U ʹj38@s2ddlZddlZddlmZddlmZmZmZmZmZm Z m Z m Z ddl m Z mZddgZGdddeZd d e d e d e_de ee ee ee ee eeeeeeeeed ddZe ee ee ee ee eeeeeeed ddZe ee ee ee ee eeeeeeed ddZdS)N)Tensor) Optimizer_use_grad_for_differentiable _get_value_dispatch_sqrt_stack_if_compiling_default_to_fused_or_foreach_differentiable_doc _foreach_doc)ListOptionalRAdamradamcsTeZdZddddeeedfdd Zfd d Zd d ZedddZ Z S)rMbP?g?g+?:0yE>rNF)foreachdifferentiablec sd|kstd|d|ks,td|d|dkrDdksXntd|dd|dkrpdksntd|dd|kstd |t||||||d }t||dS) NzInvalid learning rate: zInvalid epsilon value: r?z#Invalid beta parameter at index 0: rz#Invalid beta parameter at index 1: zInvalid weight_decay value: )lrbetaseps weight_decayrr) ValueErrordictsuper__init__) selfparamsrrrrrrdefaults __class__P/var/www/html/bwave/python/venv/lib/python3.8/site-packages/torch/optim/radam.pyr s& zRAdam.__init__cst||jD]}|dd|ddqt|j}t|dkoZt |dd}|s|D]}t t |d|d<qddS)NrrFrstep) r __setstate__ param_groups setdefaultliststatevalueslentorchZ is_tensortensorfloat)rr+groupZ state_valuesZstep_is_tensorsr"r$r%r',s    zRAdam.__setstate__c Cs|dD]}|jdk r|||jjr0td||j|j|}t|dkrtd|d<tj|tj d|d<tj|tj d|d<||d||d||dqdS) Nr z'RAdam does not support sparse gradientsrrr&)Z memory_formatexp_avg exp_avg_sq) gradappendZ is_sparse RuntimeErrorr+r-r.r/Z zeros_likeZpreserve_format) rr1params_with_gradgradsexp_avgs exp_avg_sqs state_stepspr+r$r$r% _init_group9s(        zRAdam._init_groupc Csd}|dk r&t |}W5QRX|jD]l}g}g}g}g}g}|d\} } |||||||t|||||| | |d|d|d|d|dd q,|S) zPerforms a single optimization step. Args: closure (Callable, optional): A closure that reevaluates the model and returns the loss. Nrrrrrr)beta1beta2rrrrr)r.Z enable_gradr(r>r) rclosureZlossr1r8r9r:r;r<r?r@r$r$r%r&Rs6   z RAdam.step)rrrr)N) __name__ __module__ __qualname__r boolrr'r>rr& __classcell__r$r$r"r%r s a Implements RAdam 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)}, \: \lambda \text{ (weightdecay)}, \\ &\hspace{13mm} \epsilon \text{ (epsilon)} \\ &\textbf{initialize} : m_0 \leftarrow 0 \text{ ( first moment)}, v_0 \leftarrow 0 \text{ ( second moment)}, \\ &\hspace{18mm} \rho_{\infty} \leftarrow 2/(1-\beta_2) -1 \\[-1.ex] &\rule{110mm}{0.4pt} \\ &\textbf{for} \: t=1 \: \textbf{to} \: \ldots \: \textbf{do} \\ &\hspace{6mm}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{6mm}m_t \leftarrow \beta_1 m_{t-1} + (1 - \beta_1) g_t \\ &\hspace{6mm}v_t \leftarrow \beta_2 v_{t-1} + (1-\beta_2) g^2_t \\ &\hspace{6mm}\widehat{m_t} \leftarrow m_t/\big(1-\beta_1^t \big) \\ &\hspace{6mm}\rho_t \leftarrow \rho_{\infty} - 2 t \beta^t_2 /\big(1-\beta_2^t \big) \\[0.1.ex] &\hspace{6mm}\textbf{if} \: \rho_t > 5 \\ &\hspace{12mm} l_t \leftarrow \frac{\sqrt{ (1-\beta^t_2) }}{ \sqrt{v_t} +\epsilon } \\ &\hspace{12mm} r_t \leftarrow \sqrt{\frac{(\rho_t-4)(\rho_t-2)\rho_{\infty}}{(\rho_{\infty}-4)(\rho_{\infty}-2) \rho_t}} \\ &\hspace{12mm}\theta_t \leftarrow \theta_{t-1} - \gamma \widehat{m_t} r_t l_t \\ &\hspace{6mm}\textbf{else} \\ &\hspace{12mm}\theta_t \leftarrow \theta_{t-1} - \gamma \widehat{m_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 `On the variance of the adaptive learning rate and beyond`_. This implementation uses the same weight_decay implementation as Adam (were the weight_decay is applied to the gradient) and not the one from AdamW (were weight_decay is applied to the update). This is different from the `author's implementation`_. a" Args: params (iterable): iterable of parameters to optimize or dicts defining parameter groups lr (float, optional): learning rate (default: 1e-3) 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) z z .. _On the variance of the adaptive learning rate and beyond: https://arxiv.org/abs/1908.03265 .. _author's implementation: https://github.com/LiyuanLucasLiu/RAdam F) r r9r:r;r<rrr?r@rrrc Cstdd|Dstd|dkr4t||dd\} }|rJtjrJtd|r^tjs^t} nt} | |||||||| | | |d dS) zpFunctional API that performs RAdam algorithm computation. See :class:`~torch.optim.RAdam` for details. css|]}t|tjVqdS)N) isinstancer.r).0tr$r$r% szradam..zPAPI has changed, `state_steps` argument must contain a list of singleton tensorsNF)Z use_fusedz6torch.jit.script not supported with foreach optimizers)r?r@rrrr)allr7r r.ZjitZ is_scripting_multi_tensor_radam_single_tensor_radam)r r9r:r;r<rrr?r@rrr_funcr$r$r%rs0) r r9r:r;r<r?r@rrrrcCsht|D]X\} } || } || }|| }|| }|d7}t|}d||}d||}|dkrp| j| |d} || d|||j| | d|d||}dd|d}|d||||}|dkrPt|d|d||d|d|}|}| r|| }n || }t||}| j||||ddq| j||ddqdS) Nrralpha)valueg@g) enumerateraddZlerp_Zmul_Zaddcmul_mathsqrtZadd_)r r9r:r;r<r?r@rrrriparamr5r3r4Zstep_tr&bias_correction1Zbias_correction2Zbias_corrected_exp_avgrho_infrho_trectZexp_avg_sq_sqrtZ adaptive_lrr$r$r%rMsB     rMcs~t|dkrdS| rtdt|||||g} | D]>\\} } }}}}t|ddddfdd|D}|dkrtj| | |d} t|| dt |t || | d~ fdd|D}d d|D}fd d|D}t fd dt ||D}fd dt |||D}t |}t|| t||t|t||t | ||q8dS) Nrz#_foreach ops don't support autogradrrScs8g|]0}dt|t|dt|qS)rSrrrHr&)r@r\r$r% Ksz'_multi_tensor_radam..rPcsDg|]<}|dkrsj (o'  D 6 >