提交 00febff7 编写于 作者: Q qingen

[vec][loss] update docstring, test=doc fix #1717

上级 16675770
......@@ -132,6 +132,9 @@ class NCELoss(nn.Layer):
def forward(self, output, target):
"""Forward inference
Args:
output (tensor): the model output, which is the input of loss function
"""
output = paddle.reshape(output, [-1, self.N])
B = output.shape[0]
......
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