U ʹj5@s(ddlZddlmZddlmZmZmZmZmZmZm Z ddl m Z m Z ddgZ GdddeZd d ed e d ed e_de ee ee ee eee eeeeeeed ddZddZe ee ee ee eeeeeeeed ddZe ee ee ee eeeeeeeed ddZdS)N)Tensor) Optimizer_use_grad_for_differentiable _get_value_default_to_fused_or_foreach_differentiable_doc _foreach_doc _maximize_doc)ListOptionalAdagradadagradcs^eZdZddddeeeedfdd Zfd d Zd d ZddZe dddZ Z S)r {Gz?r绽|=NF)maximizedifferentiable)foreachrrc sd|kstd|d|ks,td|d|ksBtd|d|ksXtd|d|ksntd|t|||||||| d} t|| |jD]X} | dD]J} |j| } td| d <t| rt ||n|}tj | |tj d | d <qqdS) NgzInvalid learning rate: zInvalid lr_decay value: zInvalid weight_decay value: z)Invalid initial_accumulator_value value: zInvalid epsilon value: )lrlr_decayeps weight_decayinitial_accumulator_valuerrrparamsstep)Z memory_formatsum) ValueErrordictsuper__init__ param_groupsstatetorchtensor is_complexcomplexZ full_likeZpreserve_format)selfrrrrrrrrrdefaultsgrouppr!Z init_value __class__R/var/www/html/bwave/python/venv/lib/python3.8/site-packages/torch/optim/adagrad.pyr sH      zAdagrad.__init__cst||jD](}|dd|dd|ddqt|j}t|dkoft |dd}|s|D]}t t |d|d<qpdS)NrrFrrr) r __setstate__r setdefaultlistr!valueslenr"Z is_tensorr#float)r&r!r(Z state_valuesZstep_is_tensorsr*r,r-r.?s     zAdagrad.__setstate__cCs4|jD](}|dD]}|j|}|dqqdS)Nrr)r r!Z share_memory_)r&r(r)r!r,r,r- share_memoryNs   zAdagrad.share_memoryc Cshd}|dD]V}|jdk r |jjr&d}||||j|j|}||d||dq |S)NFrTrr)grad is_sparseappendr!) r&r(params_with_gradgrads state_sums state_stepshas_sparse_gradr)r!r,r,r- _init_groupTs     zAdagrad._init_groupc Csd}|dk r&t |}W5QRX|jD]b}g}g}g}g}||||||}t|||||d|d|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. Nrrrrrrr)rrrrr=rrr)r"Z enable_gradr r>r) r&closureZlossr(r9r:r;r<r=r,r,r-rbs2  z Adagrad.step)rrrrrN)N) __name__ __module__ __qualname__r boolrr.r5r>rr __classcell__r,r,r*r-r s& 3 a[Implements Adagrad algorithm. .. math:: \begin{aligned} &\rule{110mm}{0.4pt} \\ &\textbf{input} : \gamma \text{ (lr)}, \: \theta_0 \text{ (params)}, \: f(\theta) \text{ (objective)}, \: \lambda \text{ (weight decay)}, \\ &\hspace{12mm} \tau \text{ (initial accumulator value)}, \: \eta\text{ (lr decay)}\\ &\textbf{initialize} : state\_sum_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} \tilde{\gamma} \leftarrow \gamma / (1 +(t-1) \eta) \\ &\hspace{5mm} \textbf{if} \: \lambda \neq 0 \\ &\hspace{10mm} g_t \leftarrow g_t + \lambda \theta_{t-1} \\ &\hspace{5mm}state\_sum_t \leftarrow state\_sum_{t-1} + g^2_t \\ &\hspace{5mm}\theta_t \leftarrow \theta_{t-1}- \tilde{\gamma} \frac{g_t}{\sqrt{state\_sum_t}+\epsilon} \\ &\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 `Adaptive Subgradient Methods for Online Learning and Stochastic Optimization`_. a Args: params (iterable): iterable of parameters to optimize or dicts defining parameter groups lr (float, optional): learning rate (default: 1e-2) lr_decay (float, optional): learning rate decay (default: 0) weight_decay (float, optional): weight decay (L2 penalty) (default: 0) eps (float, optional): term added to the denominator to improve numerical stability (default: 1e-10) z z .. _Adaptive Subgradient Methods for Online Learning and Stochastic Optimization: http://jmlr.org/papers/v12/duchi11a.html F) rr:r;r<r=rrrrrrrc Cstdd|Dstd|dkr4t||dd\} }|rJtjrJtd|r^tjs^t} nt} | ||||||| | || |d dS) ztFunctional API that performs Adagrad algorithm computation. See :class:`~torch.optim.Adagrad` for details. css|]}t|tjVqdSN) isinstancer"r).0tr,r,r- szadagrad..zPAPI has changed, `state_steps` argument must contain a list of singleton tensorsNF)Z use_fusedz6torch.jit.script not supported with foreach optimizersrrrrr=rr)all RuntimeErrorrr"ZjitZ is_scripting_multi_tensor_adagrad_single_tensor_adagrad)rr:r;r<r=rrrrrrr_funcr,r,r-rs0cCs8|}|dks |dkr*t|St|||S)Nr)sizeZnumelr"Z empty_likeZsparse_coo_tensor)r6 grad_indicesr1rQr,r,r- _make_sparses rS) rr:r;r<rrrrr=rrc Csrt||||D]\\} } } }|d7}t|}| s4| n| } |dkr^| jrPtd| j| |d} |d|d|}| jr| } | }| }| t | || d| | }| |}| jt | |||| dqt | }|rt | } t | } t | } | j| | dd| r4| |}n| |}| j| || d|rt | } t | } qdS)Nrrz;weight_decay option is not compatible with sparse gradientsalphavalue)ziprr7rLaddZcoalesceZ_indicesZ_valuesZadd_rSpowZ sparse_maskZsqrt_r"r$ view_as_realZaddcmul_sqrtZaddcdiv_Zview_as_complex)rr:r;r<rrrrr=rrparamr6Z state_sumZstep_trZclrrRZ grad_valuesstdZ std_valuesr$r,r,r-rNsF      rNcsp| r tdt|dkrdSt||||g} | D]2\\} } }}}tdd| D}|rt| | ||||dd| d S| rt| } dd | D} d d |D}d d | D} t |d |dkr| rtj | | |d ntj | | |d } fdd |D}tj || | d dt |}t |||dks>| rPt | || }n t| |}t| ||q6dS)Nz#_foreach ops don't support autogradrcss|] }|jVqdSrE)r7)rGr6r,r,r-rIDsz(_multi_tensor_adagrad..TFrJcSs$g|]}t|rt|n|qSr,r"r$r\rGxr,r,r- Ysz)_multi_tensor_adagrad..cSs$g|]}t|rt|n|qSr,r`rar,r,r-rcZscSs$g|]}t|rt|n|qSr,r`rar,r,r-rc]srrTcs&g|]} dt|dqS)r)r)rGrrrr,r-rcisrW)AssertionErrorr2rZ"_group_tensors_by_device_and_dtyper1anyrNr"Z _foreach_negZ _foreach_add_Z _foreach_addZ_foreach_addcmul_Z _foreach_sqrtZ _foreach_mul_Z _foreach_mulZ_foreach_addcdiv_)rr:r;r<rrrrr=rrZgrouped_tensorlistsZ device_paramsZ device_gradsZdevice_state_sumsZdevice_state_stepsrOZdevice_has_sparse_gradZ minus_clrr_ numeratorr,rdr-rM,sR         rM)NNF)r"rZ optimizerrrrrrr r typingr r __all__r __doc__rCr3rrSrNrMr,r,r,r-sp $   3 5 ;