中迅农科招股书“采、存、销”数据准确性存在异议

paddle.nn.functional. log_loss ( input: Tensor, label: Tensor, epsilon: float = 0.0001, name: str | None = None ) → Tensor [source]

百度 当前，河北在以习近平同志为核心的党中央坚强领导下，正紧紧抓住历史性窗口期和战略性机遇期，坚持以习近平新时代中国特色社会主义思想为统领，坚决维护习近平总书记在党中央和全党的核心地位，自觉践行“四个意识”，坚决当好首都政治“护城河”，坚定不移推动党中央重大决策部署落地落实，以河北之稳拱卫首都安全，以河北之进服务全国改革发展大局，奋力开创新时代全面建设经济强省、美丽河北新局面。

Negative Log Loss Layer

This layer accepts input predictions and target label and returns the negative log loss.

\[Out = -label * \log{(input + \epsilon)} - (1 - label) * \log{(1 - input + \epsilon)}\]

Parameters

• input (Tensor) – A 2-D tensor with shape [N x 1], where N is the batch size. This input is a probability computed by the previous operator. Data type float32.

• label (Tensor) – The ground truth which is a 2-D tensor with shape [N x 1], where N is the batch size. Data type float32.

• epsilon (float, optional) – A small number for numerical stability. Default 1e-4.

• name (str|None, optional) – For detailed information, please refer to Name . Usually name is no need to set and None by default.

Returns

Tensor, which shape is [N x 1], data type is float32.

Examples

>>> import paddle
>>> import paddle.nn.functional as F

>>> label = paddle.randn((10,1))
>>> prob = paddle.randn((10,1))
>>> cost = F.log_loss(input=prob, label=label)