Conv3DTranspose

Public technical reference documentation from Graiphic. For current SOTA installation and toolkit guides, visit the documentation center.

Description

Returns the Conv3DTranspose layer weights. Type : polymorphic.

Documentation illustration (illustration unavailable in the archive).

Input parameters

weights : cluster

index : integer, index of layer.
name : string, name of layer.
Documentation illustration (illustration unavailable in the archive). weight : variant, weight of layer.

Documentation illustration (illustration unavailable in the archive).

Output parameters

weights_info : cluster

index : integer, index of layer.
name : string, name of layer.
weights : cluster

filters : array, 5D values. filters = [n_filters, channel, size[0], size[1], size[2]].
biases : array, 1D values. biases = [n_filters].

Documentation illustration (illustration unavailable in the archive).

Dimension

filters = [n_filters, channel, size[0], size[1], size[2]]

The size of filters depends on the input of the Conv3DTranspose layer and the parameters n_filters and size.
For example, if the input of the layer has a size of [batch_size = 10, channel = 8, conv_dim1 = 7, conv_dim2 = 5, conv_dim3 = 5], n_filters has the value 6 and size the value [3, 3, 3] then filters will have a size of [n_filters = 6, channel = 8, size[0] = 3, size[1] = 3, size[2] = 3].

biases = [n_filters].

The size of biases depends on the parameter n_filters of the Conv3DTranspose layer.

Example

All these exemples are snippets PNG, you can drop these Snippet onto the block diagram and get the depicted code added to your VI (Do not forget to install Deep Learning library to run it).