o p iY@s$dZddlZddlZddlmZddlmZmZddlm Z m Z ddl m Z m Z ddlmZgZd Zd Zd Zd Zd ZdZdZdZdZddZeedZeedZ   d$ddZe dddddedddfddZe dddddedddfdd Z e dddddeddfd!dZ!d"d#Z"dS)%a This module will download dataset from http://www.robots.ox.ac.uk/~vgg/data/flowers/102/index.html and parse train/test dataset into paddle reader creators. This set contains images of flowers belonging to 102 different categories. The images were acquired by searching the web and taking pictures. There are a minimum of 40 images for each category. The database was used in: Nilsback, M-E. and Zisserman, A. Automated flower classification over a large number of classes.Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (2008) http://www.robots.ox.ac.uk/~vgg/publications/papers/nilsback08.{pdf,ps.gz}. N) cpu_count)load_image_bytessimple_transform) map_readers xmap_readers) deprecated try_import)downloadz8http://paddlemodels.bj.bcebos.com/flowers/102flowers.tgzz9http://paddlemodels.bj.bcebos.com/flowers/imagelabels.matz3http://paddlemodels.bj.bcebos.com/flowers/setid.matZ 52808999861908f626f3c1f4e79d11faZ e0620be6f572b9609742df49c70aed4dZ a5357ecc9cb78c4bef273ce3793fc85cZtstidZtrnidvalidcCs8|\}}t|}t|dd|gdd}|d|fS)zB map image bytes data to type needed by model input layer )g\(Y@gR1]@gQ^@)meanZfloat32)rrflattenZastype)Zis_trainsampleimglabelr]/home/app/PaddleOCR-VL/.venv_paddleocr/lib/python3.10/site-packages/paddle/dataset/flowers.pydefault_mapper:s rTFc s6fdd}|rt||tdt|St||S)a 1. read images from tar file and merge images into batch files in 102flowers.tgz_batch/ 2. get a reader to read sample from batch file :param data_file: downloaded data file :type data_file: string :param label_file: downloaded label file :type label_file: string :param setid_file: downloaded setid file containing information about how to split dataset :type setid_file: string :param dataset_name: data set name (tstid|trnid|valid) :type dataset_name: string :param mapper: a function to map image bytes data to type needed by model input layer :type mapper: callable :param buffered_size: the size of buffer used to process images :type buffered_size: int :param cycle: whether to cycle through the dataset :type cycle: bool :return: data reader :rtype: callable c 3std}|dd}|d}i}|D]}d|dd}||d||<qt}|}d}|D]} | j|vrV|| } || j} | t| dfVq:dS)Nzscipy.iolabelsrz jpg/image_Z05z.jpgr ) rZloadmattarfileopen getmembersname extractfilereadint) ZsciorZindexesZ img2labelirtfZmemsZfile_idZmemimager data_file dataset_name label_file setid_filerrreaderms$   zreader_creator..reader)rminrr) r#r%r&r$mapper buffered_sizeuse_xmapcycler'rr"rreader_creatorJs# r.z2.0.0zpaddle.vision.datasets.Flowersz>Please use new dataset API which supports paddle.io.DataLoader)ZsinceZ update_tolevelreasonc C0tttdtttdtttdtt||||dS)a8 Create flowers training set reader. It returns a reader, each sample in the reader is image pixels in [0, 1] and label in [1, 102] translated from original color image by steps: 1. resize to 256*256 2. random crop to 224*224 3. flatten :param mapper: a function to map sample. :type mapper: callable :param buffered_size: the size of buffer used to process images :type buffered_size: int :param cycle: whether to cycle through the dataset :type cycle: bool :return: train data reader :rtype: callable flowersr-) r.r DATA_URLDATA_MD5 LABEL_URL LABEL_MD5 SETID_URL SETID_MD5 TRAIN_FLAGr*r+r,r-rrrtrain   r<c Cr1)a3 Create flowers test set reader. It returns a reader, each sample in the reader is image pixels in [0, 1] and label in [1, 102] translated from original color image by steps: 1. resize to 256*256 2. random crop to 224*224 3. flatten :param mapper: a function to map sample. :type mapper: callable :param buffered_size: the size of buffer used to process images :type buffered_size: int :param cycle: whether to cycle through the dataset :type cycle: bool :return: test data reader :rtype: callable r2r3) r.r r4r5r6r7r8r9 TEST_FLAGr;rrrtestr=r?cCs,tttdtttdtttdtt|||S)a Create flowers validation set reader. It returns a reader, each sample in the reader is image pixels in [0, 1] and label in [1, 102] translated from original color image by steps: 1. resize to 256*256 2. random crop to 224*224 3. flatten :param mapper: a function to map sample. :type mapper: callable :param buffered_size: the size of buffer used to process images :type buffered_size: int :return: test data reader :rtype: callable r2) r.r r4r5r6r7r8r9 VALID_FLAG)r*r+r,rrrr s   cCs(ttdtttdtttdtdS)Nr2)r r4r5r6r7r8r9rrrrfetchs  rA)rTF)#__doc__ functoolsrmultiprocessingrZpaddle.dataset.imagerrZ paddle.readerrrZ paddle.utilsrrcommonr __all__r4r6r8r5r7r9r:r>r@rpartialZ train_mapperZ test_mapperr.r<r?r rArrrrs^      =