m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

test=develop

Browse Source
revert-14666-feature/estiminate_flops
jerrywgz 6 years ago
parent 3df0538940
commit 126e18c1e8
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File

4
python/paddle/fluid/layers/nn.py
Unescape View File

@ -1152,7 +1152,7 @@ def cross_entropy(input, label, soft_label=False, ignore_index=kIgnoreIndex):
labels. Default: `False`. labels. Default: `False`.
ignore_index (int): Specifies a target value that is ignored and does ignore_index (int): Specifies a target value that is ignored and does
not contribute to the input gradient. Only valid not contribute to the input gradient. Only valid
if soft_label is set to False. Default: -100 if soft_label is set to False. Default: kIgnoreIndex
Returns: Returns:
A 2-D tensor with shape [N x 1], the cross entropy loss. A 2-D tensor with shape [N x 1], the cross entropy loss.
@ -4856,7 +4856,7 @@ def softmax_with_cross_entropy(logits,
labels as soft labels. By default, `soft_label` is set to False. labels as soft labels. By default, `soft_label` is set to False.
ignore_index (int): Specifies a target value that is ignored and does ignore_index (int): Specifies a target value that is ignored and does
not contribute to the input gradient. Only valid not contribute to the input gradient. Only valid
if soft_label is set to False. Default: -100 if soft_label is set to False. Default: kIgnoreIndex
numeric_stable_mode (bool): A flag to indicate whether to use a more numeric_stable_mode (bool): A flag to indicate whether to use a more
numerically stable algorithm. Only valid numerically stable algorithm. Only valid
when soft_label is False and GPU is used. when soft_label is False and GPU is used.

Write Preview
Loading…
Cancel
Save