Name	Size	Mode	Actions
adadelta.cpython-36.pyc	4829	0644	editdlrm
adagrad.cpython-36.pyc	4767	0644	editdlrm
adam.cpython-36.pyc	6250	0644	editdlrm
adamax.cpython-36.pyc	4869	0644	editdlrm
adamw.cpython-36.pyc	6258	0644	editdlrm
asgd.cpython-36.pyc	2848	0644	editdlrm
lbfgs.cpython-36.pyc	8802	0644	editdlrm
lr_scheduler.cpython-36.pyc	63792	0644	editdlrm
nadam.cpython-36.pyc	5727	0644	editdlrm
optimizer.cpython-36.pyc	11827	0644	editdlrm
radam.cpython-36.pyc	5712	0644	editdlrm
rmsprop.cpython-36.pyc	6543	0644	editdlrm
rprop.cpython-36.pyc	5182	0644	editdlrm
sgd.cpython-36.pyc	6267	0644	editdlrm
sparse_adam.cpython-36.pyc	3329	0644	editdlrm
swa_utils.cpython-36.pyc	11370	0644	editdlrm
_functional.cpython-36.pyc	10407	0644	editdlrm
__init__.cpython-36.pyc	1049	0644	editdlrm

3 �Eg}�@s4dd
lZddl
mZ
ddlmZ
Gdd�de�Zd
S)�N�
)
�_functional)
� Optimizercs4eZ
dZd
Zd �f
dd� Zej�dd d�
�
Z�ZS)�RAdamaz 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 \sqrt{ (1-\beta^t_2) / \big( v_t +\epsilon \big) } \\ &\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`_. Args: params (iterable): iterable of parameters to optimize or dicts defining parameter groups lr (float, optional): learning rate (default: 2e-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) .. _On the variance of the adaptive learning rate and beyond: https://arxiv.org/abs/1908.03265 �����MbP?��������?�+�����?�:�0�yE>r
cs�d
|k
stdj
|�
�
�
d
|k
s,tdj
|�
�
�
d
|dk
oBdkn
sZtdj
|d�
�
�
d
|dk
opdkn
s�tdj
|d�
�
�
d
|k
s�td j
|�
�
�
t||||d �}tt|�j|
|�
dS)NgzInvalid learning rate: {}zInvalid epsilon value: {}r
g�?z%Invalid beta parameter at index 0: {}rz%Invalid beta parameter at index 1: {}zInvalid weight_decay value: {})�lr�betas�eps�weight_decay)� ValueError�format�dict�superr�__init__)�self�paramsr rrr �defaults)
� __class__��=/usr/local/lib64/python3.6/site-packages/torch/optim/radam.pyr9s










zRAdam.__init__NcCsN
d
}|
d
k r&tj
��
|
�}Wd
QRX�
x |jD�
]}g}g}g}g}g}g} |d\} }x�|dD]�}|jd
k rd|j|�

|jjr�td�
�
|j|j�

|j|} t| �
dkr�d| d<tj |tj d�| d<tj |tj d�| d <|j| d�

|j| d �

| dd 7<| j| d�

qdWtj||||| | ||d|d|d d�
q0W|S)z�Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model and returns the loss. Nrrz'RAdam does not support sparse gradientsr
�step)
Z memory_formatZexp_avgZ exp_avg_sqrr r r)�beta1�beta2r r r) �torchZenable_gradZparam_groupsZgrad�appendZ is_sparse�RuntimeError�state�lenZ zeros_likeZpreserve_format�
FZradam)rZclosureZloss�groupZparams_with_gradZgradsZexp_avgsZexp_avg_sqsZmax_exp_avg_sqsZstate_stepsrr�
prrrrrHsL














 











z RAdam.step�rr)rr$r r
)
N) �__name__� __module__�__qualname__�__doc__rrZno_gradr� __classcell__rr)
rrrs 1

r)r�rr!Z optimizerrrrrrr�
s