CaitinZhao/cvpr2019_Pyramid-Feature-Attention-Network-for-Saliency-detection

作者你好,请问关于EdgeHoldLoss损失函数问题?

Closed this issue · 0 comments

在你的代码中edge = tf.nn.conv2d(x, laplace, strides=(1, 1, 1, 1), padding='SAME')出现了以下错误
ValueError: Shape must be rank 4 but is rank 3 for 'loss/Conv2D' (op: 'Conv2D') with input shapes: [?,640,640], [3,3,1,1].
我的输入是一张二值图(x),请问我该如何更改呢?谢谢。