o W h1@sndZddlZddlmZddlZddlZddlmZm Z m Z ddl m Z m Z dd d Zdd ejd fd dZdS)zlFunctions for estimating the best YOLO batch size to use a fraction of the available CUDA memory in PyTorch.N)deepcopy) DEFAULT_CFGLOGGERcolorstr)autocastprofileTcCsbt|d"tt||d|krdkrnn|nd|dWdS1s*wYdS)a Compute 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 (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?)fraction max_num_objN)r autobatchrtrain)modelimgszampbatchrrO/var/www/vscode/kcb/lib/python3.10/site-packages/ultralytics/utils/autobatch.pycheck_train_batch_sizes ,$rr cstd}t|dd|ddt|j}|jdvr,t|d||Stj j j r=t|d||Sd }d t d d d }tj|} | j|tj||} tj||} | | } t||d| jddd| dd| dd| dd dkrgdngd} zzfdd| D}t||d||dfddtt| D}|rt|nggf\}}tj||dd}tt| ||d|d }dvrd}|| |kr| t|dd }|dks|dkrt|d |d!|d"|}t||| | }t|d#|d$|d%|dd&dd'|dd(d) |WWtjSt yj}zt|d*|d+|d"|WYd}~WtjSd}~wwtjw),a> Automatically 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 rrr r @csg|] }t|dqS))torchempty).0b)rrr Lszautobatch..r )ndevicercs~g|];\}\}}|r=t|dttfr=d|dkrkr=nn|dks7|dr7|d|ddkr||dgqS)rrr ) isinstanceintfloat)r&ixy)resultstrrr(Ps , )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 parametersr*typewarningr$backendscudnn benchmarkosgetenvstripcudaget_device_properties total_memorymemory_reservedmemory_allocatednamer enumeratezipnppolyfitr,roundindexmaxpolyval empty_cache Exception)rrr batch_sizerprefixr*gbd propertiesraf batch_sizesimgxyfit_xfit_ypr'r.er)rr1r2rr&sZ      <     <   r)rTr r )__doc__r>copyrnumpyrIr$ultralytics.utilsrrrultralytics.utils.torch_utilsrrrrrrrrrs