我有2个三维张量A的形状(batch_size,dim1,dim2)和B的大小(batch_size,dim2,dim3).我想执行以下计算:for i in range(batch_size):我尝试了C = tf.matmul(A,B),但得到了错误:
tensorflow.python.framework.errors_impl.InvalidArgumentError:形状必须<e
shuffle=True,) # training data will be randomly shuffled at each epoch输出错误非常清楚地说明:
tensorflow.python.framework.errors_impl.InvalidArgumentError:不兼容形状: 100,530 is 100,3714{{节点丢失_1/退出_9_损耗/子}}]它无法从低维到高维拾取。
首先:
InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 524288 values,/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 965, in _Users/wu