Question

import tensorflow as tf 
import numpy as np 

W = tf.Variable([0,3], dtype = tf.float32)
b = tf.Variable([-0.3], dtype = tf.float32)

x = tf.placeholder(tf.float32)
linear_model = W * x + b
y = tf.placeholder(tf.float32)

loss = tf.reduce_sum(tf.square(linear_model - y))

optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)

x_train = [1,2,3,4]
y_train = [0,-1,-2,-3]

init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

for i in range(1000):
    sess.run(train, {x: x_train, y: y_train})

curr_W, curr_b, curr_loss = sess.run([W,b,loss], {x: [1,2,3,4], y: [0,-1,-2,-3]})
print("w: %s, b: %s, loss: %s", curr_W, curr_b, curr_loss)

错误：InvalidArgumentError（参见上面的回溯）：不兼容的形状：[2]与[4] [[Node：mul = Mul [T = DT_FLOAT，_device =＆＃34; / job：localhost / replica：0 / task：0 / cpu：0＆＃34;]（Variable / read，_recv_Placeholder_0）]]

Answer 1

我想问题就在这里而不是在W中使用float32

W = tf.Variable([0,3], dtype = tf.float32)
b = tf.Variable([-0.3], dtype = tf.float32)

它将是

W = tf.Variable([0.3], dtype = tf.float32)
b = tf.Variable([-0.3], dtype = tf.float32)

我无法找出编译器报告错误的原因？

1 个答案: