/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-rocal/checkouts/docs-6.1.1/rocAL_pybind/amd/rocal/readers.py File Reference

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-rocal/checkouts/docs-6.1.1/rocAL_pybind/amd/rocal/readers.py File Reference#

rocAL: /home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-rocal/checkouts/docs-6.1.1/rocAL_pybind/amd/rocal/readers.py File Reference

File containing reader functions for multiple datasets and data formats. More...

Functions
def	rocAL_pybind.amd.rocal.readers.coco (annotations_file='', ltrb=True, masks=False, ratio=False, avoid_class_remapping=False, pixelwise_masks=False, is_box_encoder=False, is_box_iou_matcher=False, aspect_ratio_grouping=False, stick_to_shard=False, pad_last_batch=False)
	Creates a COCOReader node. More...

def	rocAL_pybind.amd.rocal.readers.file (file_root, file_filters=None, file_list='', stick_to_shard=False, pad_last_batch=False)
	Creates a labelReader node for reading files from folder or file_list. More...

def	rocAL_pybind.amd.rocal.readers.tfrecord (path, user_feature_key_map, features, reader_type=0, stick_to_shard=False, pad_last_batch=False)
	Creates a TFRecordReader node for loading TFRecord dataset. More...

def	rocAL_pybind.amd.rocal.readers.caffe (path, bbox=False, stick_to_shard=False, pad_last_batch=False)
	Creates a CaffeReader node for loading Caffe dataset. More...

def	rocAL_pybind.amd.rocal.readers.caffe2 (path, bbox=False, stick_to_shard=False, pad_last_batch=False)
	Creates a Caffe2Reader node for loading Caffe2 dataset. More...

def	rocAL_pybind.amd.rocal.readers.video (sequence_length, file_list_frame_num=False, file_root="", image_type=types.RGB, num_shards=1, random_shuffle=False, step=1, stride=1, decoder_mode=types.SOFTWARE_DECODE, enable_frame_num=False, enable_timestamps=False, file_list="", stick_to_shard=False, pad_last_batch=False, file_list_include_preceding_frame=False, normalized=False, skip_vfr_check=False)
	Creates a VideoDecoder node for loading video sequences. More...

def	rocAL_pybind.amd.rocal.readers.video_resize (sequence_length, resize_width, resize_height, file_list_frame_num=False, file_root="", image_type=types.RGB, num_shards=1, random_shuffle=False, step=3, stride=3, decoder_mode=types.SOFTWARE_DECODE, scaling_mode=types.SCALING_MODE_DEFAULT, interpolation_type=types.LINEAR_INTERPOLATION, resize_longer=0, resize_shorter=0, max_size=[], enable_frame_num=False, enable_timestamps=False, file_list="", stick_to_shard=False, pad_last_batch=False, file_list_include_preceding_frame=False, normalized=False, skip_vfr_check=False)
	Creates a VideoDecoderResize node in the pipeline for loading and resizing video sequences. More...

def	rocAL_pybind.amd.rocal.readers.sequence_reader (file_root, sequence_length, image_type=types.RGB, num_shards=1, random_shuffle=False, step=3, stride=1, stick_to_shard=False, pad_last_batch=False)
	Creates a SequenceReader node for loading image sequences. More...

def	rocAL_pybind.amd.rocal.readers.mxnet (path, stick_to_shard=False, pad_last_batch=False)
	Creates an MXNETReader node for reading data from MXNet record files. More...

Detailed Description

File containing reader functions for multiple datasets and data formats.

Function Documentation

◆ caffe()

def rocAL_pybind.amd.rocal.readers.caffe	(	path,
		bbox = `False`,
		stick_to_shard = `False`,
		pad_last_batch = `False`
	)

Creates a CaffeReader node for loading Caffe dataset.

    @param path              Path to the Caffe dataset.
    @param bbox              Type of reader (False for classification, True for detection).
    @param stick_to_shard    Determines whether the reader should stick to a data shard instead of going through the entire dataset
    @param pad_last_batch    If set to True, pads the shard by repeating the last sample.

    @return    caffe reader meta data, bboxes, and labels.

◆ caffe2()

def rocAL_pybind.amd.rocal.readers.caffe2	(	path,
		bbox = `False`,
		stick_to_shard = `False`,
		pad_last_batch = `False`
	)

Creates a Caffe2Reader node for loading Caffe2 dataset.

    @param path              Path to the Caffe2 dataset.
    @param bbox              Type of reader (False for classification, True for detection).
    @param stick_to_shard    Determines whether the reader should stick to a data shard instead of going through the entire dataset.
    @param pad_last_batch    If set to True, pads the shard by repeating the last sample.

    @return    caffe2 reader meta data, bboxes, and labels.

◆ coco()

def rocAL_pybind.amd.rocal.readers.coco	(	annotations_file = `''`,
		ltrb = `True`,
		masks = `False`,
		ratio = `False`,
		avoid_class_remapping = `False`,
		pixelwise_masks = `False`,
		is_box_encoder = `False`,
		is_box_iou_matcher = `False`,
		aspect_ratio_grouping = `False`,
		stick_to_shard = `False`,
		pad_last_batch = `False`
	)

Creates a COCOReader node.

    @param annotations_file         Path to the COCO annotations file.
    @param ltrb                     Whether bounding box coordinates are provided in (left, top, right, bottom) format.
    @param masks                    Whether to read polygon masks from COCO annotations.
    @param ratio                    Whether bounding box coordinates are provided in normalized format.
    @param avoid_class_remapping    Specifies if class remapping should be avoided.
    @param pixelwise_masks          Whether to read mask data and generate pixel-wise masks.
    @param is_box_encoder           Whether to enable box encoder in the pipeline.
    @param is_box_iou_matcher       Whether to enable box IOU matcher in the pipeline.
    @param aspect_ratio_grouping    Whether to enable aspect ratio grouping in the pipeline.
    @param stick_to_shard           Determines whether the reader should stick to a data shard instead of going through the entire dataset.
    @param pad_last_batch           If set to True, pads the shard by repeating the last sample.

    @return    meta data, labels, and bounding boxes.

◆ file()

def rocAL_pybind.amd.rocal.readers.file	(	file_root,
		file_filters = `None`,
		file_list = `''`,
		stick_to_shard = `False`,
		pad_last_batch = `False`
	)

Creates a labelReader node for reading files from folder or file_list.

    @param file_root         Path to a directory that contains the data files.
    @param file_filters      A list of glob strings to filter the list of files in the sub-directories of the file_root.
    @param file_list         Path to a text file that contains one whitespace-separated filename label pair per line. The filenames are relative to the location of that file or to file_root, if specified.
    @param stick_to_shard    Determines whether the reader should stick to a data shard instead of going through the entire dataset.
    @param pad_last_batch    If set to True, pads the shard by repeating the last sample.

    @return    label reader meta data and labels.

◆ mxnet()

def rocAL_pybind.amd.rocal.readers.mxnet	(	path,
		stick_to_shard = `False`,
		pad_last_batch = `False`
	)

Creates an MXNETReader node for reading data from MXNet record files.

    @param path              Path to the MXNet record files.
    @param stick_to_shard    Determines whether the reader should stick to a data shard instead of going through the entire dataset.
    @param pad_last_batch    If set to True, pads the shard by repeating the last sample.

    @return    Metadata and loaded data from the MXNet record file.

◆ sequence_reader()

def rocAL_pybind.amd.rocal.readers.sequence_reader	(	file_root,
		sequence_length,
		image_type = `types.RGB`,
		num_shards = `1`,
		random_shuffle = `False`,
		step = `3`,
		stride = `1`,
		stick_to_shard = `False`,
		pad_last_batch = `False`
	)

Creates a SequenceReader node for loading image sequences.

    @param file_root            Root directory containing image sequences.
    @param sequence_length      Number of frames in each sequence.
    @param image_type           Color format of the frames.
    @param num_shards           Number of shards for data parallelism.
    @param random_shuffle       Specifies if frames should be randomly shuffled.
    @param step                 Distance between first frames of consecutive sequences.
    @param stride               Distance between consecutive frames in a sequence.
    @param stick_to_shard       Determines whether the reader should stick to a data shard instead of going through the entire dataset.
    @param pad_last_batch       If set to True, pads the shard by repeating the last sample.

    @return    list of loaded image sequences.

◆ tfrecord()

def rocAL_pybind.amd.rocal.readers.tfrecord	(	path,
		user_feature_key_map,
		features,
		reader_type = `0`,
		stick_to_shard = `False`,
		pad_last_batch = `False`
	)

Creates a TFRecordReader node for loading TFRecord dataset.

    @param path                    Path to the TFRecord dataset.
    @param user_feature_key_map    User-provided feature key mapping.
    @param features                Features to load from TFRecords.
    @param reader_type             Type of reader (0 for classification, 1 for detection).
    @param stick_to_shard          Determines whether the reader should stick to a data shard instead of going through the entire dataset.
    @param pad_last_batch          If set to True, pads the shard by repeating the last sample.

    @return    Features loaded from TFRecords.

◆ video()

def rocAL_pybind.amd.rocal.readers.video	(	sequence_length,
		file_list_frame_num = `False`,
		file_root = `""`,
		image_type = `types.RGB`,
		num_shards = `1`,
		random_shuffle = `False`,
		step = `1`,
		stride = `1`,
		decoder_mode = `types.SOFTWARE_DECODE`,
		enable_frame_num = `False`,
		enable_timestamps = `False`,
		file_list = `""`,
		stick_to_shard = `False`,
		pad_last_batch = `False`,
		file_list_include_preceding_frame = `False`,
		normalized = `False`,
		skip_vfr_check = `False`
	)

Creates a VideoDecoder node for loading video sequences.

    @param sequence_length                      Number of frames in video sequence.
    @param file_list_frame_num                  Specifies whether file list includes frame numbers.
    @param file_root                            Root directory containing video files.
    @param image_type                           Color format of the frames.
    @param num_shards                           Number of shards for data parallelism.
    @param random_shuffle                       Specifies if frames should be randomly shuffled.
    @param step                                 Distance between first frames of consecutive sequences.
    @param stride                               Distance between consecutive frames in a sequence.
    @param decoder_mode                         Device used for video decoding.
    @param enable_frame_num                     Specifies whether frame numbers are enabled.
    @param enable_timestamps                    Specifies whether timestamps are enabled.
    @param file_list                            List of video files.
    @param stick_to_shard                       Determines whether the reader should stick to a data shard instead of going through the entire dataset.
    @param pad_last_batch                       If set to True, pads the shard by repeating the last sample.
    @param file_list_include_preceding_frame    Changes the behavior how file_list start and end frame timestamps are translated to a frame number.
    @param normalized                           Gets the output as normalized data.
    @param skip_vfr_check                       Skips the check for the variable frame rate (VFR) videos.

    @return   list of loaded video sequences.

◆ video_resize()

def rocAL_pybind.amd.rocal.readers.video_resize	(	sequence_length,
		resize_width,
		resize_height,
		file_list_frame_num = `False`,
		file_root = `""`,
		image_type = `types.RGB`,
		num_shards = `1`,
		random_shuffle = `False`,
		step = `3`,
		stride = `3`,
		decoder_mode = `types.SOFTWARE_DECODE`,
		scaling_mode = `types.SCALING_MODE_DEFAULT`,
		interpolation_type = `types.LINEAR_INTERPOLATION`,
		resize_longer = `0`,
		resize_shorter = `0`,
		max_size = `[]`,
		enable_frame_num = `False`,
		enable_timestamps = `False`,
		file_list = `""`,
		stick_to_shard = `False`,
		pad_last_batch = `False`,
		file_list_include_preceding_frame = `False`,
		normalized = `False`,
		skip_vfr_check = `False`
	)

Creates a VideoDecoderResize node in the pipeline for loading and resizing video sequences.

@param sequence_length Number of frames in video sequence.
@param resize_width output width for resizing.
@param resize_height output height for resizing.
@param file_list_frame_num Specifies whether file list includes frame numbers.
@param file_root Root directory containing video files.
@param image_type Color format of the frames.
@param num_shards Number of shards for data parallelism.
@param random_shuffle Specifies if frames should be randomly shuffled.
@param step Distance between first frames of consecutive sequences.
@param stride Distance between consecutive frames in a sequence.
@param decoder_mode Device used for video decoding.
@param scaling_mode Scaling mode for resizing.
@param interpolation_type Interpolation type for resizing.
@param resize_longer Target size for the longer dimension during resizing.
@param resize_shorter Target size for the shorter dimension during resizing.
@param max_size Maximum size for resizing.
@param enable_frame_num Specifies whether frame numbers are enabled.
@param enable_timestamps Specifies whether timestamps are enabled.
@param file_list List of video files.
@param stick_to_shard Determines whether the reader should stick to a data shard instead of going through the entire dataset.
@param pad_last_batch If set to True, pads the shard by repeating the last sample.
@param file_list_include_preceding_frame Specifies if file list includes preceding frames.
@param normalized Gets the output as normalized data.
@param skip_vfr_check Skips the check for the variable frame rate (VFR) videos.

@returns loaded and resized video sequences and meta data.