All (Model) — Deep Learning Toolkit / Architecture / Get & Set / Set / Weight / Write

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

Load all weights model

Description

Load the weights of a model. By default, all layer weights will be loaded but if you set “RANDOM” to a specific index in “init_weight_array”, the selected layer will be randomly initialized.
Documentation illustration (illustration unavailable in the archive).

Input parameters

Model in : model architecture.
weights_model : model architecture.
file_type : enum, type of the file on which the summary is written.

- None : returns the summary only in a cluster array.
- txt : returns the summary in a text file and cluster array. (default)
- csv : returns the summary in a comma-separated values (csv) file and cluster array.

Documentation illustration (illustration unavailable in the archive). init_weight_array : array

index : integer, index of layer.
init_weight : enum, weight initialization mode.

Documentation illustration (illustration unavailable in the archive).

Output parameters

Model out : model architecture.

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).