我正在尝试使用TensorFlow运行一个线性回归模型。我已经给出了下面的代码。但是,我得到的错误是:ValueError:Shape必须至少是秩2,但对于输入形状为[1],?“model_19/MatMul”(op:'BatchMatMulV2')的“model_19/MatMul”(op:'BatchMatMulV2'),它的秩1
从错误来看,似乎是函数模型的输入造成了问题。对于解决错误的任何建议,我们将不胜感激
import tensorflow as tf
x_train = [1.0, 2.0, 3.0, 4.0]
y_train = [1.5, 3.5, 5.5, 7.5]
def model_linear(x, y):
with tf.variable_scope('model', reuse=tf.AUTO_REUSE):
W = tf.get_variable("W", initializer=tf.constant([0.1]))
b = tf.get_variable("b", initializer=tf.constant([0.0]))
output = tf.matmul(W, x) + b
loss = tf.reduce_sum(tf.square(output - y))
return loss
optimizer = tf.train.GradientDescentOptimizer(0.01)
with tf.Session():
tf.global_variables_initializer().run()
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
loss = model_linear(x, y)
train = optimizer.minimize(loss)
for i in range(1000):
train.run(feed_dict = {x:x_train, y:y_train})
tf.matmul
需要秩2张量,即矩阵。而是平面向量。试试x.reshape(-1,1)
或x.expand_dims(0)
。看起来你的权重矩阵也需要这个相关问题 更多 >
编程相关推荐