+ j1l^RIt^RIHt^RIt^RIHt^RIHt^RIHt^RI H t R.t !RR4t R#) N) deprecatedTensor) constraints) lazy_property_size Distributioncaa]tRt^toRtRtRtRt]V3RlRl4t ] P!4] P!4R3V3RlV3Rlllt R7V3R lR llt ]V3R lR l4t]V3R lRl4t]V3RlRl4t]V3RlRl4t]V3RlRl4t]V3RlRl4t]V3RlRl4t]V3RlRl4t] P!43V3RlRllt] P!43V3RlRllt]!R]R 7V3R!lR"l4tV3R#lR$ltV3R%lR&ltV3R'lR(ltR8V3R)lR*lltV3R+lR,lt V3R-lR.lt!] P!43V3R/lR0llt"V3R1lR2lt#R7R3lt$V3R4lR5lt%R6t&Vt'V;t(#)9r a; Distribution is the abstract base class for probability distributions. Args: batch_shape (torch.Size): The shape over which parameters are batched. event_shape (torch.Size): The shape of a single sample (without batching). validate_args (bool, optional): Whether to validate arguments. Default: None. FTc$<V^8dQhRS[RR/#valuereturnN)bool)format __classdict__s"a/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torch/distributions/distribution.py __annotate__Distribution.__annotate__s,,,$,c 6VR9d\hV\nR#)a] Sets whether validation is enabled or disabled. The default behavior mimics Python's ``assert`` statement: validation is on by default, but is disabled if Python is run in optimized mode (via ``python -O``). Validation may be expensive, so you may want to disable it once a model is working. Args: value (bool): Whether to enable validation. N)TF) ValueErrorr _validate_args)rs&rset_default_validate_args&Distribution.set_default_validate_argss  % &+ #rNcf<V^8dQhRS[PRS[PRS[R,RR/#)r batch_shape event_shape validate_argsNr)torchSizer)rrs"rrr.s?&&ZZ&ZZ&d{ &  &rc<WnW nVeW0nVP'Ed VPpVP4FwrV\P!V4'dK#WPP9d,\\\V4V4\4'dK^\W4pVP!V4p\"P$!V4'dK\'RV R\V4P( R\+VP,4 R\/V4 R \/V4 R V 2 4h \0S V`e4R# \d:/p\ P !TP R2R,R,^R7ELRi;i) Nz$ does not define `arg_constraints`. zAPlease set `arg_constraints = {}` or initialize the distribution z2with `validate_args=False` to turn off validation. stacklevelzExpected parameter z ( of shape z) of distribution z to satisfy the constraint , but found invalid values: ) _batch_shape _event_shaperarg_constraintsNotImplementedErrorwarningswarn __class__itemsr is_dependent__dict__ isinstancegetattrtypercheckr! _is_all_truer__name__tupleshapereprsuper__init__) selfrrr r*param constraintrvalidr.s &&&& rr<Distribution.__init__.s~ ('  $"/      "&"6"6&5%:%:%<!++J77 -*DJ. 33,"((/))%00$-eW5 K001E%++&=" 3' "$ ~~&&JKYZJK !  s EAF  F c <V^8dQhRS[/#)rrr)rrs"rrrVs""%"rc \h)a Returns a new distribution instance (or populates an existing instance provided by a derived class) with batch dimensions expanded to `batch_shape`. This method calls :class:`~torch.Tensor.expand` on the distribution's parameters. As such, this does not allocate new memory for the expanded distribution instance. Additionally, this does not repeat any args checking or parameter broadcasting in `__init__.py`, when an instance is first created. Args: batch_shape (torch.Size): the desired expanded size. _instance: new instance provided by subclasses that need to override `.expand`. Returns: New distribution instance with batch dimensions expanded to `batch_shape`. r+)r=r _instances&&&rexpandDistribution.expandVs &"!rc4<V^8dQhRS[P/#rrr!r")rrs"rrrl!!UZZ!rc VP#)z6 Returns the shape over which parameters are batched. )r(r=s&rrDistribution.batch_shapek    rc4<V^8dQhRS[P/#rIrJ)rrs"rrrsrKrc VP#)z: Returns the shape of a single sample (without batching). )r)rMs&rrDistribution.event_shaperrOrcJ<V^8dQhRS[S[S[P3,/#rI)dictstrr Constraint)rrs"rrrzs$""c;+A+A&A!B"rc \h)z Returns a dictionary from argument names to :class:`~torch.distributions.constraints.Constraint` objects that should be satisfied by each argument of this distribution. Args that are not tensors need not appear in this dict. rDrMs&rr*Distribution.arg_constraintsy "!rcB<V^8dQhRS[PR,/#)rrN)rrV)rrs"rrrs""//$6"rc \h)zq Returns a :class:`~torch.distributions.constraints.Constraint` object representing this distribution's support. rDrMs&rsupportDistribution.support "!rc <V^8dQhRS[/#rIr)rrs"rrrs""f"rc \h)z' Returns the mean of the distribution. rDrMs&rmeanDistribution.mean "!rc <V^8dQhRS[/#rIr)rrs"rrrsOOfOrc 2\VP R24h)z' Returns the mode of the distribution. z does not implement mode)r+r.rMs&rmodeDistribution.modes "T^^$44L"MNNrc <V^8dQhRS[/#rIr)rrs"rrrs""&"rc \h)z+ Returns the variance of the distribution. rDrMs&rvarianceDistribution.variancercrc <V^8dQhRS[/#rIr)rrs"rrrs$$$rc 6VPP4#)z5 Returns the standard deviation of the distribution. )rjsqrtrMs&rstddevDistribution.stddevs }}!!##rc&<V^8dQhRS[RS[/#r sample_shaperr r)rrs"rrrs..5.F.rc \P!4;_uu_4VPV4uuRRR4# +'giR#;i)z| Generates a sample_shape shaped sample or sample_shape shaped batch of samples if the distribution parameters are batched. N)r!no_gradrsampler=rss&&rsampleDistribution.samples' ]]__<< -___s : A c&<V^8dQhRS[RS[/#rrrt)rrs"rrrs""E"V"rc \h)z Generates a sample_shape shaped reparameterized sample or sample_shape shaped batch of reparameterized samples if the distribution parameters are batched. rDrxs&&rrwDistribution.rsampler^rz=`sample_n(n)` will be deprecated. Use `sample((n,))` instead.)categoryc&<V^8dQhRS[RS[/#)rnr)intr)rrs"rrrs--#-&-rc NVP\P!V344#)zY Generates n samples or n batches of samples if the distribution parameters are batched. )ryr!r")r=rs&&rsample_nDistribution.sample_ns{{5::qd+,,rc&<V^8dQhRS[RS[/#rrrr)rrs"rrrs""f""rc \h)zk Returns the log of the probability density/mass function evaluated at `value`. Args: value (Tensor): rDr=rs&&rlog_probDistribution.log_probrYrc&<V^8dQhRS[RS[/#rr)rrs"rrrs"""F"rc \h)z_ Returns the cumulative density/mass function evaluated at `value`. Args: value (Tensor): rDrs&&rcdfDistribution.cdfrYrc&<V^8dQhRS[RS[/#rr)rrs"rrrs""&"V"rc \h)zg Returns the inverse cumulative density/mass function evaluated at `value`. Args: value (Tensor): rDrs&&ricdfDistribution.icdfrYrc&<V^8dQhRS[RS[/#)rrFr)rr)rrs"rrrs""""rc \h)a Returns tensor containing all values supported by a discrete distribution. The result will enumerate over dimension 0, so the shape of the result will be `(cardinality,) + batch_shape + event_shape` (where `event_shape = ()` for univariate distributions). Note that this enumerates over all batched tensors in lock-step `[[0, 0], [1, 1], ...]`. With `expand=False`, enumeration happens along dim 0, but with the remaining batch dimensions being singleton dimensions, `[[0], [1], ..`. To iterate over the full Cartesian product use `itertools.product(m.enumerate_support())`. Args: expand (bool): whether to expand the support over the batch dims to match the distribution's `batch_shape`. Returns: Tensor iterating over dimension 0. rD)r=rFs&&renumerate_supportDistribution.enumerate_supports ,"!rc <V^8dQhRS[/#rIr)rrs"rrrs"""rc \h)zg Returns entropy of distribution, batched over batch_shape. Returns: Tensor of shape batch_shape. rDrMs&rentropyDistribution.entropys "!rc <V^8dQhRS[/#rIr)rrs"rrrs))F)rc J\P!VP44#)zj Returns perplexity of distribution, batched over batch_shape. Returns: Tensor of shape batch_shape. )r!exprrMs&r perplexityDistribution.perplexitysyy((rc:<V^8dQhRS[RS[P/#rr)r r!r")rrs"rrr s# P PE PUZZ Prc \V\P4'g\P!V4p\P!WP,VP,4#)a@ Returns the size of the sample returned by the distribution, given a `sample_shape`. Note, that the batch and event shapes of a distribution instance are fixed at the time of construction. If this is empty, the returned shape is upcast to (1,). Args: sample_shape (torch.Size): the size of the sample to be drawn. )r2r!r"r(r)rxs&&r_extended_shapeDistribution._extended_shape sF, 33 ::l3Lzz,):)::T=N=NNOOrc$<V^8dQhRS[RR/#r r)rrs"rrrs22f22rc  \V\P4'g \R4h\ VP 44\ VP 4, pVP 4VRVP 8wd+\RVP 4 RVP R24hVP 4pVPVP ,p\\V4\V44F/wrVV^8wgKV^8wgKWV8wgK\RV RV R24h VPpTf \R 4hTP!T4p\P"!T4'gS\R \%T4P& R \)TP*4 R\-T4 R\-T4 RT 2 4hR# \d8\P!TP R2R,R ,^R 7R#i;i)a Argument validation for distribution methods such as `log_prob`, `cdf` and `icdf`. The rightmost dimensions of a value to be scored via these methods must agree with the distribution's batch and event shapes. Args: value (Tensor): the tensor whose log probability is to be computed by the `log_prob` method. Raises ValueError: when the rightmost dimensions of `value` do not match the distribution's batch and event shapes. z/The value argument to log_prob must be a TensorNz5The right-most size of value must match event_shape: z vs .z9Value is not broadcastable with batch_shape+event_shape: z% does not define `support` to enable z;sample validation. Please initialize the distribution with z-`validate_args=False` to turn off validation.r$zsupport is unexpectedly NonezExpected value argument (r&z) to be within the support (z) of the distribution r')r2r!rrlensizer)r(zipreversedr\r+r,r-r.AssertionErrorr5r6r4r7r8r9r:) r=revent_dim_start actual_shapeexpected_shapeijr\r@s && r_validate_sampleDistribution._validate_samples%..NO Oejjl+c$2C2C.DD ::<( )T->-> >G ~UYZ^ZkZkYllmn zz| **T->->>.0HIDAAv!q&QV OP\~]abpaqqrsJ llG ? !?@ @ e$!!%((K(()E%++4F3GH--1']O<''+Dzl3..3W 6 )#  MM>>""GHOPAB    s* G>HHcVfU\V4PVP8wd1\RVPP RVP R24hVfVP \V44#T#)Nz Subclass z of zR that defines a custom __init__ method must also define a custom .expand() method.)r4r<r+r.r7__new__)r=clsrEs&&&r_get_checked_instance"Distribution._get_checked_instanceLsp  d!4!4 !D%DNN334DG>> ,5+rs2( +3  MAMAr