TypeError: minimize() missing 1 required positional argument: 'var_list'

Question

I am trying to minimize the loss using SGD, but its throwing error while I am using SGD, I am trying to do it in tensorflow 2.0, one additional parameter that is causing issue is var_list

import tensorflow as tf
import numpy
import matplotlib.pyplot as plt
rng = numpy.random
print(rng)

# Parameters
learning_rate = 0.01
training_epochs = 1000
display_step = 50

# Training Data
train_X = numpy.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
                         7.042,10.791,5.313,7.997,5.654,9.27,3.1])
train_Y = numpy.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
                         2.827,3.465,1.65,2.904,2.42,2.94,1.3])
n_samples = train_X.shape
print(n_samples)

X = tf.Variable(train_X, name = 'X' ,dtype = 'float32')
Y = tf.Variable(train_Y, name = 'Y' ,dtype = 'float32')
print(X)

# Set model weights
W = tf.Variable(rng.randn(), name="weight")
b = tf.Variable(rng.randn(), name="bias")
print(W)
print(b)

# Construct a linear model
pred = tf.add(tf.multiply(X, W), b)


# Mean squared error. reduce_sum just calculates the sum of the parameters given.
cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)
# Gradient descent
# Note, minimize() knows to modify W and b because Variable objects are trainable=True by default
#optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
optimizer = tf.optimizers.SGD(name='SGD').minimize(cost)
#optimizer = tf.SGD(learning_rate).minimize(cost)
# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()

Answer 1

Just like PankajKabra answered, you are missing the var_list argument of .minimize() and as he pointed out, you should provide the variables you want to minimize, which are W and b. Your code should now be like

optimizer = tf.optimizers.SGD(name='SGD').minimize(cost,var_list=[W,b])

But another problem is that for some reason,your definition for cost should be made a function so that it can be callable. You can quickly do this using the lambda. so you should replace your cost with

cost = lambda: tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)

Check if that helps