AI-MXNet
view release on metacpan or search on metacpan
lib/AI/MXNet/Image.pm view on Meta::CPAN
AI::MXNet::NDArray $src
Shape $size
Num $min_area
ArrayRef[Int] [$from, $to] # $ratio
Maybe[Int] $interp=2
Returns:
--------
($cropped_image, [$x0, $y0, $new_w, $new_h])
=cut
method random_size_crop(AI::MXNet::NDArray $src, Shape $size, Num $min_area, ArrayRef[Num] $ratio, Maybe[Int] $interp=2)
{
my ($h, $w) = @{ $src->shape };
my ($from, $to) = @{ $ratio };
my $new_ratio = $from + ($to-$from) * rand;
my $max_area;
if($new_ratio * $h > $w)
{
$max_area = $w*int($w/$new_ratio);
}
else
{
$max_area = $h*int($h*$new_ratio);
}
$min_area *= $h*$w;
if($max_area < $min_area)
{
return __PACKAGE__->random_crop($src, $size, $interp);
}
my $new_area = $min_area + ($max_area-$min_area) * rand;
my $new_w = int(sqrt($new_area*$new_ratio));
my $new_h = $new_w;
assert($new_w <= $w and $new_h <= $h);
my $x0 = int(rand($w - $new_w + 1));
my $y0 = int(rand($h - $new_h + 1));
my $out = __PACKAGE__->fixed_crop($src, $x0, $y0, $new_w, $new_h, $size, $interp);
return ($out, [$x0, $y0, $new_w, $new_h]);
}
=head2 ResizeAug
Makes "resize shorter edge to size augumenter" closure.
Parameters:
-----------
Shape $size
Int $interp=2
Returns:
--------
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns [__PACKAGE__->resize_short($src, $size, $interp)]
=cut
method ResizeAug(Shape $size, Int $interp=2)
{
my $aug = sub {
my $src = shift;
return [__PACKAGE__->resize_short($src, $size, $interp)];
};
return $aug;
}
=head2 RandomCropAug
Makes "random crop augumenter" closure.
Parameters:
-----------
Shape $size
Int $interp=2
Returns:
--------
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns [(__PACKAGE__->random_crop($src, $size, $interp))[0]]
=cut
method RandomCropAug(Shape $size, Int $interp=2)
{
my $aug = sub {
my $src = shift;
return [(__PACKAGE__->random_crop($src, $size, $interp))[0]];
};
return $aug;
}
=head2 RandomSizedCropAug
Makes "random crop augumenter" closure.
Parameters:
-----------
Shape $size
Num $min_area
ArrayRef[Num] $ratio
Int $interp=2
Returns:
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns [(__PACKAGE__->random_size_crop($src, $size, $min_area, $ratio, $interp))[0]]
=cut
method RandomSizedCropAug(Shape $size, Num $min_area, ArrayRef[Num] $ratio, Int $interp=2)
{
my $aug = sub {
my $src = shift;
return [(__PACKAGE__->random_size_crop($src, $size, $min_area, $ratio, $interp))[0]];
};
return $aug;
}
=head2 CenterCropAug
Makes "center crop augumenter" closure.
Parameters:
-----------
Shape $size
Int $interp=2
Returns:
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns [(__PACKAGE__->center_crop($src, $size, $interp))[0]]
=cut
method CenterCropAug(Shape $size, Int $interp=2)
{
my $aug = sub {
my $src = shift;
return [(__PACKAGE__->center_crop($src, $size, $interp))[0]];
};
return $aug;
}
=head2 RandomOrderAug
Makes "Apply list of augmenters in random order" closure.
Parameters:
-----------
ArrayRef[CodeRef] $ts
Returns:
--------
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns ArrayRef[AI::MXNet::NDArray]
=cut
method RandomOrderAug(ArrayRef[CodeRef] $ts)
{
my $aug = sub {
my $src = shift;
my @ts = List::Util::shuffle(@{ $ts });
my @tmp;
for my $t (@ts)
{
push @tmp, &{$t}($src);
}
return \@tmp;
};
return $aug;
}
=head2 RandomOrderAug
Makes "Apply random brightness, contrast and saturation jitter in random order" closure
Parameters:
-----------
Num $brightness
Num $contrast
Num $saturation
Returns:
--------
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns ArrayRef[AI::MXNet::NDArray]
=cut
method ColorJitterAug(Num $brightness, Num $contrast, Num $saturation)
{
my @ts;
my $coef = AI::MXNet::NDArray->array([[[0.299, 0.587, 0.114]]]);
if($brightness > 0)
{
my $baug = sub { my $src = shift;
my $alpha = 1 + -$brightness + 2 * $brightness * rand;
$src *= $alpha;
return [$src];
};
push @ts, $baug;
}
if($contrast > 0)
{
my $caug = sub { my $src = shift;
my $alpha = 1 + -$contrast + 2 * $contrast * rand;
my $gray = $src*$coef;
$gray = (3.0*(1.0-$alpha)/$gray->size)*$gray->sum;
$src *= $alpha;
$src += $gray;
return [$src];
};
push @ts, $caug;
}
if($saturation > 0)
{
my $saug = sub { my $src = shift;
my $alpha = 1 + -$saturation + 2 * $saturation * rand;
my $gray = $src*$coef;
$gray = AI::MXNet::NDArray->sum($gray, { axis=>2, keepdims =>1 });
$gray *= (1.0-$alpha);
$src *= $alpha;
$src += $gray;
return [$src];
};
push @ts, $saug;
}
return __PACKAGE__->RandomOrderAug(\@ts);
}
=head2 LightingAug
Makes "Add PCA based noise" closure.
Parameters:
-----------
Num $alphastd
PDL $eigval
PDL $eigvec
Returns:
--------
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns ArrayRef[AI::MXNet::NDArray]
=cut
method LightingAug(Num $alphastd, PDL $eigval, PDL $eigvec)
{
my $aug = sub { my $src = shift;
my $alpha = AI::MXNet::NDArray->zeros([3]);
AI::MXNet::Random->normal(0, $alphastd, { out => $alpha });
my $rgb = ($eigvec*$alpha->aspdl) x $eigval;
$src += AI::MXNet::NDArray->array($rgb);
return [$src]
};
return $aug
}
=head2 ColorNormalizeAug
Makes "Mean and std normalization" closure.
Parameters:
-----------
PDL $mean
PDL $std
Returns:
--------
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns [__PACKAGE__->color_normalize($src, $mean, $std)]
=cut
method ColorNormalizeAug(PDL $mean, PDL $std)
{
$mean = AI::MXNet::NDArray->array($mean);
$std = AI::MXNet::NDArray->array($std);
my $aug = sub { my $src = shift;
return [__PACKAGE__->color_normalize($src, $mean, $std)]
};
return $aug;
}
=head2 HorizontalFlipAug
Makes "Random horizontal flipping" closure.
Parameters:
-----------
Num $p < 1
Returns:
--------
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns [$p > rand ? AI::MXNet::NDArray->flip($src, axis=1>) : $src]
=cut
method HorizontalFlipAug(Num $p)
{
my $aug = sub { my $src = shift;
return [$p > rand() ? AI::MXNet::NDArray->flip($src, { axis=>1 }) : $src]
};
return $aug;
}
=head2 CastAug
Makes "Cast to float32" closure.
Returns:
--------
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns [$src->astype('float32')]
=cut
method CastAug()
{
my $aug = sub { my $src = shift;
return [$src->astype('float32')]
};
return $aug;
}
=head2 CreateAugmenter
Create augumenter list
Parameters:
-----------
Shape :$data_shape,
Bool :$resize=0,
Bool :$rand_crop=0,
Bool :$rand_resize=0,
Bool :$rand_mirror=0,
Maybe[Num|PDL] :$mean=,
Maybe[Num|PDL] :$std=,
Num :$brightness=0,
Num :$contrast=0,
Num :$saturation=0,
Num :$pca_noise=0,
Int :$inter_method=2
=cut
method CreateAugmenter(
Shape :$data_shape,
Bool :$resize=0,
Bool :$rand_crop=0,
Bool :$rand_resize=0,
Bool :$rand_mirror=0,
Maybe[Num|PDL] :$mean=,
Maybe[Num|PDL] :$std=,
Num :$brightness=0,
Num :$contrast=0,
Num :$saturation=0,
Num :$pca_noise=0,
Int :$inter_method=2
)
{
my @auglist;
if($resize > 0)
{
push @auglist, __PACKAGE__->ResizeAug($resize, $inter_method);
}
my $crop_size = [$data_shape->[2], $data_shape->[1]];
if($rand_resize)
{
assert($rand_crop);
push @auglist, __PACKAGE__->RandomSizedCropAug($crop_size, 0.3, [3.0/4.0, 4.0/3.0], $inter_method);
}
elsif($rand_crop)
{
push @auglist, __PACKAGE__->RandomCropAug($crop_size, $inter_method);
}
else
{
push @auglist, __PACKAGE__->CenterCropAug($crop_size, $inter_method);
}
lib/AI/MXNet/Image.pm view on Meta::CPAN
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;
}
}
$self->imglist(\%result);
( run in 0.531 second using v1.01-cache-2.11-cpan-39bf76dae61 )