未验证 提交 8edec09d 编写于 作者: B Bin Lu 提交者: GitHub

Update centerloss.py

上级 b79f3f2e
......@@ -43,4 +43,5 @@ class CenterLoss(nn.Layer):
dist = paddle.multiply(distmat, mask)
loss = paddle.sum(paddle.clip(dist, min=1e-12, max=1e+12)) / batch_size
return {'CenterLoss': loss}
\ No newline at end of file
return {'CenterLoss': loss}
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