Closed ppyJacK closed 6 years ago
按着示例代码打的,但是在调用计算误差调用softmax_cross_entropy_with_logits()函数的时候传入的参数shape不一样会报错,pred的shape是[128,10],但是y的shape是[1,10],第一个维度的形状不一样啊。。。
附报错提醒 ValueError : Dimension 0 in both shapes must be equal, but are 128 and 1. Shapes are [128,10] and [1,10]. for 'softmax_cross_entropy_with_logits_sg' (op: 'SoftmaxCrossEntropyWithLogits') with input shapes: [128,10], [1,10].
按着示例代码打的,但是在调用计算误差调用softmax_cross_entropy_with_logits()函数的时候传入的参数shape不一样会报错,pred的shape是[128,10],但是y的shape是[1,10],第一个维度的形状不一样啊。。。
附报错提醒 ValueError : Dimension 0 in both shapes must be equal, but are 128 and 1. Shapes are [128,10] and [1,10]. for 'softmax_cross_entropy_with_logits_sg' (op: 'SoftmaxCrossEntropyWithLogits') with input shapes: [128,10], [1,10].