FiddlmZmZddlmZ erJeddusJddlZeedsJiZddZ ddZ d Z d Zd Zd Zd ZereeeedZyiZy#e e f$rdZY6wxYw))SETTINGS TESTS_RUNNING)model_info_for_loggerswandbTN __version__cRddl}ddlm}|j|||dj |j j d}|jgdj} dddd} |||d } tjd tj| gd | | S) aLCreate and log a custom metric visualization table. This function crafts a custom metric visualization that mimics the behavior of the default wandb precision-recall curve while allowing for enhanced customization. The visual metric is useful for monitoring model performance across different classes. Args: x (list): Values for the x-axis; expected to have length N. y (list): Corresponding values for the y-axis; also expected to have length N. classes (list): Labels identifying the class of each point; length N. title (str, optional): Title for the plot. x_title (str, optional): Label for the x-axis. y_title (str, optional): Label for the y-axis. Returns: (wandb.Object): A wandb object suitable for logging, showcasing the crafted metric visualization. rN)classyxr r r )r r r )titlez x-axis-titlez y-axis-titlezwandb/area-under-curve/v0datacolumns)fields string_fields) polarspolars.selectors selectors DataFrame with_columnsnumericroundselectrowswb plot_tableTable) r r classesr x_titley_titleplcsdfrrrs `/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/ultralytics/utils/callbacks/wb.py _custom_tabler&s$! aa8 9 F Frzz|GYGYZ[G\ ]B 99( ) . . 0DS7 3F#WgVM ==# d$78#  c "ddl} |g}| j|d|d|jd} | j} | j | || j |djdj} |rot jtt| | ||g} t jj|t jj| |||iyd gt| z}t|D]Y\}}| j!| | j!| j | |||j!||gt| z[t j|t#| | ||||id y) a<Log a metric curve visualization. This function generates a metric curve based on input data and logs the visualization to wandb. The curve can represent aggregated data (mean) or individual class data, depending on the 'only_mean' flag. Args: x (np.ndarray): Data points for the x-axis with length N. y (np.ndarray): Corresponding data points for the y-axis with shape (C, N), where C is the number of classes. names (list, optional): Names of the classes corresponding to the y-axis data; length C. id (str, optional): Unique identifier for the logged data in wandb. title (str, optional): Title for the visualization plot. x_title (str, optional): Label for the x-axis. y_title (str, optional): Label for the y-axis. num_x (int, optional): Number of interpolated data points for visualization. only_mean (bool, optional): Flag to indicate if only the mean curve should be plotted. Notes: The function leverages the '_custom_table' function to generate the actual visualization. rN)axisr r)r meanF)commit)numpylinspacertolistinterpr,rrlistziprunlogplotlinelen enumerateextendr&)r r namesidr r r!num_x only_meannpx_newx_logy_logtableriyis r% _plot_curverF4sR< } KK!aeU + 1 1! 4E LLNE IIeQ 2 3 9 9! < C C EEd3ue#45?QR  E277<<wu<MNO(SZ'q\ 4EAr LL  LL5!R0 1 NNE!H:E 2 3 4 M%QR[`ar'c 0|jjD]u\}}|d}tj||k7s$tj j |jt jt|i||t|<wy)aLog plots to WandB at a specific step if they haven't been logged already. This function checks each plot in the input dictionary against previously processed plots and logs new or updated plots to WandB at the specified step. Args: plots (dict): Dictionary of plots to log, where keys are plot names and values are dictionaries containing plot metadata including timestamps. step (int): The step/epoch at which to log the plots in the WandB run. Notes: The function uses a shallow copy of the plots dictionary to prevent modification during iteration. Plots are identified by their stem name (filename without extension). Each plot is logged as a WandB Image object. timestampstepN) copyitems_processed_plotsgetrr4r5stemImagestr)plotsrJnameparamsrHs r% _log_plotsrUisx  **,/ f;'    % 2 FFJJ 288CI#67dJ C%. T " /r'c tjsgddlm}ddlm}t |j jjddjdd}||jdz d z }|j jxr|j}tj|j jr/t |j jjddnd |t|j |r-|jjj!dd d n#|d|j#j%d |rd ndt |jyy)z8Initialize and start wandb project if module is present.r)datetime)Path/- _rz latest-run Ultralyticsz %Y%m%d_%H%M%SallowN)projectrSconfigr<resumedir)rr4rWpathlibrXrQargsrSreplacesave_dirrbexistsinitr`varsresolvesplitnowstrftime)trainerrWrXrS latest_runresumings r%on_pretrain_routine_startrrs  66% 7<<$$%--c37??SI'**+g5 D <<&&>:+<+<+> CJ<22?CDE&7DG$$%  r'ct|j|jdzt|jj|jdz|jdk(r7tj j t||jdztj j |j|jdzdy)zBLog training metrics and model information at the end of an epoch.rIrT)rJr-N) rUrRepoch validatorrr4r5rmetricsros r%on_fit_epoch_endrysw}}7==1#45w  &&W]]Q->?}}  )'29J KFFJJwW]]Q%6tJDr'cntjj|j|jd|j dztjj|j |j dz|j dk(r%t|j|j dzyy)z>Log metrics and save images at the end of each training epoch.train)prefixrtrIN) rr4r5label_loss_itemstlossrulrrUrRrxs r%on_train_epoch_endrs}FFJJw'' g'FW]]]^M^J_FFJJwzz  1J2}}7==w}}q'89r'c t|jj|jdzt|j|jdzt j ddtj jd}|jjr=|j|jtj j|dg|jjrt|jjd rt|jjj |jjj"D]V\}}|\}}}}t%||t'|jjj(j+d |||| Xtj j-y ) zNSave the best model as an artifact and log final plots at the end of training.rtrImodelrun__model)typerSbest)aliasescurves_resultszcurves/)r;r<r r r!N)rUrvrRrurArtifactr4r<rrhadd_file log_artifactrehasattrrwr3curvesrrFr2r;valuesfinish)roart curve_name curve_valuesr r r r!s r% on_train_endrsUw  &&W]]Q->?w}}7==1#45 ++74 {&)A BC|| W\\" C&2||gg&7&7&?&?AQR(+G,=,=,E,E,L,LgN_N_NgNgNvNv(w  $J %1 "Aq'7 7,,44::AACDZL)   FFMMOr')rrrryr)Precision Recall CurveRecall Precision)Nzprecision-recallrrrdF)ultralytics.utilsrrultralytics.utils.torch_utilsrrrrrM ImportErrorAssertionErrorr&rFrUrrryrr callbacksr'r%rs6@   G  $$ $ 2} %% % J  "   2bj/. *E:> &?0,$    a ^$ BsA A%$A%