提交 e4007337 编写于 作者: Y Yu Yang

Follow comments

上级 1524f204
......@@ -122,7 +122,6 @@ class SGD(ITrainer):
self.__gradient_machine__.eval(batch_evaluator)
for each_param in self.__gradient_machine__.getParameters():
updater.update(each_param)
# Get cost. We use numpy to calculate total cost for this batch.
cost_sum = out_args.sumCosts()
cost = cost_sum / len(data_batch)
updater.finishBatch(cost)
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册