cjolivier01 commented on a change in pull request #7903: Refactor AdaGrad
optimizer to support sparse tensors
URL: https://github.com/apache/incubator-mxnet/pull/7903#discussion_r139756939
##########
File path: python/mxnet/optimizer.py
##########
@@ -665,26 +667,46 @@ class AdaGrad(Optimizer):
eps: float, optional
Small value to avoid division by 0.
"""
- def __init__(self, eps=1e-7, **kwargs):
+ def __init__(self, eps=1e-7, stype='default', **kwargs):
super(AdaGrad, self).__init__(**kwargs)
self.float_stable_eps = eps
+ self.stype = stype
def create_state(self, index, weight):
- return zeros(weight.shape, weight.context) # history
+ return zeros(weight.shape, weight.context, stype=self.stype) # history
def update(self, index, weight, grad, state):
+ #print("ENTER ADAGRAD UPDATE")
assert(isinstance(weight, NDArray))
assert(isinstance(grad, NDArray))
self._update_count(index)
lr = self._get_lr(index)
wd = self._get_wd(index)
-
+ save_grad_stype = grad.stype
grad = grad * self.rescale_grad
if self.clip_gradient is not None:
grad = clip(grad, -self.clip_gradient, self.clip_gradient)
history = state
- history[:] += (grad * grad)
- weight[:] += -lr * (grad / sqrt(history + self.float_stable_eps) + wd
* weight)
+ save_history_stype = history.stype
+
+ is_sparse = True if weight.stype != 'default' or grad.stype !=
'default' else False
Review comment:
many of these ops support both sparse and dense input combinations (and
handle them in an efficient manner without fallback). not to say it's the most
efficient way to do it, but it's legal.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
