conv_convolution.

  • with_bias – Whether to add a bias. By default, true.

  • w_init – Optional weight initialization. By default, truncated normal.

  • b_init – Optional bias initialization. By default, zeros.

  • data_format – The data format of the input. Either NHWC or NCHW. By default, NHWC.

  • mask (Optional[TypeVar(ArrayType, Array, Variable, TrainVar, Array, ndarray)]) – Optional mask of the weights.

  • name (Optional[str]) – The name of the module.

Methods

__init__(in_channels, out_channels, kernel_size)

Initializes the module.

clear_input()

cpu()

Move all variable into the CPU device.

cuda()

Move all variables into the GPU device.

get_delay_data(identifier, delay_step, *indices)

Get delay data according to the provided delay steps.

load_state_dict(state_dict[, warn, compatible])

Copy parameters and buffers from state_dict into this module and its descendants.

load_states(filename[, verbose])

Load the model states.

nodes([method, level, include_self])

Collect all children nodes.

register_delay(identifier, delay_step, ...)

Register delay variable.

register_implicit_nodes(*nodes[, node_cls])

register_implicit_vars(*variables[, var_cls])

reset(*args, **kwargs)

Reset function which reset the whole variables in the model.

reset_local_delays([nodes])

Reset local delay variables.

reset_state(*args, **kwargs)

Reset function which reset the states in the model.

save_states(filename[, variables])

Save the model states.

state_dict()

Returns a dictionary containing a whole state of the module.

to(device)

Moves all variables into the given device.

tpu()

Move all variables into the TPU device.

train_vars([method, level, include_self])

The shortcut for retrieving all trainable variables.

tree_flatten()

Flattens the object as a PyTree.

tree_unflatten(aux, dynamic_values)

Unflatten the data to construct an object of this class.

unique_name([name, type_])

Get the unique name for this object.

update(x)

The function to specify the updating rule.

update_local_delays([nodes])

Update local delay variables.

vars([method, level, include_self, ...])

Collect all variables in this node and the children nodes.

Attributes

global_delay_data

Global delay data, which stores the delay variables and corresponding delay targets.

mode

Mode of the model, which is useful to control the multiple behaviors of the model.

name

Name of the model.