新聞中心
這里有您想知道的互聯(lián)網(wǎng)營銷解決方案
softmax函數(shù)用法及案例分析-創(chuàng)新互聯(lián)
創(chuàng)新互聯(lián)www.cdcxhl.cn八線動態(tài)BGP香港云服務(wù)器提供商,新人活動買多久送多久,劃算不套路!
這篇文章將為大家詳細講解有關(guān)softmax函數(shù)用法及案例分析,小編覺得挺實用的,因此分享給大家做個參考,希望大家閱讀完這篇文章后可以有所收獲。
如下所示:
def softmax(logits, axis=None, name=None, dim=None): """Computes softmax activations. This function performs the equivalent of softmax = tf.exp(logits) / tf.reduce_sum(tf.exp(logits), axis) Args: logits: A non-empty `Tensor`. Must be one of the following types: `half`, `float32`, `float64`. axis: The dimension softmax would be performed on. The default is -1 which indicates the last dimension. name: A name for the operation (optional). dim: Deprecated alias for `axis`. Returns: A `Tensor`. Has the same type and shape as `logits`. Raises: InvalidArgumentError: if `logits` is empty or `axis` is beyond the last dimension of `logits`. """ axis = deprecation.deprecated_argument_lookup("axis", axis, "dim", dim) if axis is None: axis = -1 return _softmax(logits, gen_nn_ops.softmax, axis, name)
當前題目:softmax函數(shù)用法及案例分析-創(chuàng)新互聯(lián)
網(wǎng)站地址:http://www.dlmjj.cn/article/diohcg.html