The TensorFlow dance craze
0 likes238 views
The document introduces TensorFlow, a machine learning library. It discusses how TensorFlow uses multi-dimensional arrays called tensors to represent data and models. An example regression problem is demonstrated where TensorFlow is used to fit a line to sample data points by iteratively updating the slope and offset values to minimize loss. The document promotes TensorFlow by noting its ability to distribute operations across processors and optimize entire graphs.
![You have some data
Even though it’s in a 2D spreadsheet it can
describe a multidimensional space.
House Price Data
1 mile to park
2 bedrooms
1800 sq ft
So our Tensor is [1, 2, 1800]Square footage
Distance to park
# of bathrooms](https://image.slidesharecdn.com/thetensorflowdancecraze-161221212828/85/The-TensorFlow-dance-craze-13-320.jpg)
![Demo code: fitting a line to points
Demo is of Datalab notebook
# Create 100 phony x, y data points in NumPy, y = x * 0.1 + 0.3
tf.reset_default_graph()
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
x_measured = np.random.rand(100).astype(np.float32)
y_measured = x_measured * (0.1 + (0.05 *np.random.rand(100))) + 0.3
plt.scatter(x_measured, y_measured)
plt.xlabel('<- Bluer : Uniform Color : Redder ->')
plt.ylabel('Deaths per mission')
plt.title('Star Trek Uniform Color Mortality Incidence')
# plt.plot([0, 1], [0, 0.5], color='purple', lw=2)
# plt.plot([0, 1], [0.25, 0.5], color='purple', lw=2)
Measured Data](https://image.slidesharecdn.com/thetensorflowdancecraze-161221212828/85/The-TensorFlow-dance-craze-19-320.jpg)
![Demo code continued
import tensorflow as tf
# Try to find values for slope and offset that match
# y_measured = slope * x_measured + offset
slope = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
offset = tf.Variable(tf.zeros([1]))
y_predicted = slope * x_measured + offset
loss = tf.reduce_mean(tf.square(y_predicted - y_measured))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
A test value for slope](https://image.slidesharecdn.com/thetensorflowdancecraze-161221212828/85/The-TensorFlow-dance-craze-20-320.jpg)
![Demo code continued
# Launch the graph.
sess = tf.Session()
sess.run(tf.initialize_all_variables()) # and initialize variables
# Fit the line.
print 'step #t', 'slopett', 'offset'
for step in range(201):
sess.run(train)
if step % 20 == 0:
print step,'t', sess.run(slope)[0], 't', sess.run(offset)[0]
A test value for slope and offset](https://image.slidesharecdn.com/thetensorflowdancecraze-161221212828/85/The-TensorFlow-dance-craze-21-320.jpg)
![4+ D Spaces
A given measurement all fits into a simple Tensor: [4, 4, 4, 3]](https://image.slidesharecdn.com/thetensorflowdancecraze-161221212828/85/The-TensorFlow-dance-craze-24-320.jpg)
![Some Tensors
Scalar 0.2
Vector [1, 2, 1800]
Matrix
[2, 1, 1],
[1, 2, 0],
[0, 1, 0]
n-Tensors](https://image.slidesharecdn.com/thetensorflowdancecraze-161221212828/85/The-TensorFlow-dance-craze-25-320.jpg)
![Rank 2 Tensor
When a bunch of
vectors hang out
they make a Matrix
[2, 1, 1],
[1, 2, 0],
[0, 1, 0]](https://image.slidesharecdn.com/thetensorflowdancecraze-161221212828/85/The-TensorFlow-dance-craze-26-320.jpg)
The TensorFlow dance craze
- 1. The TensorFlow dance craze Gabe Hamilton
- 2. TensorFlow is a Machine Learning library
- 3. What is Machine Learning? usually: Statistical Pattern Matching Using past measurements to predict something about a new piece of information
- 4. Does this picture contain a cat? Classification How much is this home worth? Regression Regression Talk https://docs.google.com/presentation/d/17FoojZ17DKDZqoByhB16PmtAXtnJ tXSy1-feK9-A_fg/edit#slide=id.p10
- 5. There are lots of other ML libraries
- 6. Is it right for you? Maybe Not, use Prediction API http://www.slideshare.net/gabehamilton/intro-to-google-prediction-api-15167420 Or equivalent Amazon or Microsoft APIs if you have a CSV of observed data.
- 7. But I’d like to get into the details or I am working on a complex problem...
- 8. You do still have some choices. Some people prefer Keras on top of TensorFlow https://keras.io/ or tf-slim or pretty-tensor
- 9. So why use TensorFlow? It’s not much different than the “easier” libraries. You’ll want to understand more and more details anyway. Because you like It has the hottest dance moves!
- 10. Look out a Tensor!
- 11. Some Math and a Multi-Dimensional Array had a baby
- 12. For our purposes It’s a multi-dimensional array. Just remember that you are putting a mathematical construct in that array. A tensor is a multi-dimensional array with certain transformation properties
- 13. You have some data Even though it’s in a 2D spreadsheet it can describe a multidimensional space. House Price Data 1 mile to park 2 bedrooms 1800 sq ft So our Tensor is [1, 2, 1800]Square footage Distance to park # of bathrooms
- 14. Let’s build a Tensor Machine = a Tensor
- 15. Comparing output is our Output But we are expecting - = Loss
- 16. Iterate until we have a good model
- 19. Demo code: fitting a line to points Demo is of Datalab notebook # Create 100 phony x, y data points in NumPy, y = x * 0.1 + 0.3 tf.reset_default_graph() import numpy as np import matplotlib.pyplot as plt %matplotlib inline x_measured = np.random.rand(100).astype(np.float32) y_measured = x_measured * (0.1 + (0.05 *np.random.rand(100))) + 0.3 plt.scatter(x_measured, y_measured) plt.xlabel('<- Bluer : Uniform Color : Redder ->') plt.ylabel('Deaths per mission') plt.title('Star Trek Uniform Color Mortality Incidence') # plt.plot([0, 1], [0, 0.5], color='purple', lw=2) # plt.plot([0, 1], [0.25, 0.5], color='purple', lw=2) Measured Data
- 20. Demo code continued import tensorflow as tf # Try to find values for slope and offset that match # y_measured = slope * x_measured + offset slope = tf.Variable(tf.random_uniform([1], -1.0, 1.0)) offset = tf.Variable(tf.zeros([1])) y_predicted = slope * x_measured + offset loss = tf.reduce_mean(tf.square(y_predicted - y_measured)) optimizer = tf.train.GradientDescentOptimizer(0.5) train = optimizer.minimize(loss) A test value for slope
- 21. Demo code continued # Launch the graph. sess = tf.Session() sess.run(tf.initialize_all_variables()) # and initialize variables # Fit the line. print 'step #t', 'slopett', 'offset' for step in range(201): sess.run(train) if step % 20 == 0: print step,'t', sess.run(slope)[0], 't', sess.run(offset)[0] A test value for slope and offset
- 22. Q & A Plus more slides for longer talks or answering questions
- 23. Why TensorFlow is useful Build your graph in a high level language, execute in fast implementations. Distribute graph operations across processors. Whole graph can be optimized.
- 24. 4+ D Spaces A given measurement all fits into a simple Tensor: [4, 4, 4, 3]
- 25. Some Tensors Scalar 0.2 Vector [1, 2, 1800] Matrix [2, 1, 1], [1, 2, 0], [0, 1, 0] n-Tensors
- 26. Rank 2 Tensor When a bunch of vectors hang out they make a Matrix [2, 1, 1], [1, 2, 0], [0, 1, 0]