Basics Flashcards
How do you create a session?
sess = tf.Session()
What do you need to do to use TensorFlow in Python?
import tensorflow as tf
How do you create a constant in TensorFlow?
a = tf.constant(3.0, dtype=tf.float32)
How do you run a TensorFlow session?
sess.run([node1, node2])
How can you print a session to the prompt?
print(sess.run([node1, node2])
How do you add values in TensorFlow?
c = a + b c = tf.add(a, b)
How do you add inputs to TensorFlow?
a = tf.placeholder(tf.float32)
b = ft.placeholder(tf.float32)
c = a + b
sess.run(c, {a: 3, b: 4})
will give 7
to print to the console use
print(sess.run(c, {a: 3, b: 4}))How do you multiply a and b in TensorFlow
c = a * b
How can you stack node in TensorFlow?
c = a + b d = c * 3
How do you create a variable in TensorFlow?
W = tf.Variable([0.3], dtype=tf.float32)
Create a linear model with TensorFlow
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
How do you initialize variables in TensorFlow?
init = tf.global_variables_initializer()
sess.run(init)
How can you add the contents of a vector V together in TensorFlow?
total = tf.reduce_sum(V)
Write a MSD error function in TensorFlow.
y = tf.placeholder(tf.float32) squared_deltas = tf.square(linear_model - y) loss = tf.reduce_sum(squared_deltas)
to run the model and print the output use something like
print( sess.run( loss, { x: [1, 2, 3, 4], y: [0, -1, -2, -3] } ) )
How can you set the value of a variable in TensorFlow?
fixW = tf.assign(W, [-1.0])
sess.run(fixW)
How do you setup a gradient descent optimizer in TensorFlow?
optim = tf.train.GradientDescentOptimizer(0.01) train = optim.minimize(loss)
How do you run the TensorFlow optimizer once its setup?
sess.run(init) # reset values to defaults.
for i in range(1000):
sess.run(train, {x: [1, 2, 3, 4], y: [0, -1, -2, -3]})
print(sess.run([W, b]))
How do you check if a file is executable?
ls -la
How can you make a file executable?
chmod +x fname
How can you produce a series of equally spaced numbers with numpy?
x = np.linspace(-3.0, 3.0, 100)
How can you produce a series of equally spaced numbers with TensorFlow?
x = tf.linspace(-3.0, 3.0, 100)
How do you start an interactive session in TensorFlow?
sess = tf.InteractiveSession()
How do you get the default graph in TensorFlow?
g = tf.get_default_graph()
How can you get a list of all the operations that have been added to a graph g?
[op.name for op in g.get_operations()]
How do you evaluate a tensor x?
computed_x = x.eval(session=sess)
How do you set the graph for a session in TensorFlow?
sess = tf.Session(graph=g)
How do you close a TensorFlow session?
sess.close()
How do you create a new graph in TensorFlow?
g_new = tf.Graph()
How can you get the shape of a Tensor and print it to the command line as a list?
print(x.get_shape().as_list())
How do you configure python to use Pyplot?
import matplotlib.pyplot as plt
How do you plot inline with iPython?
%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
How can you check to see if you can multiply 2 matrices?
There inner dimensions must match
A has m rows and n columns
B has n rows and p columns
The number of columns in A matches the number of rows in B.
If you multiply two matrices what is the size and the resulting matrix?
If matrix A is m x n, and matrix B is n x p, the resulting matrix from A x B will have the dimensions m x p.
What is convolution?
Convolution is a mathematical operation on two functions, to produce a third function.
How can you create a 2-D Gaussian kernel?
A is a vector containing a normal distribution. Multiplying A by its transpose will give you a Gaussian kernel.
G = A * A’
How do you multiply a matrix by its inverse in Tensorflow?
z = a normal distribution vector
ksize = z.get_shape().as_list()[0]
G = tf.matmul(tf.reshape(z, [ksize, 1])
tf.reshape(z, [1, ksize]))
How do you create a Gabor kernel?
Modulate a Gaussian with a sine wave.
How do you plot an image in python?
Use the pyplot library (matplotlib.pyplot)
plt.imshow(img)
How do you load an image in python?
img = plt.imread(‘path_to_file’)
How can you convert a list into an array in python?
data = np.array(list)
How do you get the mean and standard deviation of a set of images?
Combine them into an array of image x height x width x channel
mean_img = np.mean(data, axis=0) std_img = np.std(data, axis=0)
How can you flatten an array into a vector in Python?
flattened = data.ravel()
What are the six key ideas behind Stoicism?
- Appreciate the shortness of life
- Live in the present
- Don’t seek other peoples praise or approval
- There are no good or bad events, only your perception of them
- Identify whats in your control and whats not
- Find happiness in virtue
What are the four stoic virtues?
- Wisdom
- Courage
- Justice
- Temperance
What are the questions for Seneca’s evening review?
What bad habit did I curb today?
How am I better?
Were my actions just?
How can I improve?
What is the difference between the L1-norm and the L2-norm?
These are the ‘Least Absolute Deviations’ and ‘Least Squares’ methods. Generally the L2-norm is the best for producing a stable solution. However, if the data has outliers that it is best to ignore a more robust solution may be found with the Least Absolute Deviations method.
How do you do integer devision in Python?
Use the double slash
a = 4
b = 2
c = a // b
What will np.arange(100) do in Python?
Create a vector of numbers from 0 to 99.
For a non-integer step size its better to use linespace.
What are the 3 Gradient Decent methods?
- Stochastic Gradient Descent : Uses 1 example of the training data each iteration.
- Batch Gradient Descent : Uses all the training data examples each iteration.
- Mini Batch Gradient Descent : uses a subset of the training data examples each iteration.
