TensorFlow之計算交叉熵的函數 tf.nn.sparse_softmax_cross_entropy_with_logits

寫在前面：原由是遇到一個錯誤：ValueError: Rank mismatch: Rank of labels (received 2) should equal rank of logits minus 1 (received 2).因而去了解接下來介紹的這兩個函數。python   tf.nn.sparse_softmax_cross_entropy_with_logits tf.nn.sp

>>阅读原文<<