CODEWITHSUNDEEP
pythonnumpytensorflow
Dirk Nachbar
Dirk Nachbar

Reputation: 522

TF: Fetch argument x has invalid type <type 'numpy.float32'>, must be a string or Tensor. (Can not convert a float32 into a Tensor or Operation.)

I have a time series model in TF. It's basically a simple auto-regressive model.

The original y is a vector of length 100 (n).

I get the float is not tensor error (as per subject). I only get it at the second instance though. 

LR = .01
STEPS = 100

def Net(x, w, b):
  # x has 2 previous values
  x = [x[-1], x[-2], x[-1] - x[-2]]
  x = tf.reshape(x, [1, 3])
  x = tf.add(tf.matmul(x, w[0]), b[0])
  pred = tf.add(tf.matmul(x, w[1]), b[1])
  return pred

y_data = y - np.mean(y)

x = tf.placeholder(tf.float32, [2], name='x')
y = tf.placeholder(tf.float32, [1], name='y')
w = [tf.Variable(tf.random_normal([3, 3])), tf.Variable(tf.random_normal([3, 1]))]
b = [tf.Variable(tf.random_normal([1])), tf.Variable(tf.random_normal([1]))]
pred = Net(x, w, b)
cost = tf.sqrt(tf.reduce_mean(tf.square(tf.subtract(pred, y))))
optimizer = tf.train.AdamOptimizer(learning_rate=LR).minimize(cost)

init = tf.global_variables_initializer()
with tf.Session() as sess:
  sess.run(init)
  for step in range(STEPS):
    # random samples of data
    ts = np.random.choice(np.arange(2, n), int(n * .5), replace=False)
    for t in ts:
      x_data = [y_data[t - 2], y_data[t - 1]]
      y_data_cur = [y_data[t]]
      print(x_data, y_data_cur, x, y, pred)
      _, cost, p = sess.run([optimizer, cost, pred], feed_dict={x: x_data, y: y_data_cur})
      print(cost, p)
    if step % 10 == 0:
      print(step, cost)

Upvotes: 1

Views: 3532

Answers (1)

javidcf
javidcf

Reputation: 59681

When you run your model:

_, cost, p = sess.run([optimizer, cost, pred], feed_dict={x: x_data, y: y_data_cur})

You are overwriting the cost variable, which used to hold the TensorFlow tensor for the cost, with its evaluated value, so the next iteration fails. Just change the name of the variable:

_, cost_val, p = sess.run([optimizer, cost, pred], feed_dict={x: x_data, y: y_data_cur})

And of course replace cost with cost_val in the print statements.

Upvotes: 4

Related Questions