Phu)ddlmZmZmZmZddlZddlmZddlmZm Z m Z m Z m Z m Z mZmZmZmZmZmZmZddlmZddgZGd deZd d ed ed ed ed ed ze_ d'deedeedeedeedeedeedeedededeedeedeedededededeeefded ed!ef(d"Zdeedeedeedeedeedeedeedeedededededeeefded ed!ededef$d#Zdeedeedeedeedeedeedeedeedededededeeefded ed!ededef$d$Zdeedeedeedeedeedeedeedeedededededeeefded ed!ededed%df&d&Zy)()ListOptionalUnionTupleN)Tensor) OptimizerParamsT_use_grad_for_differentiable _get_value_stack_if_compiling_dispatch_sqrt_default_to_fused_or_foreach_capturable_doc_differentiable_doc _foreach_doc _fused_doc _maximize_doc _view_as_real)$_get_fused_kernels_supported_devicesAdamadamceZdZ ddddddddedeeefdeeefdeded ed e ed ed ed ede effdZ fdZ dZ e ddZxZS)rFN)foreachmaximize capturabledifferentiablefusedparamslrbetaseps weight_decayamsgradrrrrrc < d|kstd|t|tr|r | s tdd|kstd|d|dcxkrdksntd|dd|dcxkrdksntd |dd|kstd |t|||||||| | | } t||| | rY| r t d d |_t t fd|jDst d d|r t dyy)NzInvalid learning rate: Elr as a Tensor is not supported for capturable=False and foreach=TruezInvalid epsilon value: r?z#Invalid beta parameter at index 0: rz#Invalid beta parameter at index 1: zInvalid weight_decay value: ) r r!r"r#r$rrrrrz)`fused` does not support `differentiable`Tc3K|]=}|dD]3}|jjvxrtj|5?yw)rN)devicetypetorchis_floating_point).0pgpfused_supported_devicess [C:\Users\daisl\Desktop\realtime-object-detection\venv\Lib\site-packages\torch/optim/adam.py z Adam.__init__..8sR5FrPRS[P\1 !88+''*+P\+5FsAAzX`fused=True` requires all the params to be floating point Tensors of supported devices: .z0`fused` and `foreach` cannot be `True` together.) ValueError isinstancerdictsuper__init__ RuntimeError_step_supports_amp_scalingrall param_groups)selfrr r!r"r#r$rrrrrdefaultsr1 __class__s @r2r9z Adam.__init__spby6rd;< < b& !gjde ecz6se<= =eAh$$B58*MN NeAh$$B58*MN Nl";L>JK K2U%17!)7z'5UD * "#NOO.2D + 'K&L #595F5F#$99P8QQR$TUU"#UVV c6t|||jD]n}|jdd|jdd|jdd|jdd|jdd|jddpt |j j }t|dk7xrtj|dd }|s<|D]6}tjt|d tj |d <8yy) Nr$Frrrrrrstepdtype) r8 __setstate__r= setdefaultliststatevalueslenr, is_tensortensorfloatfloat32)r>rIgroup state_valuesstep_is_tensorsr@s r2rFzAdam.__setstate__As U#&&E   Y .   Z /   Y -   \5 1   -u 5   Wd + 'DJJ--/0 l+q0^eoolSToV\F]6^!!LLqy)9O& "rAc@d}|dD]} | j|tj| z}|j| | jjr t d|j| j|j | } t| dk(r|ds|dr0tjdtj| jn$tjd tj | d <tj| tj | d <tj| tj | d<|dr(tj| tj | d<|j| d |j| d|dr|j| d|dr| d jr t d|dr(tj|dr|ds t d|j| d |S)NFrzJAdam does not support sparse gradients, please consider SparseAdam insteadrrr)rEr*r&rDrC) memory_formatexp_avg exp_avg_sqr$max_exp_avg_sqrzB`requires_grad` is not supported for `step` in differentiable moderr r')gradr, is_complexappend is_sparser:rIrKzerosrOr*rM zeros_likepreserve_format requires_gradrL) r>rPparams_with_gradgradsexp_avgs exp_avg_sqsmax_exp_avg_sqs state_steps has_complexr0rIs r2 _init_groupzAdam._init_groupPs xAvv!u//22  ''*66##&'stt QVV$ 1 u:? !.%. BemmAHHM"\\#U]]C&M (-'7'7I^I^'_E)$*/*:*:1ELaLa*bE,'Y'272B2B1TYTiTi2j./i 01""5#67##**51A+BC)*uV}/J/J&'kll#d (DUS_M`&'noo""5=1O!PrAc|jd}|$tj5|}ddd|jD]|}g}g}g}g}g}g} |d\} } |j ||||||| } t |||||| f|d| | | |d|d|d|d|d|d |d |d t |d dt |d dd~|S#1swYxYw)zPerform a single optimization step. Args: closure (Callable, optional): A closure that reevaluates the model and returns the loss. Nr!r$r r#r"rrrrr grad_scale found_inf)r$rhbeta1beta2r r#r"rrrrrrkrl) _cuda_graph_capture_health_checkr, enable_gradr=rirgetattr) r>closurelossrPrbrcrdrerfrgrmrnrhs r2rCz Adam.steps2 --/  ""$y%&&E! EHK OK >LE5** K    i(';">2%Lz*i( .$%56Gn"4t<!$ T:) %'R Y%$s CC)gMbP?)g?g+?g:0yE>rFN)__name__ __module__ __qualname__r rrNrrboolrr9rFrir rC __classcell__)r@s@r2rrs-1.:"'(!& 0W,0"'$)(-)-0W 0W5&=)0WeUl+0W 0W % 0W  0W#4.0W 0W"0W"&0W!0Wd P3j"7"7rAa Implements Adam algorithm. .. math:: \begin{aligned} &\rule{110mm}{0.4pt} \\ &\textbf{input} : \gamma \text{ (lr)}, \beta_1, \beta_2 \text{ (betas)},\theta_0 \text{ (params)},f(\theta) \text{ (objective)} \\ &\hspace{13mm} \lambda \text{ (weight decay)}, \: \textit{amsgrad}, \:\textit{maximize} \\ &\textbf{initialize} : m_0 \leftarrow 0 \text{ ( first moment)}, v_0\leftarrow 0 \text{ (second moment)},\: \widehat{v_0}^{max}\leftarrow 0\\[-1.ex] &\rule{110mm}{0.4pt} \\ &\textbf{for} \: t=1 \: \textbf{to} \: \ldots \: \textbf{do} \\ &\hspace{5mm}\textbf{if} \: \textit{maximize}: \\ &\hspace{10mm}g_t \leftarrow -\nabla_{\theta} f_t (\theta_{t-1}) \\ &\hspace{5mm}\textbf{else} \\ &\hspace{10mm}g_t \leftarrow \nabla_{\theta} f_t (\theta_{t-1}) \\ &\hspace{5mm}\textbf{if} \: \lambda \neq 0 \\ &\hspace{10mm} g_t \leftarrow g_t + \lambda \theta_{t-1} \\ &\hspace{5mm}m_t \leftarrow \beta_1 m_{t-1} + (1 - \beta_1) g_t \\ &\hspace{5mm}v_t \leftarrow \beta_2 v_{t-1} + (1-\beta_2) g^2_t \\ &\hspace{5mm}\widehat{m_t} \leftarrow m_t/\big(1-\beta_1^t \big) \\ &\hspace{5mm}\widehat{v_t} \leftarrow v_t/\big(1-\beta_2^t \big) \\ &\hspace{5mm}\textbf{if} \: amsgrad \\ &\hspace{10mm}\widehat{v_t}^{max} \leftarrow \mathrm{max}(\widehat{v_t}^{max}, \widehat{v_t}) \\ &\hspace{10mm}\theta_t \leftarrow \theta_{t-1} - \gamma \widehat{m_t}/ \big(\sqrt{\widehat{v_t}^{max}} + \epsilon \big) \\ &\hspace{5mm}\textbf{else} \\ &\hspace{10mm}\theta_t \leftarrow \theta_{t-1} - \gamma \widehat{m_t}/ \big(\sqrt{\widehat{v_t}} + \epsilon \big) \\ &\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 `Adam: A Method for Stochastic Optimization`_. a Args: params (iterable): iterable of parameters to optimize or dicts defining parameter groups lr (float, Tensor, optional): learning rate (default: 1e-3). A tensor LR is not yet supported for all our implementations. Please use a float LR if you are not also specifying fused=True or capturable=True. betas (Tuple[float, float], optional): coefficients used for computing running averages of gradient and its square (default: (0.9, 0.999)) eps (float, optional): term added to the denominator to improve numerical stability (default: 1e-8) weight_decay (float, optional): weight decay (L2 penalty) (default: 0) amsgrad (bool, optional): whether to use the AMSGrad variant of this algorithm from the paper `On the Convergence of Adam and Beyond`_ (default: False) z z .. _Adam\: A Method for Stochastic Optimization: https://arxiv.org/abs/1412.6980 .. _On the Convergence of Adam and Beyond: https://openreview.net/forum?id=ryQu7f-RZ rrcrdrerfrgrrrrrkrlrhr$rmrnr r#r"rc h| )|'t||d\}}|rt|tr|sd}| d} |d}tjj st d|Ds td|r)tjjr td| r)tjjr td| r%tjjst}n-|r%tjjst}nt}|||||||| | ||||||||| | y) znFunctional API that performs Adam algorithm computation. See :class:`~torch.optim.Adam` for details. NF) use_fusedc3PK|]}t|tj ywrt)r6r,r)r.ts r2r3zadam..-s2dXcST:a3NXcs$&zPAPI has changed, `state_steps` argument must contain a list of singleton tensorsz6torch.jit.script not supported with foreach optimizersz4torch.jit.script not supported with fused optimizers) r$rhrmrnr r#r"rrrrkrl) rr6rr,_utils is_compilingr<r:jit is_scripting _fused_adam_multi_tensor_adam_single_tensor_adam)rrcrdrerfrgrrrrrkrlrhr$rmrnr r#r"r_funcs r2rrs> }1&.TYZ 7 z"f-jG } << $ $ &s2dXc2d/dmnn599))+STT '')QRR UYY++- //1!"       " &#rAc ||Jtjjrt| tsJt |D]-\}}|s||n|| }||}||}||}tj js9|r7|jr |js|jr |jsJd|dz }| dk7r|j|| }tj|rqtj|}tj|}tj|}|rtj||||<tj|}|j|d| z |j| j||j!d| z |s|r|}d| |zz }d| |zz }| |z }|j#}|j%}|ro|r||j'}n||}||j)tj*||||j%||zz j-||z }n(|j%||zz j-||z }|j/||nt1|}d| |zz }d| |zz }| |z }t3|}|rDtj*|||||||j%|z j-|}n"|j%|z j-|}|j/||| |stj||stj4||||<0y)NzGIf capturable=True, params and state_steps must be CUDA or XLA tensors.rralpha)value)out)r,rrr6rN enumerater~ris_cudais_xlaaddr[ view_as_reallerp_mul_addcmul_conjnegsqrtclonecopy_maximumadd_addcdiv_r rview_as_complex) rrcrdrerfrgrkrlr$rhrmrnr r#r"rrriparamrZrWrXstep_trCbias_correction1bias_correction2 step_size step_size_negbias_correction2_sqrtrYdenoms r2rrPs`(  )"33 3 yy"e$$$f%5'uQxeAhY1+ ^ Q||((*z6>>u||  YX YV !  1 88E86D   E "%%d+D((1G++J7J%*%7%78J%K"&&u-E  dAI&''diikU'K D 5D=0  5D=0 --I%MMOM$4$9$9$; !!%4Q%7%=%=%?N%4Q%7N"((~z)RS )+0026Km6[\bbcfivcvw#*.Cm.STZZ[^an[no NN7E *f%D 5D=0  5D=0 --I$23C$D ! oa0*/RSBTU)+0025JJPPQTU#*-BBHHM NN7E)N < u''q 2!&!6!6q7I!JOA c&rAc Xt|dk(ryt| tr |s tdtj j s%|r#tdt||DsJd||J|rJdtj||||||g}|jD]i\\}}}}}}}|rt j|}| r |rt|||||nt|||||djr.t j|t j ddd nt j|d | dk7r3|rt j||| nt j"||| }t j$||d | z t j&|| t j(|||d | z ~|rOt j*| |}t j*| |}t j,|d t j,|d t j.|t j0|| t j2|t j4||}|}|r,t j6||t j8|}nt j8|}t j0||t j||t j0||t j:|||p|Dcgc]}d | t=|zz }}|Dcgc]}d | t=|zz }}t?|D cgc] } | | z d z c} }|D cgc] } tA| }} |r,t j6||t j8|}nt j8|}t j0||t j||t j:||||lycc}wcc}wcc} wcc} w) Nrr'c3VK|]!\}}|jxr |j#ywrt)r)r.r0rCs r2r3z%_multi_tensor_adam..s'V=U'!T199--=Us')z@If capturable=True, params and state_steps must be CUDA tensors.z#_foreach ops don't support autogradr(cpu)r*rr)!rKr6rr:r,r~rr<zipr "_group_tensors_by_device_and_dtyperJ _foreach_negris_cpu _foreach_add_rM _foreach_add_foreach_lerp_ _foreach_mul__foreach_addcmul_ _foreach_pow _foreach_sub_ _foreach_neg_ _foreach_div__foreach_reciprocal__foreach_sqrt__foreach_maximum_ _foreach_sqrt_foreach_addcdiv_r r r)!rrcrdrerfrgrkrlr$rhrmrnr r#r"rrrgrouped_tensors device_params device_gradsdevice_exp_avgsdevice_exp_avg_sqsdevice_max_exp_avg_sqsdevice_state_stepsrrrrrexp_avg_sq_sqrtrCbcs! r2rrs& 6{a"fjbcc << $ $ &:VS=UVV O N OV  )"33 3DDD BB + LNO # # %    --l;L m\?L^`vwm\?L^_ a ' '    2ELLU4S[^ _    2A 6 1 ##L-|T$11, Uab  _lAIF .6  2L,PQTYPYZ  $11%9KL $11%9KL     0! 4    0! 4    0 1    0" 5  & &'7 8  !1 2 )I$4 !''(>@RS#("5"56L"M"'"5"56H"I   1F G    5    ;  # #M?O TJ\]J\$EZ-=$= =J\ ]J\]J\$EZ-=$= =J\ ]+FV,WFVb2g^FV,WXIBR$SBRB^B%7BR !$S''(>@RS#("5"56L"M"'"5"56H"I   1F G    5  # #M?OU^ _y&T ^],W$SsP<PP" 9P'returnc |sy|r td||j|ind}||j|ind}t| tr&t | jdk7r| j| ind}t j ||||||g}|jD]\\}}\\}}}}}}}d\}}|||vr|j|d||<||}|||vr|j|d||<||}|||vr| j|d||<||} tj|dtj|||||||| | | | |||||tj||gt|zy) Nz9Adam with fused=True does not support differentiable=Truer)NNT) non_blocking)r*rr) r$r rmrnr#r"rrkrl)r:r*r6rstrr ritemstor,r _fused_adam_rrK) rrcrdrerfrgrkrlr$rhrmrnr r#r"rrrgrad_scale_dictfound_inf_dictlr_dictrr*rrrrrrrdevice_grad_scaledevice_found_infs r2rrJs* VWW9C9Oz((*5UYO6?6Ki&& 2QUN",B!7C Ners// 6666L 6 o9od&L       ' M? T$(! %!%(,'+"KfKV K<K6lKv, K 6l K4.KKKKf%KV$KK !K"#K$%K&5&= !'K()K*+K,-K\mKV mK#F|mK"&v,mK&*&\mK*.f mK &*&\ mK %-V$4 mK$,F#3mK"&mK&*mK %mK %mK"%-0mK',mK#mK #'!mK"%)#mK$)-%mK`G`tF|G`"6lG`!%fG`%)LG`)-V G` %)L G` $,F#3 G`#+6"2G`!%G`%)G`$G`$G`!/G`&+G`"G` "&!G`"$(#G`$(,%G`THb LHb <Hb6lHbf Hb &\ Hb f Hb HbHbHbHb Hb Hb eVmHbHb !Hb"#Hb$%Hb&'Hb( )HbrA