$h ,ddlZddlmZddlmZmZmZmZmZmZm Z ddl m Z m Z ddgZ GddeZd d ed ed ed ze_ dde ede ede ede ede edededededededefdZde ede ede ede edededededededefdZde ede ede ede edededededededefdZdS)N)Tensor) Optimizer_use_grad_for_differentiable_default_to_fused_or_foreach_differentiable_doc _foreach_doc _maximize_doc _view_as_real)ListOptionalAdadeltaadadeltacteZdZ dddddeed ed effd Zfd Zd ZeddZ xZ S)r??ư>rNF)maximizedifferentiableforeachrrc Jd|kstd|d|cxkrdksntd|d|kstd|d|kstd|t|||||||} t|| dS)NgzInvalid learning rate: rzInvalid rho value: zInvalid epsilon value: zInvalid weight_decay value: )lrrhoeps weight_decayrrr) ValueErrordictsuper__init__) selfparamsrrrrrrrdefaults __class__s T/var/www/html/auto_sub_bot/venv/lib/python3.11/site-packages/torch/optim/adadelta.pyrzAdadelta.__init__ sbyy;r;;<< <c    S    838899 9czz)r2 enable_gradr(r@r)r closurelossr+r:r;r<r=rrrrrrrr>s r$r-z Adadelta.stepPsZ  "$$ ! !wyy ! ! ! ! ! ! ! ! ! ! ! ! ! ! !&  E! EKJd e e n%i j!&'M IBS,>**52BE;XbccK  )!-'      s /33)rrrrN)N) __name__ __module__ __qualname__r boolrr'r@rr- __classcell__)r#s@r$rr s   "&+$+++$++++++++@66666:",,,"!,,,,,r%aImplements Adadelta algorithm. .. math:: \begin{aligned} &\rule{110mm}{0.4pt} \\ &\textbf{input} : \gamma \text{ (lr)}, \: \theta_0 \text{ (params)}, \: f(\theta) \text{ (objective)}, \: \rho \text{ (decay)}, \: \lambda \text{ (weight decay)} \\ &\textbf{initialize} : v_0 \leftarrow 0 \: \text{ (square avg)}, \: u_0 \leftarrow 0 \: \text{ (accumulate variables)} \\[-1.ex] &\rule{110mm}{0.4pt} \\ &\textbf{for} \: t=1 \: \textbf{to} \: \ldots \: \textbf{do} \\ &\hspace{5mm}g_t \leftarrow \nabla_{\theta} f_t (\theta_{t-1}) \\ &\hspace{5mm}if \: \lambda \neq 0 \\ &\hspace{10mm} g_t \leftarrow g_t + \lambda \theta_{t-1} \\ &\hspace{5mm} v_t \leftarrow v_{t-1} \rho + g^2_t (1 - \rho) \\ &\hspace{5mm}\Delta x_t \leftarrow \frac{\sqrt{u_{t-1} + \epsilon }}{ \sqrt{v_t + \epsilon} }g_t \hspace{21mm} \\ &\hspace{5mm} u_t \leftarrow u_{t-1} \rho + \Delta x^2_t (1 - \rho) \\ &\hspace{5mm}\theta_t \leftarrow \theta_{t-1} - \gamma \Delta x_t \\ &\rule{110mm}{0.4pt} \\[-1.ex] &\bf{return} \: \theta_t \\[-1.ex] &\rule{110mm}{0.4pt} \\[-1.ex] \end{aligned} For further details regarding the algorithm we refer to `ADADELTA: An Adaptive Learning Rate Method`_. a Args: params (iterable): iterable of parameters to optimize or dicts defining parameter groups rho (float, optional): coefficient used for computing a running average of squared gradients (default: 0.9). A higher value of `rho` will result in a slower average, which can be helpful for preventing oscillations in the learning process. eps (float, optional): term added to the denominator to improve numerical stability (default: 1e-6). lr (float, optional): coefficient that scale delta before it is applied to the parameters (default: 1.0) weight_decay (float, optional): weight decay (L2 penalty) (default: 0) z zd .. _ADADELTA\: An Adaptive Learning Rate Method: https://arxiv.org/abs/1212.5701 Fr!r;r<r=rrr>rrrrrc |t||d\} }|r-tjrt d|r&tjst } nt } | ||||||| | | || dS)zvFunctional API that performs Adadelta algorithm computation. See :class:`~torch.optim.Adadelta` for details. NF) use_fusedz6torch.jit.script not supported with foreach optimizers)rrrrrrr>)rr2jit is_scriptingr6_multi_tensor_adadelta_single_tensor_adadelta)r!r;r<r=rrr>rrrrr_funcs r$rrs,1&.TYZZZ 7U59))++USTTT'uy--//'%&D   !%      r%cvt||||D]\} } } }|s| n| } |dkr| | |} tj| rparamr1r/r0stddeltas r$rOrOs14{J11%%,j)$.tt$ 1  88E866D  E " " ,+J77J*955I%d++D%%dDC%@@@nnS!!'')) c""((**  "KKMME 3T"""s$$UES$AAA  E " " 1)%00E 5 $$$$/%%r%cd| r Jdt|dkrdStj||||g} | D]`\\} } }}}|rt j| } | rt | | |||dkr1|rt j| | |nt j| | |} t j ||t j || | d|z t j||}t j |t j||}t j |t j ||t j || t j| || t j ||t j |||d|z bdS)Nz#_foreach ops don't support autogradrrSrrU) r7r"_group_tensors_by_device_and_dtypevaluesr2 _foreach_negr _foreach_add_ _foreach_add _foreach_mul__foreach_addcmul__foreach_sqrt_ _foreach_div_)r!r;r<r=rrrrrrr>grouped_tensors device_params device_gradsdevice_square_avgsdevice_acc_deltasrPrbdeltass r$rNrN sDDDDD  6{{aBFES^`jCkllOUdUkUkUmUmRRQ M-'9;Lq  < -l;;L  ^ -7IK\ ] ] ] 1   c#L-|TTTTT$1, Uabbb  .444  2L,VWZ]V]^^^^ !3S99 S!!!#$5s;; V$$$ FC((( FL111 M6"==== -s333  166SQQQQQ9RRr%)NFF)r2r optimizerrrrrr r r typingr r __all__r__doc__rHfloatrrOrNr%r$rzs  YYYYYYYYYYYYYYYYYY!!!!!!!! z "rrrrryrrrj6           7/r# -- L- <-f-V -d^--- - - ------`&% L&% <&%f&%V &%  &% &% &%&%&%&%&%&%&%&%R1R L1R <1Rf1RV 1R  1R1R 1R 1R1R1R1R1R1R1R1R1Rr%