NAME
AI::MXNet:Image - Read individual image files and perform augmentations.imdecode
Decode an image from string. Requires OpenCV to work.
Parameters
----------
$buf : str, array ref, pdl, ndarray
Binary image data.
:$flag : int
0 for grayscale. 1 for colored.
:$to_rgb : int
0 for BGR format (OpenCV default). 1 for RGB format (MXNet default).
:$out : NDArray
Output buffer. Do not specify for automatic allocation.scale_down
Scale down crop size if it's bigger than the image size.
Parameters:
-----------
Shape $src_size
Shape $size
Returns:
--------
($w, $h)resize_short
Resize shorter edge to the size.
Parameters:
-----------
AI::MXNet::NDArray $src
Int $size
Int $interp=2
Returns:
--------
AI::MXNet::NDArray $resized_imagefixed_crop
Crop src at fixed location, and (optionally) resize it to the size.
Parameters:
-----------
AI::MXNet::NDArray $src
Int $x0
Int $y0
Int $w
Int $h
Maybe[Shape] $size=
Int $interp=2
Returns:
--------
AI::MXNet::NDArray $cropped_imagerandom_crop
Randomly crop src with size. Upsample result if src is smaller than the size.
Parameters:
-----------
AI::MXNet::NDArray $src
Shape $size=
Int $interp=2
Returns:
--------
($cropped_image, [$x0, $y0, $new_w, $new_h])center_crop
Randomly crop src with size around the center. Upsample result if src is smaller than the size.
Parameters:
-----------
AI::MXNet::NDArray $src
Shape $size=
Int $interp=2
Returns:
--------
($cropped_image, [$x0, $y0, $new_w, $new_h])color_normalize
Normalize src with mean and std.
Parameters:
-----------
AI::MXNet::NDArray $src
Num|AI::MXNet::NDArray $mean
Maybe[Num|AI::MXNet::NDArray] $std=
Int $interp=2
Returns:
--------
AI::MXNet::NDArray $normalized_imagerandom_size_crop
Randomly crop src with size. Randomize area and aspect ratio.
Parameters:
-----------
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])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)]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]]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]]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]]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]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]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]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)]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]CastAug
Makes "Cast to float32" closure.
Returns:
--------
CodeRef that accepts AI::MXNet::NDArray $src as input
and returns [$src->astype('float32')]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=2NAME
AI::MXNet::ImageIter - Image data iterator.DESCRIPTION
Image data iterator with a large number of augumentation choices.
Supports reading from both .rec files and raw image files with image list.
To load from .rec files, please specify path_imgrec. Also specify path_imgidx
to use data partition (for distributed training) or shuffling.
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