DŽg-O$*dZddlmZmZmZmZddlZddlmZddlm Z m Z m Z m Z m Z mZmZmZmZmZmZmZddgZGd deZd d e d ed e d e d ze_deedeedeedeedeedeededededededededededef dZdeedeedeedeedeedeededededededededededef dZe e  d#deedeedeedeedeedeed!eededededededededededef"d"Zy)$z)Implementation for the RMSprop algorithm.)castListOptionalUnionN)Tensor) _capturable_doc_default_to_fused_or_foreach_differentiable_doc_disable_dynamo_if_unsupported _foreach_doc!_get_capturable_supported_devices_get_scalar_dtype _maximize_doc_use_grad_for_differentiable _view_as_real OptimizerParamsTRMSproprmspropceZdZ ddedeeefdededededeeded effd Z fd Z d Z e dd Z xZS)rparamslralphaeps weight_decaymomentumforeachmaximizedifferentiablec jt|tr|jdk7r tdd|kstd|d|kstd|d|kstd|d|kstd|d|kstd|t |||||||| | | } t ||| y) NrzTensor lr must be 1-elementgzInvalid learning rate: zInvalid epsilon value: zInvalid momentum value: zInvalid weight_decay value: zInvalid alpha value: ) rrrrcenteredr capturablerrr ) isinstancernumel ValueErrordictsuper__init__)selfrrrrrrr"r#rrr defaults __class__s [/home/mcse/projects/flask_80/flask-venv/lib/python3.12/site-packages/torch/optim/rmsprop.pyr)zRMSprop.__init__s b& !bhhjAo:; ;by6rd;< <cz6se<= =h7zBC Cl";L>JK Ke|4UG<= =%!)   *c|t|||jD]}|jdd|jdd|jdd|jdd|jdd|jdd|d D]}|jj |g}t |dk7s.tj|d rGt|d }|dr*tj|t|j ntj|t |d <y) Nrrr"Frrr r#rstepdtypedevicer2) r( __setstate__ param_groups setdefaultstategetlentorch is_tensorfloattensorrr3)r*r8grouppp_statestep_valr,s r-r5zRMSprop.__setstate__Fs U#&& E   Z +   Z /   Y -   Z /   -u 5   \5 18_ **..B/w<1$U__WV_-M$WV_5H !. $,=,?#\\(:K:MN FO  r.cd}|dD]} | j|tj| z}|j| | jjr t d|j| j|j | } t| dk(r|dr*tjdt| jntjdt| d <tj| tj | d <|d dkDr(tj| tj | d <|dr(tj| tj | d<|j| d |j| d |d dkDr|j| d |ds|j| d|S)NFrz)RMSprop does not support sparse gradientsrr#r1r4r0) memory_format square_avgrmomentum_bufferr"grad_avg) gradr; is_complexappend is_sparse RuntimeErrorr8r:zerosrr3 zeros_likepreserve_format) r*r?params_with_gradgrads square_avgsmomentum_buffer_list grad_avgs state_steps has_complexr@r8s r- _init_groupzRMSprop._init_group[s x$ 4Avv~ 5++A. .K  # #A &vv"#NOO LL JJqME5zQ\*KK*;*=ahhOR/@/BCf ',&6&6U%:%:'l#$q(/4/?/?)>)>0E+,$(-(8(8)>)>)E*%   u\2 3   uV} -Z 1$$++E2C,DEZ   z!23I$ 4Lr.cj|jd}|$tj5|}ddd|jD]_}g}g}g}g}g}g} |j ||||||| } t |||||| |d|d|d|d|d|d|d|d |d |d | a|S#1swYyxYw) zPerform a single optimization step. Args: closure (Callable, optional): A closure that reevaluates the model and returns the loss. Nrrrrrr"rrr r#) rrrrrr"rrr r#rW) _cuda_graph_capture_health_checkr; enable_gradr6rXr) r*closurelossr?rQrRrSrUrTrVrWs r-r0z RMSprop.steps --/  ""$ !y !&&$ E-/ "$E(*K&(I13 (*K** $K  $;Gn%L">2z*z*i(z*$%56 .'# %$ L S ! !s B))B2) g{Gz?gGz?g:0yE>rrFFNFFN)__name__ __module__ __qualname__rrr=rrboolr)r5rXrr0 __classcell__)r,s@r-rrs$("&$'+'+ %- '+ '+  '+  '+'+$'+'+'+R*1f"4"4r.a Implements RMSprop algorithm. .. math:: \begin{aligned} &\rule{110mm}{0.4pt} \\ &\textbf{input} : \alpha \text{ (alpha)},\: \gamma \text{ (lr)}, \: \theta_0 \text{ (params)}, \: f(\theta) \text{ (objective)} \\ &\hspace{13mm} \lambda \text{ (weight decay)},\: \mu \text{ (momentum)},\: centered\\ &\textbf{initialize} : v_0 \leftarrow 0 \text{ (square average)}, \: \textbf{b}_0 \leftarrow 0 \text{ (buffer)}, \: g^{ave}_0 \leftarrow 0 \\[-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 \alpha v_{t-1} + (1 - \alpha) g^2_t \hspace{8mm} \\ &\hspace{5mm} \tilde{v_t} \leftarrow v_t \\ &\hspace{5mm}if \: centered \\ &\hspace{10mm} g^{ave}_t \leftarrow g^{ave}_{t-1} \alpha + (1-\alpha) g_t \\ &\hspace{10mm} \tilde{v_t} \leftarrow \tilde{v_t} - \big(g^{ave}_{t} \big)^2 \\ &\hspace{5mm}if \: \mu > 0 \\ &\hspace{10mm} \textbf{b}_t\leftarrow \mu \textbf{b}_{t-1} + g_t/ \big(\sqrt{\tilde{v_t}} + \epsilon \big) \\ &\hspace{10mm} \theta_t \leftarrow \theta_{t-1} - \gamma \textbf{b}_t \\ &\hspace{5mm} else \\ &\hspace{10mm}\theta_t \leftarrow \theta_{t-1} - \gamma g_t/ \big(\sqrt{\tilde{v_t}} + \epsilon \big) \hspace{3mm} \\ &\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 `lecture notes `_ by G. Hinton. and centered version `Generating Sequences With Recurrent Neural Networks `_. The implementation here takes the square root of the gradient average before adding epsilon (note that TensorFlow interchanges these two operations). The effective learning rate is thus :math:`\gamma/(\sqrt{v} + \epsilon)` where :math:`\gamma` is the scheduled learning rate and :math:`v` is the weighted moving average of the squared gradient. a Args: params (iterable): iterable of parameters to optimize or dicts defining parameter groups lr (float, Tensor, optional): learning rate (default: 1e-2) momentum (float, optional): momentum factor (default: 0) alpha (float, optional): smoothing constant (default: 0.99) eps (float, optional): term added to the denominator to improve numerical stability (default: 1e-8) centered (bool, optional) : if ``True``, compute the centered RMSProp, the gradient is normalized by an estimation of its variance weight_decay (float, optional): weight decay (L2 penalty) (default: 0) z z rrRrSrUrTrVrrrrrr"rr r#rWc pt|D]'\}}||}tjjs\|rZt }|j j |j j k(r|j j |vs Jd|d||}| s|n| }||}|dz }| dk7r|j|| }tj|}|r?tj|}tj|}tj|}|j|j||d|z | rT||}|rtj|}|j|d|z |j||dj}n|j}| r|j|}n|j!|}| dkDrS||}|rtj|}|j| j#|||j!|| |j#||| *y)NIIf capturable=True, params and state_steps must be on supported devices: .rrrvalue) enumerater;_utils is_compilingrr3typeaddrJ view_as_realmul_addcmul_lerp_addcmulsqrt_sqrtadd_addcdiv_)rrRrSrUrTrVrrrrrr"rr r#rWiparamr0capturable_supported_devicesrIrFis_complex_paramrHavgbufs r-_single_tensor_rmsproprs&f%1151~||((*z+L+N ( !!T[[%5%55LL%%)EE {[[wZxxyz {FQx#t$ ^    1 88E86D ++E2 &&u-E%%d+D++J7J''d!e)'D  |H --h7 NN4U +$$Xxr$BHHJC//#C ''#,C((3-C a<&q)C((- HHX  ' 'c 2 JJs2#J & NN4RCN 0c11r.c 2!t|dk(ry| rJdtjjs5|r3t !t !fdt ||Ds Jd!dtj||||||g}|jD]|\\}}}}}}}ttt|}ttt|}ttt|}ttt|}|rg||g}| dkDr(ttt|}|j|| r(ttt|}|j|t|g|| rtj|}tjjs=|dj r.tj"|tj$ddd ntj"|d | dk7r3| rtj"||| ntj&||| }tj(||tj*|||d |z | rvttt|}tj,||d |z tj.|||d }tj0|tj"||n+tj2|}tj"||| dkDrttt|}tj(|| tj4||||rIt7|tjr/tj8|| } tj"|| tj"||| |rJt7|tjr0tj:|| tj4|||ctj4|||| y) Nrz#_foreach ops don't support autogradc3K|]N\}}|jj|jjk(xr|jjvPywr^)r3rn).0r@r0r{s r- z(_multi_tensor_rmsprop..isQ 4 HHMMT[[-- - > !== > sAArerfg?cpu)r3rgrrhrj)r:r;rlrmrallzipr"_group_tensors_by_device_and_dtypevaluesrrrrKr _foreach_negis_cpu _foreach_add_r> _foreach_add _foreach_mul__foreach_addcmul__foreach_lerp__foreach_addcmul_foreach_sqrt_ _foreach_sqrt_foreach_addcdiv_r$ _foreach_mul _foreach_div_)"rrRrSrUrTrVrrrrrr"rr r#rWgrouped_tensorsgrouped_params_grouped_grads_grouped_square_avgs_grouped_grad_avgs_grouped_momentum_buffer_list_grouped_state_steps__grouped_params grouped_gradsgrouped_square_avgsgrouped_state_stepsstate_and_gradsgrouped_momentum_buffer_listgrouped_grad_avgsr} momentum_lrr{s" @r-_multi_tensor_rmsproprNs& 6{aDDD  << $ $ &:'H'J$ v{3   wWWsVttu v  w  BB  Y0DkRO  " " $YW     ) d6lO<T&\>: "4<1EF"4<1EF ,.ABO!|/3L"?0, &&'CD$(f7I$J!&&'89 . ;? ; !..}=M ||((*/B1/E/L/L   #U\\#e%DC     3Q 7 1 ##M>V % 2 2!>!  /7   QY   $T&\3E F   !2M1u9 M((#%68IQSC   %   S )%%&9:C   S ) a<+/V ;, (    .s 3() 1ell#3s$&zPAPI has changed, `state_steps` argument must contain a list of singleton tensorsNF) use_fusedz6torch.jit.script not supported with foreach optimizers) rrrrrr"rr#r rW) r;rlrmrrMr jit is_scriptingrr)rrRrSrUrTrVrrr r#rWrrrrrr"rfuncs r-rrs: << $ $ &s3-830 ^  1 Ne 7599))+STTuyy--/$%   !%!r.)NFFFF)__doc__typingrrrrr;r optimizerr r r r r rrrrrrr__all__rr=rbrrrrDr.r-rs71..      i gigV*V     W<BD1 LD1 <D1fD1F| D1 v, D1 f D1 D1 D1 D1D1D1D1D1D1 !D1"#D1N}W L}W <}Wf}WF| }W v, }W f }W }W }W }W}W}W}W}W}W !}W"#}W@ 1GH# A LA <AfAF| A v, A f Ad^AAAAA A !A" #A$%A&'A()AIAr.