Xj1fddlmZddlmZmZmZddlmZmZm Z ddl m Z ddl m Z mZddlmZgdZe dd Zd ed efd Ze dGddee Ze dGddeZe dGddee ZdS)) defaultdict)CallableIteratorSized)AnyNoReturnTypeVar)functional_datapipe) DataChunk IterDataPipe)_check_unpickable_fn)BatcherIterDataPipeGrouperIterDataPipeUnBatcherIterDataPipe_T_coT) covariantnamereturnc6tdtd|)Nzmodule z has no attribute )AttributeError__name__)rs VC:\Projects\DSCons\.venv\Lib\site-packages\torch\utils\data\datapipes\iter\grouping.py __getattr__rs! E8EEtEE F FFbatchc eZdZUdZeed<eed<eed<defdededede eddf fd Z de efd Z defd Z xZS) ra2 Creates mini-batches of data (functional name: ``batch``). An outer dimension will be added as ``batch_size`` if ``drop_last`` is set to ``True``, or ``length % batch_size`` for the last batch if ``drop_last`` is set to ``False``. Args: datapipe: Iterable DataPipe being batched batch_size: The size of each batch drop_last: Option to drop the last batch if it's not full wrapper_class: wrapper to apply onto each batch (type ``List``) before yielding, defaults to ``DataChunk`` Example: >>> # xdoctest: +SKIP >>> from torchdata.datapipes.iter import IterableWrapper >>> dp = IterableWrapper(range(10)) >>> dp = dp.batch(batch_size=3, drop_last=True) >>> list(dp) [[0, 1, 2], [3, 4, 5], [6, 7, 8]] datapipe batch_size drop_lastF wrapper_classrNc|dkrtdt||_||_||_||_dS)Nrz+Batch size is required to be larger than 0!)AssertionErrorsuper__init__rrrr )selfrrrr __class__s rr$zBatcherIterDataPipe.__init__5sV ?? !NOO O   $"*rc#Kg}|jD]H}||t||jkr||Vg}It|dkr |js||VdSdSdSNr)rappendlenrr r)r%rxs r__iter__zBatcherIterDataPipe.__iter__Ds  A LLOOO5zzT_,,((///// u::>>> 0((/////// > 0 0rct|jtrJ|jrt |j|jzSt |j|jzdz |jzSt t|jd)Nz# instance doesn't have valid length) isinstancerrrr*r TypeErrortyperr%s r__len__zBatcherIterDataPipe.__len__Os| dmU + + Y~ U4=))T_<<DM**T_>> # xdoctest: +SKIP >>> from torchdata.datapipes.iter import IterableWrapper >>> source_dp = IterableWrapper([[[0, 1], [2]], [[3, 4], [5]], [[6]]]) >>> dp1 = source_dp.unbatch() >>> list(dp1) [[0, 1], [2], [3, 4], [5], [6]] >>> dp2 = source_dp.unbatch(unbatch_level=2) >>> list(dp2) [0, 1, 2, 3, 4, 5, 6] r.r unbatch_levelrNc"||_||_dSN)rr=)r%rr=s rr$zUnBatcherIterDataPipe.__init__rs  *rc#bK|jD]$}|||jEd{V%dS)Nr=)r_diver=)r%elements rr,zUnBatcherIterDataPipe.__iter__vsS} M MGzz'9KzLL L L L L L L L L M Mrc#K|dkrtd|dkrFt|ttfr$|D]}||dEd{V dS|VdS|dkr|VdSt|ttfr'|D]"}|||dz Ed{V#dSt d|jd)Nz unbatch_level must be -1 or >= 0rArr.zunbatch_level z" exceeds the depth of the DataPipe) ValueErrorr/listr rB IndexErrorr=)r%rCr=items rrBzUnBatcherIterDataPipe._divezs: 2  ?@@ @ B  'D)#455 #BBD#zz$bzAAAAAAAAAABB a  MMMMM'D)#455 #QQD#zz$ma>OzPPPPPPPPPPQQ![T%7[[[r)r.) rr4r5r6r r8r$r,rBrrrrZsm,+++c+$++++MMMrrgroupbyceZdZdZdddddddeedeegefded e d e dzd e dzd ed dfdZ dZ dZ ddZ dZdZddZdS)ra Groups data from IterDataPipe by keys from ``group_key_fn``, yielding a ``DataChunk`` with batch size up to ``group_size``. (functional name: ``groupby``). The samples are read sequentially from the source ``datapipe``, and a batch of samples belonging to the same group will be yielded as soon as the size of the batch reaches ``group_size``. When the buffer is full, the DataPipe will yield the largest batch with the same key, provided that its size is larger than ``guaranteed_group_size``. If its size is smaller, it will be dropped if ``drop_remaining=True``. After iterating through the entirety of source ``datapipe``, everything not dropped due to the buffer capacity will be yielded from the buffer, even if the group sizes are smaller than ``guaranteed_group_size``. Args: datapipe: Iterable datapipe to be grouped group_key_fn: Function used to generate group key from the data of the source datapipe keep_key: Option to yield the matching key along with the items in a tuple, resulting in `(key, [items])` otherwise returning [items] buffer_size: The size of buffer for ungrouped data group_size: The max size of each group, a batch is yielded as soon as it reaches this size guaranteed_group_size: The guaranteed minimum group size to be yielded in case the buffer is full drop_remaining: Specifies if the group smaller than ``guaranteed_group_size`` will be dropped from buffer when the buffer is full Example: >>> import os >>> # xdoctest: +SKIP >>> from torchdata.datapipes.iter import IterableWrapper >>> def group_fn(file): ... return os.path.basename(file).split(".")[0] >>> source_dp = IterableWrapper( ... ["a.png", "b.png", "a.json", "b.json", "a.jpg", "c.json"] ... ) >>> dp0 = source_dp.groupby(group_key_fn=group_fn) >>> list(dp0) [['a.png', 'a.json', 'a.jpg'], ['b.png', 'b.json'], ['c.json']] >>> # A group is yielded as soon as its size equals to `group_size` >>> dp1 = source_dp.groupby(group_key_fn=group_fn, group_size=2) >>> list(dp1) [['a.png', 'a.json'], ['b.png', 'b.json'], ['a.jpg'], ['c.json']] >>> # Scenario where `buffer` is full, and group 'a' needs to be yielded since its size > `guaranteed_group_size` >>> dp2 = source_dp.groupby( ... group_key_fn=group_fn, ... buffer_size=3, ... group_size=3, ... guaranteed_group_size=2, ... ) >>> list(dp2) [['a.png', 'a.json'], ['b.png', 'b.json'], ['a.jpg'], ['c.json']] Fi'N)keep_key buffer_size group_sizeguaranteed_group_sizedrop_remainingr group_key_fnrMrNrOrPrQrct|||_||_||_||_t t |_d|_||_ d|_ |'|%d|cxkr|ksntd||_ |'|d|cxkr|ksntd||_ ||_ t|_dS)Nrz)group_size must be > 0 and <= buffer_sizezNguaranteed_group_size must be > 0 and <= group_size and group_size must be set)r rrRrMmax_buffer_sizerrGbuffer_elementscurr_buffer_sizerOrPr"rQr r )r%rrRrMrNrOrPrQs rr$zGrouperIterDataPipe.__init__s \***  (  *7B47H7H !$%)"  !k&= 1111k1111$%PQQQ)3D & ,!!.C*Q*Q*Q*Qz*Q*Q*Q*Q$d*?D &,&rcd}d}d}|jD]<}t|j||krt|j|}|}=|j:||jkr/|js(t dt |j||j ||jkr |j|}|xj|zc_|j|=|S)NrzFailed to group items)rUr*rPrQ RuntimeErrorstrrV)r% biggest_key biggest_sizeresult_to_yieldfindkeys r_remove_biggest_keyz'GrouperIterDataPipe._remove_biggest_keys  + & &G4'011L@@"4#7#@AA %   & 2t999':'T-A+-N)O)O   & .t999"2;?O -   -rc#VK|jD]}||}|j|||xjdz c_|j|jt |j|kr_||j|}|jr||fn|V|xjt |j|zc_|j|=|j|j kr:| }|$||}|jr||fn|Vt|j D][}||j |}|xjt |zc_|jr||fn|V\dS)Nr.)rrRrUr)rVrOr*r rMrTr^tuplekeyspop)r%r+keyresultr\s rr,zGrouperIterDataPipe.__iter__s E EA##A&&C   % , ,Q / / /  ! !Q & ! !*t#$S)CC00*.););Drzs######5555555555))))))))))EEEEEEGGGGGGGGHHHHHH    4(((GcGhGGGGW=Y=Y=Y=Y=Y,y1=Y=Y=Y@Y11111L11 1hYu%u%u%u%u%,y1u%u% u%u%u%r