++ed by:
AERO TOMMY

2 PAUSE users

Sergey V. Kolychev

NAME

    AI::MXNet::Gluon::ModelZoo - A collection of pretrained MXNet Gluon models

SYNOPSIS

    ## run forward prediction on random data
    use AI::MXNet::Gluon::ModelZoo qw(get_model);
    my $alexnet = get_model('alexnet', pretrained => 1);
    my $out = $alexnet->(mx->nd->random->uniform(shape=>[1, 3, 224, 224]));
    print $out->aspdl;

DESCRIPTION

    This module houses a collection of pretrained models (the parameters are hosted on public mxnet servers).
    https://mxnet.incubator.apache.org/api/python/gluon/model_zoo.html
    See examples/image_classification.pl for the example of real time image classification
    using a pretrained model from the ModelZoo

get_model

    Returns a pre-defined model by name

    Parameters
    ----------
    $name : Str
        Name of the model.
    :$pretrained : Bool
        Whether to load the pretrained weights for model.
    :$classes : Int
        Number of classes for the output layer.
    :$ctx : AI::MXNet::Context, default CPU
        The context in which to load the pretrained weights.
    :$root : Str, default '~/.mxnet/models'
        Location for keeping the model parameters.

    Returns
    -------
    HybridBlock
        The model.