o eb@sddlmZddlZddlmZmZddlmZddlm Z ddl m Z m Z m Z mZmZddlZddlZddlmZddlmZmZdd lmZmZdd lmZmZmZdd lm Z m!Z!m"Z"m#Z#m$Z$dd l%m&Z&eGd ddeZ'eGddde'Z(eGddde'Z)dS) annotationsN)ABCabstractmethod) dataclass)Path)DictIteratorListOptionalTuple)Classifications)load_coco_annotationssave_coco_annotations)detections_to_pascal_vocload_pascal_voc_annotations)load_yolo_annotationssave_data_yamlsave_yolo_annotations)build_class_index_mappingmap_detections_class_idmerge_class_listssave_dataset_imagestrain_test_split) Detectionsc@s,eZdZed ddZe ddd d ZdS) BaseDatasetreturnintcCdSNselfr r G/var/www/myenv/lib/python3.10/site-packages/supervision/dataset/core.py__len__&szBaseDataset.__len__皙?NTshuffleboolTuple[BaseDataset, BaseDataset]cCrrr )r" split_ratio random_stater&r r r#split*szBaseDataset.splitrrr%NT)r&r'rr()__name__ __module__ __qualname__rr$r+r r r r#r$s  rc@seZdZUdZded<ded<ded<d8d d Zd9d dZddZ d:d;ddZ     dd?d(d)Z e %d>d@d+d,Z      dAdBd-d.Z e %d>dCd0d1Z     d>> import supervision as sv >>> ds = sv.DetectionDataset(...) >>> train_ds, test_ds = ds.split(split_ratio=0.7, ... random_state=42, shuffle=True) >>> len(train_ds), len(test_ds) (700, 300) ``` data train_ratior*r&ci|]}|j|qSr r5.0namer!r r# z*DetectionDataset.split..crKr rrMr!r r#rPrQr3r5rcrKr rLrMr!r r#rPrQcrKr rrMr!r r#rPrQ)listr5keysrr1r3 r"r)r*r& image_names train_names test_names train_dataset test_datasetr r!r#r+es$ zDetectionDataset.split?images_directory_path Optional[str]annotations_directory_pathmin_image_area_percentagefloatmax_image_area_percentageapproximation_percentageNonec Cs|r t||jd|rt|jddd|jD]F\}}|j|}|r_t|j} tj || d} t|j } t ||j | |j |||d} t| d } | | Wdn1sZwYqdS)a Exports the dataset to PASCAL VOC format. This method saves the images and their corresponding annotations in PASCAL VOC format. Args: images_directory_path (Optional[str]): The path to the directory where the images should be saved. If not provided, images will not be saved. annotations_directory_path (Optional[str]): The path to the directory where the annotations in PASCAL VOC format should be saved. If not provided, annotations will not be saved. min_image_area_percentage (float): The minimum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets. max_image_area_percentage (float): The maximum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets. approximation_percentage (float): The percentage of polygon points to be removed from the input polygon, in the range [0, 1). Argument is used only for segmentation datasets. r]r5T)parentsexist_okz.xml) detectionsr3filename image_shaper`rbrcwN)rr5rmkdirr:rstemospathjoinrOrr3shapeopenwrite)r"r]r_r`rbrc image_pathr=rhannotation_nameannotations_pathr<pascal_voc_xmlfr r r# as_pascal_vocs8     zDetectionDataset.as_pascal_vocFstr force_maskscC"t|||d\}}}t|||dS)a Creates a Dataset instance from PASCAL VOC formatted data. Args: images_directory_path (str): Path to the directory containing the images. annotations_directory_path (str): Path to the directory containing the PASCAL VOC XML annotations. force_masks (bool, optional): If True, forces masks to be loaded for all annotations, regardless of whether they are present. Returns: DetectionDataset: A DetectionDataset instance containing the loaded images and annotations. Example: ```python >>> import roboflow >>> from roboflow import Roboflow >>> import supervision as sv >>> roboflow.login() >>> rf = Roboflow() >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID) >>> dataset = project.version(PROJECT_VERSION).download("voc") >>> ds = sv.DetectionDataset.from_pascal_voc( ... images_directory_path=f"{dataset.location}/train/images", ... annotations_directory_path=f"{dataset.location}/train/labels" ... ) >>> ds.classes ['dog', 'person'] ``` )r]r_r{rR)rr1)clsr]r_r{r3r5rr r r#from_pascal_vocs , z DetectionDataset.from_pascal_vocdata_yaml_pathcCs$t||||d\}}}t|||dS)a Creates a Dataset instance from YOLO formatted data. Args: images_directory_path (str): The path to the directory containing the images. annotations_directory_path (str): The path to the directory containing the YOLO annotation files. data_yaml_path (str): The path to the data YAML file containing class information. force_masks (bool, optional): If True, forces masks to be loaded for all annotations, regardless of whether they are present. Returns: DetectionDataset: A DetectionDataset instance containing the loaded images and annotations. Example: ```python >>> import roboflow >>> from roboflow import Roboflow >>> import supervision as sv >>> roboflow.login() >>> rf = Roboflow() >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID) >>> dataset = project.version(PROJECT_VERSION).download("yolov5") >>> ds = sv.DetectionDataset.from_yolo( ... images_directory_path=f"{dataset.location}/train/images", ... annotations_directory_path=f"{dataset.location}/train/labels", ... data_yaml_path=f"{dataset.location}/data.yaml" ... ) >>> ds.classes ['dog', 'person'] ``` )r]r_rr{rR)rr1)r}r]r_rr{r3r5rr r r# from_yolos1 zDetectionDataset.from_yolocCsT|dur t||jd|durt||j|j|||d|dur(t||jddSdS)a Exports the dataset to YOLO format. This method saves the images and their corresponding annotations in YOLO format. Args: images_directory_path (Optional[str]): The path to the directory where the images should be saved. If not provided, images will not be saved. annotations_directory_path (Optional[str]): The path to the directory where the annotations in YOLO format should be saved. If not provided, annotations will not be saved. data_yaml_path (Optional[str]): The path where the data.yaml file should be saved. If not provided, the file will not be saved. min_image_area_percentage (float): The minimum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets. max_image_area_percentage (float): The maximum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets. approximation_percentage (float): The percentage of polygon points to be removed from the input polygon, in the range [0, 1). This is useful for simplifying the annotations. Argument is used only for segmentation datasets. Nre)r_r5rr`rbrc)rr3)rr5rrrr3)r"r]r_rr`rbrcr r r#as_yolo@s %zDetectionDataset.as_yolorvcCr|)a Creates a Dataset instance from COCO formatted data. Args: images_directory_path (str): The path to the directory containing the images. annotations_path (str): The path to the json annotation files. force_masks (bool, optional): If True, forces masks to be loaded for all annotations, regardless of whether they are present. Returns: DetectionDataset: A DetectionDataset instance containing the loaded images and annotations. Example: ```python >>> import roboflow >>> from roboflow import Roboflow >>> import supervision as sv >>> roboflow.login() >>> rf = Roboflow() >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID) >>> dataset = project.version(PROJECT_VERSION).download("coco") >>> ds = sv.DetectionDataset.from_coco( ... images_directory_path=f"{dataset.location}/train", ... annotations_path=f"{dataset.location}/train/_annotations.coco.json", ... ) >>> ds.classes ['dog', 'person'] ``` )r]rvr{rR)rr1)r}r]rvr{r3r5rr r r# from_cocous , zDetectionDataset.from_cococ CsB|dur t||jd|durt||j|j|j|||ddSdS)a Exports the dataset to COCO format. This method saves the images and their corresponding annotations in COCO format. Args: images_directory_path (Optional[str]): The path to the directory where the images should be saved. If not provided, images will not be saved. annotations_path (Optional[str]): The path to COCO annotation file. min_image_area_percentage (float): The minimum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets. max_image_area_percentage (float): The maximum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets. approximation_percentage (float): The percentage of polygon points to be removed from the input polygon, in the range [0, 1). This is useful for simplifying the annotations. Argument is used only for segmentation datasets. Nre)annotation_pathr5rr3r`rbrc)rr5rrr3)r"r]rvr`rbrcr r r#as_cocos zDetectionDataset.as_coco dataset_listList[DetectionDataset]c Csii}}dd|D}t|d}|D])}t|j|d}|D]\}} } ||vr/td|d| ||<t|| d||<qq||||dS) a Merge a list of `DetectionDataset` objects into a single `DetectionDataset` object. This method takes a list of `DetectionDataset` objects and combines their respective fields (`classes`, `images`, `annotations`) into a single `DetectionDataset` object. Args: dataset_list (List[DetectionDataset]): A list of `DetectionDataset` objects to merge. Returns: (DetectionDataset): A single `DetectionDataset` object containing the merged data from the input list. Example: ```python >>> import supervision as sv >>> ds_1 = sv.DetectionDataset(...) >>> len(ds_1) 100 >>> ds_1.classes ['dog', 'person'] >>> ds_2 = sv.DetectionDataset(...) >>> len(ds_2) 200 >>> ds_2.classes ['cat'] >>> ds_merged = sv.DetectionDataset.merge([ds_1, ds_2]) >>> len(ds_merged) 300 >>> ds_merged.classes ['cat', 'dog', 'person'] ``` cSsg|]}|jqSr )r3)rNdatasetr r r# sz*DetectionDataset.merge..) class_lists)source_classestarget_classesz Image name z is not unique across datasets.)source_to_target_mappingrhrR)rrr3 ValueErrorr) r}r merged_imagesmerged_annotationsrmerged_classesrclass_index_mappingr<r=rhr r r#merges* )    zDetectionDataset.merger,)rr9r-)r&r'rrF)NNr[r\r[) r]r^r_r^r`rarbrarcrarrd)F)r]rzr_rzr{r'rr1) r]rzr_rzrrzr{r'rr1)NNNr[r\r[)r]r^r_r^rr^r`rarbrarcrarrd)r]rzrvrzr{r'rr1) r]r^rvr^r`rarbrarcrarrd)rrrr1)r.r/r0__doc____annotations__r$r>rEr+ry classmethodr~rrrrrr r r r#r11sP      4 <3: 54 -r1c@sZeZdZUdZded<ded<ded<dd d Z ddddZdddZedddZ d S) ClassificationDatasetaT Dataclass containing information about a classification dataset. Attributes: classes (List[str]): List containing dataset class names. images (Dict[str, np.ndarray]): Dictionary mapping image name to image. annotations (Dict[str, Detections]): Dictionary mapping image name to annotations. r2r3r4r5zDict[str, Classifications]rrrcCr6rr7r!r r r#r$'s zClassificationDataset.__len__r%NTr&r'3Tuple[ClassificationDataset, ClassificationDataset]c rG)a Splits the dataset into two parts (training and testing) using the provided split_ratio. Args: split_ratio (float, optional): The ratio of the training set to the entire dataset. random_state (int, optional): The seed for the random number generator. This is used for reproducibility. shuffle (bool, optional): Whether to shuffle the data before splitting. Returns: Tuple[ClassificationDataset, ClassificationDataset]: A tuple containing the training and testing datasets. Example: ```python >>> import supervision as sv >>> cd = sv.ClassificationDataset(...) >>> train_cd,test_cd = cd.split(split_ratio=0.7, ... random_state=42,shuffle=True) >>> len(train_cd), len(test_cd) (700, 300) ``` rHcrKr rLrMr!r r#rPQrQz/ClassificationDataset.split..crKr rrMr!r r#rPRrQrRcrKr rLrMr!r r#rPVrQcrKr rrMr!r r#rPWrQ)rSr5rTrrr3rUr r!r#r+*s$ zClassificationDataset.splitroot_directory_pathrzrdcCstj|dd|jD]}tjtj||ddq |jD]7}|j|}|j|}t|j}|j dur7|j dn| ddd}|j|}tj|||}t ||qdS)z Saves the dataset as a multi-class folder structure. Args: root_directory_path (str): The path to the directory where the dataset will be saved. T)rgNr)rnmakedirsr3rorpr5rrrO confidenceclass_id get_top_kcv2imwrite)r"r class_namertclassificationr=r<rr r r#as_folder_structure[s        z)ClassificationDataset.as_folder_structurec Cst|}tt|}i}i}|D]0}||}ttj||D]}ttj|||}t |||<t t |gd||<q"q||||dS)a Load data from a multiclass folder structure into a ClassificationDataset. Args: root_directory_path (str): The path to the dataset directory. Returns: ClassificationDataset: The dataset. Example: ```python >>> import roboflow >>> from roboflow import Roboflow >>> import supervision as sv >>> roboflow.login() >>> rf = Roboflow() >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID) >>> dataset = project.version(PROJECT_VERSION).download("folder") >>> cd = sv.ClassificationDataset.from_folder_structure( ... root_directory_path=f"{dataset.location}/train" ... ) ``` )rrR) rnlistdirsortedr@indexrorprzrimreadr rAarray) r}rr3r5rrrr=rtr r r#from_folder_structureus$     z+ClassificationDataset.from_folder_structurer,r-)r&r'rr)rrzrrd)rrzrr) r.r/r0rrr$r+rrrr r r r#rs    1r)* __future__rrnabcrr dataclassesrpathlibrtypingrr r r r rnumpyrAsupervision.classification.corer supervision.dataset.formats.cocorr&supervision.dataset.formats.pascal_vocrr supervision.dataset.formats.yolorrrsupervision.dataset.utilsrrrrrsupervision.detection.corerrr1rr r r r#s.      h