+ j^RIHt^RIHtHtHtHt^RIt^RIHt^RI H t ^RI H t !RR] 4t!R R ] 4t!R R ] 4t!R R] 4tR#))Sequence)AnyCallableOptionalUnionN)nn transforms) Transformcfaa]tRt^ toRtV3RlV3RlltV3RlRltV3RlRltRtVt V;t #) Composea_Composes several transforms together. This transform does not support torchscript. Please, see the note below. Args: transforms (list of ``Transform`` objects): list of transforms to compose. Example: >>> transforms.Compose([ >>> transforms.CenterCrop(10), >>> transforms.PILToTensor(), >>> transforms.ConvertImageDtype(torch.float), >>> ]) .. note:: In order to script the transformations, please use ``torch.nn.Sequential`` as below. >>> transforms = torch.nn.Sequential( >>> transforms.CenterCrop(10), >>> transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)), >>> ) >>> scripted_transforms = torch.jit.script(transforms) Make sure to use only scriptable transformations, i.e. that work with ``torch.Tensor``, does not require `lambda` functions or ``PIL.Image``. c4<V^8dQhRS[S[,RR/#r returnNrr)format __classdict__s"e/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/transforms/v2/_container.py __annotate__Compose.__annotate__) %%8H#5%$%c<\SV`4\V\4'g \ R4hV'g \ R4hWnR#5Argument transforms should be a sequence of callablesPass at least one transformN)super__init__ isinstancer TypeError ValueErrorr selfr __class__s&&rrCompose.__init__)s; *h//ST T:; ;$rc&<V^8dQhRS[RS[/#rinputsrr)rrs"rrr1sssrcn\V4^8pVPFpV!V!pV'dTMV3pK X#)lenr r$r)needs_unpacking transformoutputss&* rforwardCompose.forward1s9f+/I(G /WgZF)rc <V^8dQhRS[/#rrstr)rrs"rrr8((C(rcv.pVPFpVPRV 24K RPV4#z  r appendjoinr$ format_stringts& r extra_reprCompose.extra_repr88 A  4s ,!yy''rr ) __name__ __module__ __qualname____firstlineno____doc__rr3rC__static_attributes____classdictcell__ __classcell__r%rs@@rr r s-:%%(((rr caa]tRt^?toRt]P tR V3RlV3RllltV3RlRlt V3RlRlt V3RlR lt R t Vt V;t#) RandomApplyaApply randomly a list of transformations with a given probability. .. note:: In order to script the transformation, please use ``torch.nn.ModuleList`` as input instead of list/tuple of transforms as shown below: >>> transforms = transforms.RandomApply(torch.nn.ModuleList([ >>> transforms.ColorJitter(), >>> ]), p=0.3) >>> scripted_transforms = torch.jit.script(transforms) Make sure to use only scriptable transformations, i.e. that work with ``torch.Tensor``, does not require `lambda` functions or ``PIL.Image``. Args: transforms (sequence or torch.nn.Module): list of transformations p (float): probability of applying the list of transforms cd<V^8dQhRS[S[S[,S[P3,RS[RR/#rr prN)rrrr ModuleListfloat)rrs"rrRandomApply.__annotate__Us7  5();R]])J#K PU `d rc<\SV`4\V\\P 34'g \ R4hV'g \R4hWnRTu;8:dR8:gM\R4hW n R#)zJArgument transforms should be a sequence of callables or a `nn.ModuleList`rgg?z@`p` should be a floating point value in the interval [0.0, 1.0].N) rrr rrrTr!r"r rS)r$r rSr%s&&&rrRandomApply.__init__Us` *x&?@@hi i:; ;$qC_` `rc6<V^8dQhRS[S[S[3,/#r6)dictr8r)rrs"rrrVbs<<$sCx.>#doo"67C,I(G /WgZF8rr r{rNs@@rr}r}s#%%rr})collections.abcrtypingrrrrrar torchvisionr rhtorchvision.transforms.v2r r rPrkr}rrrsM$11 1/1(i1(h5()5(p#"9#"L)r