+ &jf^RIt^RIHtHt^RIHt^RIHt^RIHtH t H t R.t !RR]4t R#)N)nanTensor) constraints) Distribution) lazy_propertylogits_to_probsprobs_to_logits Categoricalcaa]tRt^ toRtR]P R]P/tRt RV3RlV3Rlllt RV3Rllt Rt ]P!R^R 7R 4t]V3R lR l4t]V3R lRl4t]V3RlRl4t]V3RlRl4t]V3RlRl4t]V3RlRl4t]P0!43RltRtRtRRltRtVtV;t#)r ax Creates a categorical distribution parameterized by either :attr:`probs` or :attr:`logits` (but not both). .. note:: It is equivalent to the distribution that :func:`torch.multinomial` samples from. Samples are integers from :math:`\{0, \ldots, K-1\}` where `K` is ``probs.size(-1)``. If `probs` is 1-dimensional with length-`K`, each element is the relative probability of sampling the class at that index. If `probs` is N-dimensional, the first N-1 dimensions are treated as a batch of relative probability vectors. .. note:: The `probs` argument must be non-negative, finite and have a non-zero sum, and it will be normalized to sum to 1 along the last dimension. :attr:`probs` will return this normalized value. The `logits` argument will be interpreted as unnormalized log probabilities and can therefore be any real number. It will likewise be normalized so that the resulting probabilities sum to 1 along the last dimension. :attr:`logits` will return this normalized value. See also: :func:`torch.multinomial` Example:: >>> # xdoctest: +IGNORE_WANT("non-deterministic") >>> m = Categorical(torch.tensor([ 0.25, 0.25, 0.25, 0.25 ])) >>> m.sample() # equal probability of 0, 1, 2, 3 tensor(3) Args: probs (Tensor): event probabilities logits (Tensor): event log probabilities (unnormalized) probslogitsTcZ<V^8dQhRS[R,RS[R,RS[R,RR/#)r Nr validate_argsreturn)rbool)format __classdict__s"w/Users/jameslopez/projects/CWCArchive/cwc-podcast/.venv/lib/python3.14/site-packages/torch/distributions/categorical.py __annotate__Categorical.__annotate__8sECC}C Cd{ C  Cc<VRJVRJ8Xd \R4hVe@VP4^8d \R4hWPR RR7, VnMMVf \ R4hVP4^8d \R4hW"P R RR7, VnVe VPM VP VnVPP4R ,Vn VPP4^8dVPP4RR M\P!4p\SV`9WCR7R#) Nz;Either `probs` or `logits` must be specified, but not both.z3`probs` parameter must be at least one-dimensional.T)keepdimzlogits is unexpectedly Nonez4`logits` parameter must be at least one-dimensional.)dimrr) ValueErrorrsumr AssertionError logsumexpr _paramsize _num_events ndimensiontorchSizesuper__init__)selfr r r batch_shape __class__s&&&& rr)Categorical.__init__8s TMv~ .M   yy{Q !VWW2t!< 0##BECE++,,""  ))  #(**,F5 r) r&rrtorch.distributionsr torch.distributions.distributionrtorch.distributions.utilsrrr __all__r rrrs0 +9UU /^,^r