/j"dZddlmZddlZddlmZddlZddlZddl m Z m Z m Z ddl mZmZ dddZdde jd fddZdS)zlFunctions for estimating the best YOLO batch size to use a fraction of the available CUDA memory in PyTorch.) annotationsN)deepcopy) DEFAULT_CFGLOGGERcolorstr)autocast profile_opsTmodeltorch.nn.Moduleimgszintampboolbatch int | float max_num_objreturnct|5tt||d|cxkrdkrnn|nd|cdddS#1swxYwYdS)aCompute optimal YOLO training batch size using the autobatch() function. Args: model (torch.nn.Module): YOLO model to check batch size for. imgsz (int, optional): Image size used for training. amp (bool, optional): Use automatic mixed precision if True. batch (int | float, optional): Fraction of GPU memory to use. If -1, use default. max_num_obj (int, optional): The maximum number of objects from dataset. Returns: (int): Optimal batch size computed using the autobatch() function. Notes: If 0.0 < batch < 1.0, it's used as the fraction of GPU memory to use. Otherwise, a default fraction of 0.6 is used. )enabledgg?333333?)fractionrN)r autobatchrtrain)r rrrrs `/home/longshao/multi-rider-rag/.venv/lib/python3.11/site-packages/ultralytics/utils/autobatch.pycheck_train_batch_sizers. #      UOO ! ! # #UcE>O>O>O>OC>O>O>O>O>OUUUXfq                     sAA""A&)A&rrfloat batch_sizecJtd}tj|dd|dzdt|j}|jdvrtj|d||Stj j j rtj|d||Sd }d tj d d d }tj|} | j|z tj||z } tj||z } | | zz } tj||d| jddd| dd| dd| dd dkrgdngd} |jdd fd| D}t/||d||fdt1t3| D}|r t3|nggf\}}t5j||d}t9t;| |z|dz |d z }dvr:d}|| |kr| t?|dz d }|dks|d krtj|d!|d"|d#|}t5j ||| z| zz }tj|d$|d%|d&|zdd'dd(|dzd)d* |tj!S#tD$rG}tj|d+|d,|d#|cYd}~tj!Sd}~wwxYw#tj!wxYw)-a9Automatically estimate the best YOLO batch size to use a fraction of the available CUDA memory. Args: model (torch.nn.Module): YOLO model to compute batch size for. imgsz (int, optional): The image size used as input for the YOLO model. fraction (float, optional): The fraction of available CUDA memory to use. batch_size (int, optional): The default batch size to use if an error is detected. max_num_obj (int, optional): The maximum number of objects from dataset. Returns: (int): The optimal batch size. z AutoBatch: z'Computing optimal batch size for imgsz=z at dz% CUDA memory utilization.>cpumpsz4intended for CUDA devices, using default batch-size zHRequires torch.backends.cudnn.benchmark=False, using default batch-size i@zCUDA:CUDA_VISIBLE_DEVICES0rz (z) z.2fz G total, z G reserved, z G allocated, zG free)r r')r r(r)r*r' @channelsc>g|]}tj|S)torchempty).0bchrs r zautobatch..Ys)EEEAu{1b%//EEEr )ndevicercg|]x\}\}}|rnt|dttfrLd|dcxkrkr9nn6|dks&|dz r|d|dz dkn||dgyS)r(rr ) isinstancerr)r3ixyresultsts rr6zautobatch..]s   6Aq 1Q4#u..  AaD 1 awq1u~1Aq8I1I1I !I 2J1I1Ir7)degNizbatch=z. outside safe range, using default batch-size .zUsing batch-size z for  zG/zG (z.0fu%) ✅zerror detected: z, using default batch-size )#rrinfonext parametersr9typewarningr1backendscudnn benchmarkosgetenvstripcudaget_device_properties total_memorymemory_reservedmemory_allocatednameyamlgetr enumeratezipnppolyfitrroundindexmaxpolyval empty_cache Exception)r rrr rprefixr9gbd propertiesraf batch_sizesimgxyfit_xfit_ypr4r<er5r?r@s ` @@@rrr-s_(m $ $F K6ww%wwXX[^wwwxxx %""$$ % % ,F {n$$&bbV`bbccc ~%&vvjtvvwww BC 0#66<<>>qACCA11&99J"$A ""6**R/A ##F++b0A QU A K6w1ww ww1www1wwwVWwwwjkwwwwxxx'("ff""""2J2J2JK  A & &B!EEEEEEEEc5Af+VVV     &s;'@'@AA   $&3sBxxB8 u Jue + + + q8|$$qt+qt3 4 4 7?? d##AKN""AE1 . q55AHH NfjjAjj]gjjj k k kAJq!$$q(1,1 vttttttALtttPQtttZbehZhttttuuu      &^^!^^Q[^^^___           s11EL.. M?8M:M?N:M??N N")r Tr r ) r rrrrrrrrrrr) r rrrrrr rrrrr)__doc__ __future__rrLcopyrnumpyrYr1ultralytics.utilsrrrultralytics.utils.torch_utilsrr rrrr0r7rrusrr""""""  ;;;;;;;;;;????????       >!' J!J!J!J!J!J!J!r7