CODEWITHSUNDEEP
pythonnumpytensorflow
Leo Li
Leo Li

Reputation: 81

I cannot find out why compiler reported the error?

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)

ERROR:InvalidArgumentError (see above for traceback): Incompatible shapes: [2] vs. [4] [[Node: mul = Mul[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Variable/read, _recv_Placeholder_0)]]

Upvotes: 1

Views: 56

Answers (1)

Exprator
Exprator

Reputation: 27543

i guess the problem is here instead of this in W as you are using float32 

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

it will be

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

Upvotes: 2

Related Questions