a yµÿf‰Sã@sšddlZddlmZddlmZddlZddlZddlm Z m Z ddl m Z dd„Z dd „Zddd„Zdd„Zedœdd„Zdd„Zdd„Zddd„ZdS)éN)Ú defaultdict)ÚPath)ÚLOGGERÚTQDM)Úincrement_pathcCsgd¢S)zî Converts 91-index COCO class IDs to 80-index COCO class IDs. Returns: (list): A list of 91 class IDs where the index represents the 80-index class ID and the value is the corresponding 91-index class ID. )[rééééééééé é Né é é ééééééééééNééNNééééééé é!é"é#é$é%é&é'Né(é)é*é+é,é-é.é/é0é1é2é3é4é5é6é7é8é9é:é;Né<NNé=Né>é?é@éAéBéCéDéEéFéGéHNéIéJéKéLéMéNéON©rVrVrVúV/var/www/html/django/DPS/env/lib/python3.9/site-packages/ultralytics/data/converter.pyÚcoco91_to_coco80_classsrXcCsgd¢S)aD Converts 80-index (val2014) to 91-index (paper). For details see https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/. Example: ```python import numpy as np a = np.loadtxt("data/coco.names", dtype="str", delimiter="\n") b = np.loadtxt("data/coco_paper.names", dtype="str", delimiter="\n") x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet ``` )Prrr r r r r rrrrrrrrrrrrrrrrrr!r"r%r&r'r(r)r*r+r,r-r.r/r0r1r2r4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDrErFrGrIrLrNrOrPrQrRrSrTrUéPéQéRéTéUéVéWéXéYéZrVrVrVrVrWÚcoco80_to_coco91_classusrcú../coco/annotations/úcoco_converted/FTc CsØt|ƒ}|d|dfD]}|jdddqtƒ}tt|ƒ ¡ d¡ƒD]f}|rVdn |j dd¡} t|ƒd| } | jddd|rª| djddd| d jdddt |ƒ} t   | ¡} Wd ƒn1sÒ0Yd d „| dDƒ} t t ƒ}| d D]}||d |¡qþg}t| ¡d|›dD]\}}| |d›}|d|d}}|rttt|dƒ d¡ƒn|d} |r˜| ttdƒ| ƒ¡g}g}g}|D]ö}| dd¡rÀq¨tj|dtjd}|d d…|dd …d7<|ddg|<|ddg|<|ddks¨|ddkr<q¨|rR||d dn |d d}|g| ¡}||vr¨| |¡|rN| d!¡d urNt|d!ƒdkr¸| g¡q¨n‚t|d!ƒdkrþt|d!ƒ}tj|dd"t ||g¡ d#¡ ¡}n óz convert_coco..Ú annotationsZimage_idz Annotations ©ÚdescrmÚheightÚwidthZcoco_urlzhttp://images.cocodataset.orgÚ file_namez./imagesZiscrowdFZbbox)Zdtyperrrr Z category_idZ segmentation©ZaxiséÿÿÿÿcSsg|]}|D]}|‘q qSrVrV)rnÚiÚjrVrVrWÚ 5rqz convert_coco..Ú keypointsú.txtÚaú%g Ú Zlvis_v1_z.jsoncss|]}|›dVqdS©rNrV)rnÚlinerVrVrWÚ Krqzconvert_coco..ZLVISZCOCOz/ data converted successfully. Results saved to )$rÚmkdirrXÚsortedrÚresolveÚglobÚstemÚreplaceÚopenÚjsonÚloadrÚlistÚappendrÚitemsÚstrÚ relative_toÚgetÚnpÚarrayZfloat64ÚtolistÚlenÚmerge_multi_segmentÚ concatenateÚreshapeÚ with_suffixÚrangeÚwriteÚrstripÚnameÚ writelinesrÚinfo)Z labels_dirÚsave_dirZ use_segmentsZ use_keypointsZ cls91to80ZlvisÚpZcoco80Z json_fileÚlnameÚfnÚfÚdatargZ imgToAnnsÚannZ image_txtZimg_idÚannsÚimgÚhÚwÚbboxesÚsegmentsr}ÚboxÚclsÚsÚfilerzrƒrVrVrWÚ convert_cocoØs† (   $  "    (*  2ÿ&ÿF&6r³c CsÎdd„t|ƒDƒ}t|ƒ ¡D]¨}|jdkrt t|ƒtj¡}|j\}}t   d|›d|›d|›¡t   |¡}g} |D]È} | dkr†qx|  | d¡} | dkr´t  d | ›d |›d ¡qxt || k t j¡tjtj¡\} } | D]d}t|ƒd krÚ| ¡}| g}|D]6}| t|d|d ƒ¡| t|d|d ƒ¡qü|  |¡qÚqxt|ƒ|j›d}t|dƒ:}| D]$}d tt|ƒ¡}| |d¡qfWdƒn1s¢0Yt   d|›d|›d|›¡qdS)u÷ Converts a dataset of segmentation mask images to the YOLO segmentation format. This function takes the directory containing the binary format mask images and converts them into YOLO segmentation format. The converted masks are saved in the specified output directory. Args: masks_dir (str): The path to the directory where all mask images (png, jpg) are stored. output_dir (str): The path to the directory where the converted YOLO segmentation masks will be stored. classes (int): Total classes in the dataset i.e. for COCO classes=80 Example: ```python from ultralytics.data.converter import convert_segment_masks_to_yolo_seg # The classes here is the total classes in the dataset, for COCO dataset we have 80 classes convert_segment_masks_to_yolo_seg("path/to/masks_directory", "path/to/output/directory", classes=80) ``` Notes: The expected directory structure for the masks is: - masks ├─ mask_image_01.png or mask_image_01.jpg ├─ mask_image_02.png or mask_image_02.jpg ├─ mask_image_03.png or mask_image_03.jpg └─ mask_image_04.png or mask_image_04.jpg After execution, the labels will be organized in the following structure: - output_dir ├─ mask_yolo_01.txt ├─ mask_yolo_02.txt ├─ mask_yolo_03.txt └─ mask_yolo_04.txt cSsi|]}|d|“qS)rrV©rnrzrVrVrWrpurqz5convert_segment_masks_to_yolo_seg..ú.pngú Processing z imgsz = z x rryzUnknown class for pixel value z in file z , skipping.r r rr~r¬ú rNzProcessed and stored at )rœrÚiterdirÚsuffixÚcv2Úimreadr‘ZIMREAD_GRAYSCALEÚshaperr¡r”Úuniquer“ÚwarningZ findContoursZastypeZuint8Z RETR_EXTERNALZCHAIN_APPROX_SIMPLEr—ZsqueezerÚroundr‰r‹ÚjoinÚmapr)Z masks_dirÚ output_dirÚclassesZpixel_to_class_mappingZ mask_pathÚmaskZ img_heightZ img_widthZ unique_valuesZyolo_format_dataÚvalueZ class_indexZcontoursÚ_ZcontourZ yolo_formatÚpointZ output_pathr²ÚitemrƒrVrVrWÚ!convert_segment_masks_to_yolo_segPs@%    ÿ  2rÉ)Údota_root_pathc sìt|ƒ}ddddddddd d d d d ddddddœ‰‡fdd„}dD]¤}|d|}|d|›d}|d|}|jdddt| ¡ƒ}t|d|›ddD]F}|jdkr®qž|j}t t |ƒ¡} | j d d…\} } ||| | ||ƒqžqBd S)!u& Converts DOTA dataset annotations to YOLO OBB (Oriented Bounding Box) format. The function processes images in the 'train' and 'val' folders of the DOTA dataset. For each image, it reads the associated label from the original labels directory and writes new labels in YOLO OBB format to a new directory. Args: dota_root_path (str): The root directory path of the DOTA dataset. Example: ```python from ultralytics.data.converter import convert_dota_to_yolo_obb convert_dota_to_yolo_obb("path/to/DOTA") ``` Notes: The directory structure assumed for the DOTA dataset: - DOTA ├─ images │ ├─ train │ └─ val └─ labels ├─ train_original └─ val_original After execution, the function will organize the labels into: - DOTA └─ labels ├─ train └─ val rrrr r r r r rrrrrrrrrr)ZplaneÚshipz storage-tankzbaseball-diamondz tennis-courtzbasketball-courtzground-track-fieldZharborZbridgez large-vehiclez small-vehicleÚ helicopterZ roundaboutzsoccer-ball-fieldz swimming-poolzcontainer-craneZairportZhelipadc s ||›d}||›d}| d¡Ð}| d¡¦}| ¡} | D]ˆ} |  ¡ ¡} t| ƒdkr^q@| d} ˆ| } dd„| dd…Dƒ‰‡‡‡fd d„tdƒDƒ}d d„|Dƒ}| | ›d d  |¡›d ¡q@Wdƒn1sÞ0YWdƒn1sü0YdS) zcConverts a single image's DOTA annotation to YOLO OBB format and saves it to a specified directory.r~Úrr¬rrcSsg|] }t|ƒ‘qSrV)Úfloat)rnr£rVrVrWr|ærqzCconvert_dota_to_yolo_obb..convert_label..Ncs0g|](}|ddkr ˆ|ˆn ˆ|ˆ‘qS)rrrVr´©ZcoordsÚ image_heightÚ image_widthrVrWr|çscSsg|] }|d›‘qS)z.6grV)rnZcoordrVrVrWr|êrqr·r)r‹Ú readlinesÚstripÚsplitr—rœrrÀ)Z image_namerÑrÐÚorig_label_dirr¢Zorig_label_pathZ save_pathr¦ÚgÚlinesrƒÚpartsÚ class_nameZ class_idxZnormalized_coordsZformatted_coords©Z class_mappingrÏrWÚ convert_labelÙs   ÿz/convert_dota_to_yolo_obb..convert_label)ÚtrainÚvalrgrfZ _originalTrhr¶z imagesrsrµN) rr…rŽr¸rr¹r‰rºr»r‘r¼) rÊrÛZphaseZ image_dirrÕr¢Z image_pathsZ image_pathZimage_name_without_extrªr«r¬rVrÚrWÚconvert_dota_to_yolo_obbžsD#î     rÞcCsN|dd…ddd…f|ddd…dd…fd d¡}t tj|dd|j¡S)a“ Find a pair of indexes with the shortest distance between two arrays of 2D points. Args: arr1 (np.ndarray): A NumPy array of shape (N, 2) representing N 2D points. arr2 (np.ndarray): A NumPy array of shape (M, 2) representing M 2D points. Returns: (tuple): A tuple containing the indexes of the points with the shortest distance in arr1 and arr2 respectively. Nrryrx)Úsumr”Z unravel_indexZargminr¼)Zarr1Zarr2ÚdisrVrVrWÚ min_indexþs 6rác Csðg}dd„|Dƒ}dd„tt|ƒƒDƒ}tdt|ƒƒD]>}t||d||ƒ\}}||d |¡|| |¡q6tdƒD]j}|dkr†t|ƒD]ì\}}t|ƒdkræ|d|dkræ|ddd…}||ddd…dd…f||<tj|||d dd ||<t ||||dd…g¡||<|dt|ƒdhvrL| ||¡q–d|d|dg}| |||d|dd…¡q–q~tt|ƒdddƒD]N}|dt|ƒdhvrš||}t|d|dƒ}| |||d…¡qšq~|S) a Merge multiple segments into one list by connecting the coordinates with the minimum distance between each segment. This function connects these coordinates with a thin line to merge all segments into one. Args: segments (List[List]): Original segmentations in COCO's JSON file. Each element is a list of coordinates, like [segmentation1, segmentation2,...]. Returns: s (List[np.ndarray]): A list of connected segments represented as NumPy arrays. cSsg|]}t |¡ dd¡‘qS)ryr)r”r•ršr´rVrVrWr|rqz'merge_multi_segment..cSsg|]}g‘qSrVrV)rnrÆrVrVrWr|rqrrrNryrx) rœr—rárÚ enumerater”Zrollr™Úabs) r®r±Zidx_listrzZidx1Zidx2ÚkÚidxZnidxrVrVrWr˜ s2  "&r˜úsam_b.ptc Cs:ddlm}ddlm}ddlm}ddlm}ddlm}||t t t dƒƒdd }t |j dd ƒdkrz| d ¡d S| d ¡||ƒ}||j t |j ƒddD]} | d\} } | d} t | ƒdkrÈq¢| d d …ddgf| 9<| d d …ddgf| 9<t | d¡} || || ƒddd}|djj| d <q¢|rBt|ƒn t|ƒjd}|jddd|j D]À} g}t| dƒ d¡j}||}| d}t| d ƒD]>\}}t||ƒg| d¡¢R}| dt |ƒ ¡|¡qœ|rdt|dƒ$}| d d!„|Dƒ¡Wd ƒn1s0Yqd| d"|›¡d S)#ud Converts existing object detection dataset (bounding boxes) to segmentation dataset or oriented bounding box (OBB) in YOLO format. Generates segmentation data using SAM auto-annotator as needed. Args: im_dir (str | Path): Path to image directory to convert. save_dir (str | Path): Path to save the generated labels, labels will be saved into `labels-segment` in the same directory level of `im_dir` if save_dir is None. Default: None. sam_model (str): Segmentation model to use for intermediate segmentation data; optional. Notes: The input directory structure assumed for dataset: - im_dir ├─ 001.jpg ├─ .. └─ NNN.jpg - labels ├─ 001.txt ├─ .. └─ NNN.txt r)Útqdm)ÚSAM)Ú YOLODataset)r)Ú xywh2xyxyiè)Únames)r§r®z;Segmentation labels detected, no need to generate new ones!NzBDetection labels detected, generating segment labels by SAM model!zGenerating segment labels)Útotalrtr¼r­rrr Zim_fileF)r­ÚverboseÚsavezlabels-segmentTrhr~r°ryr€rcss|]}|dVqdSr‚rV)rnÚtextrVrVrWr„|rqz$yolo_bbox2segment..z"Generated segment labels saved in )rçZ ultralyticsrèZultralytics.dataréÚultralytics.utilsrZultralytics.utils.opsrêÚdictrŽrœr—rfr¡rºr»ÚmasksZxynrÚparentr…r›rŸrâÚintršrržr‹r )Zim_dirr¢Z sam_modelrçrèrérrêZdatasetÚlabelr«r¬ZboxesZimZ sam_resultsZtextsZlb_nameZtxt_filer°rzr±rƒr¦rVrVrWÚyolo_bbox2segment?sF           8rö)rdreFFTF)Nræ)rŒÚ collectionsrÚpathlibrrºÚnumpyr”rðrrZultralytics.utils.filesrrXrcr³rÉr‘rÞrár˜rörVrVrVrWÚs(   gdú xN`2