a yf>.@sdZddlZddlZddlZddlZddlZddlZddlm Z m Z ddl m Z m Z mZmZmZmZmZddlmZGdddZdS)a? Module provides functionalities for hyperparameter tuning of the Ultralytics YOLO models for object detection, instance segmentation, image classification, pose estimation, and multi-object tracking. Hyperparameter tuning is the process of systematically searching for the optimal set of hyperparameters that yield the best model performance. This is particularly crucial in deep learning models like YOLO, where small changes in hyperparameters can lead to significant differences in model accuracy and efficiency. Example: Tune hyperparameters for YOLOv8n on COCO8 at imgsz=640 and epochs=30 for 300 tuning iterations. ```python from ultralytics import YOLO model = YOLO("yolov8n.pt") model.tune(data="coco8.yaml", epochs=10, iterations=300, optimizer="AdamW", plots=False, save=False, val=False) ``` N)get_cfg get_save_dir) DEFAULT_CFGLOGGER callbackscolorstrremove_colorstr yaml_print yaml_save)plot_tune_resultsc@s2eZdZdZedfddZdd d Zdd dZdS)TuneraE Class responsible for hyperparameter tuning of YOLO models. The class evolves YOLO model hyperparameters over a given number of iterations by mutating them according to the search space and retraining the model to evaluate their performance. Attributes: space (dict): Hyperparameter search space containing bounds and scaling factors for mutation. tune_dir (Path): Directory where evolution logs and results will be saved. tune_csv (Path): Path to the CSV file where evolution logs are saved. Methods: _mutate(hyp: dict) -> dict: Mutates the given hyperparameters within the bounds specified in `self.space`. __call__(): Executes the hyperparameter evolution across multiple iterations. Example: Tune hyperparameters for YOLOv8n on COCO8 at imgsz=640 and epochs=30 for 300 tuning iterations. ```python from ultralytics import YOLO model = YOLO("yolov8n.pt") model.tune(data="coco8.yaml", epochs=10, iterations=300, optimizer="AdamW", plots=False, save=False, val=False) ``` Tune with custom search space. ```python from ultralytics import YOLO model = YOLO("yolov8n.pt") model.tune(space={key1: val1, key2: val2}) # custom search space dictionary ``` NcCs|ddp>ddddddd d d d d d dd dddddddddd|_t|d|_t|jdd|_|jd|_|ptt|_t d|_ t |t |j d|jd|j ddS)z Initialize the Tuner with configurations. Args: args (dict, optional): Configuration for hyperparameter evolution. spaceN)gh㈵>皙?)g-C6?r)gffffff?g\(\?333333?)gMbP?)rg@)rgffffff?)?g4@)皙?g@)g?g@)rr)rg?)rgF@)rg$@)rr)Zlr0ZlrfZmomentumZ weight_decayZ warmup_epochsZwarmup_momentumboxclsZdflZhsv_hZhsv_sZhsv_vdegrees translatescaleZshearZ perspectiveZflipudZfliplrZbgrZmosaicZmixupZ copy_paste)Z overridesZtune)nameztune_results.csvzTuner: z*Initialized Tuner instance with 'tune_dir=z' uT💡 Learn about tuning at https://docs.ultralytics.com/guides/hyperparameter-tuning)popr rargsrtune_dirtune_csvrZget_default_callbacksrprefixZadd_integration_callbacksrinfo)selfr _callbacksr!T/var/www/html/django/DPS/env/lib/python3.9/site-packages/ultralytics/engine/tuner.py__init__FsH     zTuner.__init__single皙?rc sjrtjjdddddddf}t|t}t| d|dddfdddfd}|dkstdkrtjt ||d dn&|d krԈ| |d d| tj}| t ttd d jD}tj} t| tdkr`||| |k|| ||dd dqfddtjD} nfddjD} jD]H\} t| | d| | <t| | d| | <t| | d| | <q| S)a Mutates the hyperparameters based on bounds and scaling factors specified in `self.space`. Args: parent (str): Parent selection method: 'single' or 'weighted'. n (int): Number of parents to consider. mutation (float): Probability of a parameter mutation in any given iteration. sigma (float): Standard deviation for Gaussian random number generator. Returns: (dict): A dictionary containing mutated hyperparameters. ,Zndmin delimiterZskiprowsNrgư>r$)weightsZweightedcSs(g|] \}}t|dkr |dndqS)r'r)len.0kvr!r!r" z!Tuner._mutate..rg@cs*i|]"\}}|t|d|qSr)floatr0ir1)r2xr!r" r4z!Tuner._mutate..csi|]}|tj|qSr!)getattrrr0r1)rr!r"r;r4r%)rexistsnploadtxtminr.ZargsortrandomchoicesrangeZreshapesumseedinttimearrayr itemsZonesallZrandnZclip enumeratekeysmaxround) rparentnZmutationsigmafitnesswrgngZhypr1r!)rr2r:r"_mutaters0 (  8 z Tuner._mutate TcsTt}d\}}|jdjdddt|D] }|t|jd|dd|di}it|j } t t | } | d} zdd d gd d | D} t j| dd j} | | drdnd}t|d}| dksJdWn@ty.}z&td|dd|WYd}~n d}~00|dd}t|dgfdd|jD}|jrpdnddgt|jd}t|jd.}||dtt|dWdn1s0Yt j!|jdddddddf}|"|k}|rP| }d d!| D}| #d"D]}t$%||jdq4n|rdt$j&| dd#t'|j|j|dd|d$t|d%d&|jd't(d(|jd|jd)|d*dd|jd+|d|jd,|d|jd-}td|fd.d!t)|jD}t*|jd/|t+|,|jd0dd1t-|jd/q,dS)2a Executes the hyperparameter evolution process when the Tuner instance is called. This method iterates through the number of iterations, performing the following steps in each iteration: 1. Load the existing hyperparameters or initialize new ones. 2. Mutate the hyperparameters using the `mutate` method. 3. Train a YOLO model with the mutated hyperparameters. 4. Log the fitness score and mutated hyperparameters to a CSV file. Args: model (Model): A pre-initialized YOLO model to be used for training. iterations (int): The number of generations to run the evolution for. cleanup (bool): Whether to delete iteration weights to reduce storage space used during tuning. Note: The method utilizes the `self.tune_csv` Path object to read and log hyperparameters and fitness scores. Ensure this path is set correctly in the Tuner instance. )NNr,T)parentsexist_okzStarting iteration r)/z with hyperparameters: Zyolotraincss |]\}}|d|VqdS)=Nr!r/r!r!r" r4z!Tuner.__call__..)checkzbest.ptzlast.ptZ train_metricsrztraining faileduDWARNING ❌️ training failure for hyperparameter tuning iteration  NrSrr%csg|] }|qSr!r!r=) mutated_hypr!r"r3r4z"Tuner.__call__..r(ar'r*cSsi|]\}}|t|dqS)r%)rOr/r!r!r"r;r4z"Tuner.__call__..z*.pt) ignore_errorsu iterations complete ✅ (z.2fzs) zResults saved to boldz Best fitness=z observed at iteration zBest fitness metrics are zBest fitness model is z0Best fitness hyperparameters are printed below. cs&i|]\}}|t|dfqSr5r6r8)best_idxr:r!r"r;r4zbest_hyperparameters.yamlz# )dataheader).rHrmkdirrDrXrrrvarsrrrrJ subprocessrun returncoder>torchload ExceptionwarninggetrOr rMrjoinlistopenwritemapstrr?r@Zargmaxglobshutilcopy2rmtreer rrLr rreplacer )rmodelZ iterationscleanupt0Z best_save_dirZ best_metricsr9ZmetricsZ train_argssave_dirZ weights_dircmdZ return_codeZ ckpt_fileerSZlog_rowheadersfZbest_is_currentZckptrirhr!)rgrbr:r"__call__s& 0 $.> & zTuner.__call__)r$r%r&r)NrYT)__name__ __module__ __qualname____doc__rr#rXrr!r!r!r"r !s$, .r )rrBr{rlrHnumpyr?roZultralytics.cfgrrZultralytics.utilsrrrrrr r Zultralytics.utils.plottingr r r!r!r!r"s$