VachelHU / EvoNet

Time-Series Event Prediction with Evolutionary State Graph, WSDM 2021
88 stars 26 forks source link

ValueError: Input graph and Layer graph are not the same: Tensor("Reshape_1:0", shape=(?, 256), dtype=float32) is not from the passed-in graph. #11

Open zouyihui opened 2 years ago

zouyihui commented 2 years ago

您好,我想请教一下,当我执行net = tf.layers.dense(patterns, 3, activation=tf.nn.relu, name="outnet_fc1")的时候报错: ValueError: Input graph and Layer graph are not the same: Tensor("Reshape_1:0", shape=(?, 256), dtype=float32) is not from the passed-in graph.可能是什么问题,应该怎么解决了

VachelHU commented 2 years ago

这是 输入的张量shape 不对,检查下数据输入