o V hE@svddlZddlZddlmZddlmZmZddlmZm Z m Z dddZ edd d fd d Z e d kr9e ddSdS)N)Path) IMG_FORMATSimg2label_paths) DATASETS_DIRLOGGERTQDM皙?c Cspt|}t|d}|d|d}}|jdd|jdd|jdddd|D}tdd |D}t|d |d }td |d |d|ddd|dd |D]R} || jjdd|| jjddt| d} t | t t| |} | d| D]} t | || j| jq| | dD]} t | || j| jqqZtd|d|S)u Split dataset into train and val directories in a new directory. Creates a new directory '{source_dir}_split' with train/val subdirectories, preserving the original class structure with an 80/20 split by default. Directory structure: Before: caltech/ ├── class1/ │ ├── img1.jpg │ ├── img2.jpg │ └── ... ├── class2/ │ ├── img1.jpg │ └── ... └── ... After: caltech_split/ ├── train/ │ ├── class1/ │ │ ├── img1.jpg │ │ └── ... │ ├── class2/ │ │ ├── img1.jpg │ │ └── ... │ └── ... └── val/ ├── class1/ │ ├── img2.jpg │ └── ... ├── class2/ │ └── ... └── ... Args: source_dir (str | Path): Path to Caltech dataset root directory. train_ratio (float): Ratio for train split, between 0 and 1. Examples: >>> # Split dataset with default 80/20 ratio >>> split_classify_dataset("path/to/caltech") >>> # Split with custom ratio >>> split_classify_dataset("path/to/caltech", 0.75) _splittrainvalT)exist_okcSsg|]}|r|qS)is_dir.0dr r J/var/www/vscode/kcb/lib/python3.10/site-packages/ultralytics/data/split.py Bsz*split_classify_dataset..css"|] }tt|dVqdS)*.*N)lenlistglobrr r r Cs z)split_classify_dataset..z classes, z imagesz Splitting z (z) into z.0%z train, z val...rNzSplit complete in u ✅)rmkdiriterdirsumrrinfonamerrrandomshuffleintshutilcopy2) source_dir train_ratio source_path split_path train_pathval_path class_dirs total_imagesstats class_dir image_files split_idximgr r rsplit_classify_dataset s./   , r1z coco8/images)g?g?gFc Cs"t|}tdd|dD}t|}tdtjgd||d}gd}|D]}|j|r9|j| q)t d|d |t t |||d D]?\}} |rbttt| gdrt|j||d d d } | d| |jdWdn1swYqOdS)a Automatically split a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files. Args: path (Path, optional): Path to images directory. weights (list | tuple, optional): Train, validation, and test split fractions. annotated_only (bool, optional): If True, only images with an associated txt file are used. Examples: >>> from ultralytics.data.split import autosplit >>> autosplit() css*|]}|jddtvr|VqdS)rN)suffixlowerr)rxr r rris(zautosplit..rr)rr)weightsk)zautosplit_train.txtzautosplit_val.txtzautosplit_test.txtzAutosplitting images from z!, using *.txt labeled images only)totalazutf-8)encodingz./ N)rsortedrglobrrseedchoicesparentexistsunlinkrrrziprstropenwrite relative_toas_posix) pathr6annotated_onlyfilesnindicestxtr4ir0fr r r autosplit[s$  "rQ__main__z../datasets/caltech101)r)rr"pathlibrultralytics.data.utilsrrultralytics.utilsrrrr1rQ__name__r r r rs  R