view release on metacpan or  search on metacpan

lib/AI/MXNet/Image.pm  view on Meta::CPAN

    To load from raw image files, specify path_imglist and path_root.

    Parameters
    ----------
    batch_size : Int
        Number of examples per batch
    data_shape : Shape
        Data shape in (channels, height, width).
        For now, only RGB image with 3 channels is supported.
    label_width : Int
        dimension of label
    path_imgrec : str
        path to image record file (.rec).
        Created with tools/im2rec.py or bin/im2rec
    path_imglist : str
        path to image list (.lst)
        Created with tools/im2rec.py or with custom script.
        Format: index\t[one or more label separated by \t]\trelative_path_from_root
    imglist: array ref
        a list of image with the label(s)
        each item is a list [imagelabel: float or array ref of float, imgpath]
    path_root : str
        Root folder of image files
    path_imgidx : str
        Path to image index file. Needed for partition and shuffling when using .rec source.
    shuffle : bool
        Whether to shuffle all images at the start of each iteration.
    Can be slow for HDD.
    part_index : int
        Partition index
    num_parts : int
        Total number of partitions.
    data_name='data' Str
    label_name='softmax_label' Str
    kwargs : hash ref with any additional arguments for augmenters
=cut

has 'batch_size'  => (is => 'ro', isa => 'Int',   required => 1);
has 'data_shape'  => (is => 'ro', isa => 'Shape', required => 1);
has 'label_width' => (is => 'ro', isa => 'Int',   default  => 1);
has 'data_name'   => (is => 'ro', isa => 'Str',   default  => 'data');
has 'label_name'  => (is => 'ro', isa => 'Str',   default  => 'softmax_label');
has [qw/path_imgrec
        path_imglist
        path_root
        path_imgidx
    /]            => (is => 'ro', isa => 'Str');
has 'shuffle'     => (is => 'ro', isa => 'Bool', default => 0);
has 'part_index'  => (is => 'ro', isa => 'Int', default => 0);
has 'num_parts'   => (is => 'ro', isa => 'Int', default => 0);
has 'aug_list'    => (is => 'rw', isa => 'ArrayRef[CodeRef]');
has 'imglist'     => (is => 'rw', isa => 'ArrayRef|HashRef');
has 'kwargs'      => (is => 'ro', isa => 'HashRef');
has [qw/imgidx
        imgrec
        seq
        cur
        provide_data
        provide_label
           /]     => (is => 'rw', init_arg => undef);

sub BUILD
{
    my $self = shift;
    assert($self->path_imgrec or $self->path_imglist or ref $self->imglist eq 'ARRAY');
    if($self->path_imgrec)
    {
        print("loading recordio...\n");
        if($self->path_imgidx)
        {
            $self->imgrec(
                AI::MXNet::IndexedRecordIO->new(
                    idx_path => $self->path_imgidx,
                    uri => $self->path_imgrec,
                    flag => 'r'
                )
            );
            $self->imgidx([@{ $self->imgrec->keys }]);
        }
        else
        {
            $self->imgrec(AI::MXNet::RecordIO->new(uri => $self->path_imgrec, flag => 'r'));
        }
    }
    my %imglist;
    my @imgkeys;
    if($self->path_imglist)
    {
        print("loading image list...\n");
        open(my $f, $self->path_imglist) or confess("can't open ${\ $self->path_imglist } : $!");
        while(my $line = <$f>)
        {
            chomp($line);
            my @line = split(/\t/, $line);
            my $label = AI::MXNet::NDArray->array([@line[1..@line-2]]);
            my $key   = $line[0];
            $imglist{$key} = [$label, $line[-1]];
            push @imgkeys, $key;
        }
        $self->imglist(\%imglist);
    }
    elsif(ref $self->imglist eq 'ARRAY')
    {
        print("loading image list...\n");
        my %result;
        my $index = 1;
        for my $img (@{ $self->imglist })
        {
            my $key = $index++;
            my $label;
            if(not ref $img->[0])
            {
                $label = AI::MXNet::NDArray->array([$img->[0]]);
            }
            else
            {
                $label = AI::MXNet::NDArray->array($img->[0]);
                $result{$key} = [$label, $img->[1]];
                push @imgkeys, $key;
            }

lib/AI/MXNet/Image.pm  view on Meta::CPAN

            AI::MXNet::DataDesc->new(
                name  => $self->label_name,
                shape => [$self->batch_size, $self->label_width]
            )
        ]);
    }
    else
    {
        $self->provide_label([
            AI::MXNet::DataDesc->new(
                name  => $self->label_name,
                shape => [$self->batch_size]
            )
        ]);
    }
    if(not defined $self->imgrec)
    {
        $self->seq(\@imgkeys);
    }
    elsif($self->shuffle or $self->num_parts > 1)
    {
        assert(defined $self->imgidx);
        $self->seq($self->imgidx);
    }
    if($self->num_parts > 1)
    {
        assert($self->part_index < $self->num_parts);
        my $N = @{ $self->seq };
        my $C = $N/$self->num_parts;
        $self->seq([@{ $self->seq }[$self->part_index*$C..($self->part_index+1)*$C-1]]);
    }
    if(defined $self->aug_list or defined $self->kwargs)
    {
        $self->aug_list(AI::MXNet::Image->CreateAugmenter(data_shape => $self->data_shape, %{ $self->kwargs//{} }));
    }
    else
    {
        $self->aug_list([]);
    }
    $self->cur(0);
    $self->reset();
}

method reset()
{
    if($self->shuffle)
    {
        @{ $self->seq } = List::Util::shuffle(@{ $self->seq });
    }
    if(defined $self->imgrec)
    {
        $self->imgrec->reset;
    }
    $self->cur(0);
}

method next_sample()
{
    if(defined $self->seq)
    {
        return undef if($self->cur >= @{ $self->seq });
        my $idx = $self->seq->[$self->cur];
        $self->cur($self->cur + 1);
        if(defined $self->imgrec)
        {
            my $s = $self->imgrec->read_idx($idx);
            my ($header, $img) = AI::MXNet::RecordIO->unpack($s);
            if(not defined $self->imglist)
            {
                return ($header->label, $img);
            }
            else
            {
                return ($self->imglist->{$idx}[0], $img);
            }
        }
        else
        {
            my ($label, $fname) = @{ $self->imglist->{$idx} };
            if(not defined $self->imgrec)
            {
                open(F, $self->path_root . "/$fname") or confess("can't open $fname $!");
                my $img;
                { local $/ = undef; $img = <F> };
                close(F);
                return ($label, $img);
            }
        }
    }
    else
    {
        my $s = $self->imgrec->read;
        return undef if(not defined $s);
        my ($header, $img) = AI::MXNet::RecordIO->unpack($s);
        return ($header->label, $img)
    }
}

method next()
{
    my $batch_size = $self->batch_size;
    my ($c, $h, $w) = @{ $self->data_shape };
    my $batch_data  = AI::MXNet::NDArray->empty([$batch_size, $c, $h, $w]);
    my $batch_label = AI::MXNet::NDArray->empty(@{$self->provide_label->[0]}[1]);
    my $i = 0;
    while ($i < $batch_size)
    {
        my ($label, $s) = $self->next_sample;
        last if not defined $label;
        my $data = [AI::MXNet::Image->imdecode($s)];
        if(@{ $data->[0]->shape } == 0)
        {
            AI::MXNet::Logging->debug('Invalid image, skipping.');
            next;
        }
        for my $aug (@{ $self->aug_list })
        {
            $data = [map { @{ $aug->($_) } } @$data];
        }
        for my $d (@$data)
        {
            assert(($i < $batch_size), 'Batch size must be multiples of augmenter output length');
            $batch_data->at($i)  .= AI::MXNet::NDArray->transpose($d, { axes=>[2, 0, 1] });
            $batch_label->at($i) .= $label;
            $i++;
        }
    }
    return undef if not $i;
    return AI::MXNet::DataBatch->new(data=>[$batch_data], label=>[$batch_label], pad => $batch_size-$i);
}

1;