

In [1]:

    
import tensorflow as tf
import numpy as np
import math

Hint: Use dtype=tf.float64 if you want to have same precision as numpy for testing
Hint: You migth wanna use tf.InterativeSession for convenience

1a: Create two random 0-d tensors x and y of any distribution.
Create a TensorFlow object that returns x + y if x > y, and x - y otherwise.
Hint: look up tf.cond()
I do the first problem for you



In [10]:

    
def task_1a_np(x, y):
    return np.where(x > y, x + y, x - y)



In [11]:

    
X = tf.placeholder(tf.float64)
Y = tf.placeholder(tf.float64)
out = tf.cond(tf.greater(X, Y), lambda: tf.add(X, Y), lambda: tf.subtract(X, Y))



In [12]:

    
with tf.Session() as sess:
    for xx, yy in np.random.uniform(size=(50, 2)):
        actual = sess.run(out, feed_dict={X:xx, Y:yy})
        expected = task_1a_np(xx, yy)
        if actual != expected:
            print('Fail')
            # something something
    else:
        print('Success')









    



Success

1b: Create two 0-d tensors x and y randomly selected from the range [-1, 1).
Return x + y if x < y, x - y if x > y, 0 otherwise.
Hint: Look up tf.case().



In [35]:

    
def task_1b_np(x, y):
    return np.select(condlist=[x < y, x > y],
                     choicelist=[x + y, x - y],
                     default=0)



In [ ]:

1c: Create the tensor x of the value [[0, -2, -1], [0, 1, 2]]
and y as a tensor of zeros with the same shape as x.
Return a boolean tensor that yields Trues if x equals y element-wise.
Hint: Look up tf.equal().



In [53]:

    
def task_1c_np():
    x = np.array([[0, -2, -1], [0, 1, 2]])
    y = np.zeros_like(x)
    return x == y



In [ ]:

1d:
Get the indices of elements in x whose values are greater than 30.
Hint: Use tf.where().
Then extract elements whose values are greater than 30.
Hint: Use tf.gather().



In [2]:

    
def task_1d_np(x):
    return x[x > 30].reshape(-1, 1)



In [ ]:

1e: Create a diagnoal 2-d tensor of size 6 x 6 with the diagonal values of 1,
2, ..., 6
Hint: Use tf.range() and tf.diag().



In [3]:

    
def task_1e_np():
    return np.diag(np.arange(1, 7))



In [ ]:

1f: Create a random 2-d tensor of size 10 x 10 from any distribution.
Calculate its determinant.
Hint: Look at tf.matrix_determinant().



In [4]:

    
def task_1f_np(x):
    return np.linalg.det(x)



In [ ]:

1g: Create tensor x with value [5, 2, 3, 5, 10, 6, 2, 3, 4, 2, 1, 1, 0, 9].
Return the unique elements in x
Hint: use tf.unique(). Keep in mind that tf.unique() returns a tuple.



In [5]:

    
def task_1g_np():
    x = [5, 2, 3, 5, 10, 6, 2, 3, 4, 2, 1, 1, 0, 9]
    _, idx = np.unique(x, return_index=True)
    return np.take(x, sorted(idx))



In [ ]:

1h: Create two tensors x and y of shape 300 from any normal distribution,
as long as they are from the same distribution.
Use tf.cond() to return:

The mean squared error of (x - y) if the average of all elements in (x - y)
is negative, or
The sum of absolute value of all elements in the tensor (x - y) otherwise.
Hint: see the Huber loss function in the lecture slides 3.



In [6]:

    
def task_1h_np(x, y):
    average = np.mean(x - y)
    mse = np.mean((x - y) ** 2)
    asum = np.sum(np.abs(x - y))
    return mse if average < 0 else asum



In [ ]: