Skip to content

Commit 998ba46

Browse files
aymericdamienaymericdamien
committed
Examples major update
1 parent 0712966 commit 998ba46

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

44 files changed

+2662
-3615
lines changed

‎README.md‎

Lines changed: 17 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -4,31 +4,30 @@ Code examples for some popular machine learning algorithms, using TensorFlow lib
44
## Tutorial index
55

66
#### 1 - Introduction
7-
- Hello World ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1%20-%20Introduction/helloworld.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1%20-%20Introduction/helloworld.py))
8-
- Basic Operations ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1%20-%20Introduction/basic_operations.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1%20-%20Introduction/basic_operations.py))
7+
- Hello World ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1_Introduction/helloworld.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/helloworld.py))
8+
- Basic Operations ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1_Introduction/basic_operations.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/basic_operations.py))
99

1010
#### 2 - Basic Classifiers
11-
- Nearest Neighbor ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2%20-%20Basic%20Classifiers/nearest_neighbor.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2%20-%20Basic%20Classifiers/nearest_neighbor.py))
12-
- Linear Regression ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2%20-%20Basic%20Classifiers/linear_regression.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2%20-%20Basic%20Classifiers/linear_regression.py))
13-
- Logistic Regression ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2%20-%20Basic%20Classifiers/logistic_regression.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2%20-%20Basic%20Classifiers/logistic_regression.py))
11+
- Nearest Neighbor ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/nearest_neighbor.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/nearest_neighbor.py))
12+
- Linear Regression ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/linear_regression.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/linear_regression.py))
13+
- Logistic Regression ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/logistic_regression.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/logistic_regression.py))
1414

1515
#### 3 - Neural Networks
16-
- Multilayer Perceptron ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3%20-%20Neural%20Networks/multilayer_perceptron.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3%20-%20Neural%20Networks/multilayer_perceptron.py))
17-
- Convolutional Neural Network ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3%20-%20Neural%20Networks/convolutional_network.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3%20-%20Neural%20Networks/convolutional_network.py))
18-
- AlexNet ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3%20-%20Neural%20Networks/alexnet.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3%20-%20Neural%20Networks/alexnet.py))
19-
- Recurrent Neural Network (LSTM) ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3%20-%20Neural%20Networks/reccurent_network.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3%20-%20Neural%20Networks/recurrent_network.py))
20-
- Bidirectional Recurrent Neural Network (LSTM) ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3%20-%20Neural%20Networks/bidirectional_rnn.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3%20-%20Neural%20Networks/bidirectional_rnn.py))
21-
- AutoEncoder ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3%20-%20Neural%20Networks/autoencoder.py))
16+
- Multilayer Perceptron ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/multilayer_perceptron.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/multilayer_perceptron.py))
17+
- Convolutional Neural Network ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/convolutional_network.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/convolutional_network.py))
18+
- AlexNet ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/alexnet.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/alexnet.py))
19+
- Recurrent Neural Network (LSTM) ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/reccurent_network.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py))
20+
- Bidirectional Recurrent Neural Network (LSTM) ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/bidirectional_rnn.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/bidirectional_rnn.py))
21+
- AutoEncoder ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/autoencoder.ipynb)) / ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/autoencoder.py))
2222

23-
#### 4 - Multi GPU
24-
- Basic Operations on multi-GPU ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4%20-%20Multi%20GPU/multigpu_basics.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4%20-%20Multi%20GPU/multigpu_basics.py))
23+
#### 4 - Utils
24+
- Save and Restore a model ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4_Utils/save_restore_model.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/save_restore_model.py))
25+
- Tensorboard - Graph and loss visualization ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4_Utils/tensorboard_basic.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/tensorboard_basic.py))
2526

26-
#### 5 - User Interface (Tensorboard)
27-
- Graph Visualization ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/5%20-%20User%20Interface/graph_visualization.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/5%20-%20User%20Interface/graph_visualization.py))
28-
- Loss Visualization ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/5%20-%20User%20Interface/loss_visualization.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/5%20-%20User%20Interface/loss_visualization.py))
27+
#### 5 - Multi GPU (Tensorboard)
28+
- Basic Operations on multi-GPU ([notebook](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/5_MultiGPU/multigpu_basics.ipynb)) ([code](https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/5_MultiGPU/multigpu_basics.py))
2929

30-
31-
## More Examples
30+
## Going further - More Examples
3231
The following examples are coming from [TFLearn](https://github.com/tflearn/tflearn), a library that provides a simplified interface for TensorFlow. You can have a look, there are many [examples](https://github.com/tflearn/tflearn/tree/master/examples) and [pre-built operations and layers](http://tflearn.org/doc_index/#api).
3332

3433
#### Basics

examples/1 - Introduction/basic_operations.py renamed to examples/1_Introduction/basic_operations.py

File renamed without changes.

examples/1 - Introduction/helloworld.py renamed to examples/1_Introduction/helloworld.py

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,4 +19,5 @@
1919
# Start tf session
2020
sess = tf.Session()
2121

22-
print sess.run(hello)
22+
# Run the op
23+
print sess.run(hello)

‎examples/2 - Basic Classifiers/input_data.py‎

Lines changed: 0 additions & 144 deletions
This file was deleted.

examples/2 - Basic Classifiers/linear_regression.py renamed to examples/2_BasicModels/linear_regression.py

Lines changed: 27 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -12,30 +12,31 @@
1212

1313
# Parameters
1414
learning_rate = 0.01
15-
training_epochs = 2000
15+
training_epochs = 1000
1616
display_step = 50
1717

1818
# Training Data
19-
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])
20-
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])
19+
train_X = numpy.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
20+
7.042,10.791,5.313,7.997,5.654,9.27,3.1])
21+
train_Y = numpy.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
22+
2.827,3.465,1.65,2.904,2.42,2.94,1.3])
2123
n_samples = train_X.shape[0]
2224

2325
# tf Graph Input
2426
X = tf.placeholder("float")
2527
Y = tf.placeholder("float")
2628

27-
# Create Model
28-
2929
# Set model weights
3030
W = tf.Variable(rng.randn(), name="weight")
3131
b = tf.Variable(rng.randn(), name="bias")
3232

3333
# Construct a linear model
34-
activation = tf.add(tf.mul(X, W), b)
34+
pred = tf.add(tf.mul(X, W), b)
3535

36-
# Minimize the squared errors
37-
cost = tf.reduce_sum(tf.pow(activation-Y, 2))/(2*n_samples) #L2 loss
38-
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) #Gradient descent
36+
# Mean squared error
37+
cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)
38+
# Gradient descent
39+
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
3940

4041
# Initializing the variables
4142
init = tf.initialize_all_variables()
@@ -50,28 +51,34 @@
5051
sess.run(optimizer, feed_dict={X: x, Y: y})
5152

5253
#Display logs per epoch step
53-
if epoch % display_step == 0:
54-
print "Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(sess.run(cost, feed_dict={X: train_X, Y:train_Y})), \
54+
if (epoch+1) % display_step == 0:
55+
c = sess.run(cost, feed_dict={X: train_X, Y:train_Y})
56+
print "Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
5557
"W=", sess.run(W), "b=", sess.run(b)
5658

5759
print "Optimization Finished!"
5860
training_cost = sess.run(cost, feed_dict={X: train_X, Y: train_Y})
5961
print "Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n'
6062

63+
#Graphic display
64+
plt.plot(train_X, train_Y, 'ro', label='Original data')
65+
plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
66+
plt.legend()
67+
plt.show()
6168

6269
# Testing example, as requested (Issue #2)
63-
test_X = numpy.asarray([6.83,4.668,8.9,7.91,5.7,8.7,3.1,2.1])
64-
test_Y = numpy.asarray([1.84,2.273,3.2,2.831,2.92,3.24,1.35,1.03])
70+
test_X = numpy.asarray([6.83, 4.668, 8.9, 7.91, 5.7, 8.7, 3.1, 2.1])
71+
test_Y = numpy.asarray([1.84, 2.273, 3.2, 2.831, 2.92, 3.24, 1.35, 1.03])
6572

66-
print "Testing... (L2 loss Comparison)"
67-
testing_cost = sess.run(tf.reduce_sum(tf.pow(activation-Y, 2))/(2*test_X.shape[0]),
68-
feed_dict={X: test_X, Y: test_Y}) #same function as cost above
73+
print "Testing... (Mean square loss Comparison)"
74+
testing_cost = sess.run(
75+
tf.reduce_sum(tf.pow(pred - Y, 2)) / (2 * test_X.shape[0]),
76+
feed_dict={X: test_X, Y: test_Y}) # same function as cost above
6977
print "Testing cost=", testing_cost
70-
print "Absolute l2 loss difference:", abs(training_cost - testing_cost)
78+
print "Absolute mean square loss difference:", abs(
79+
training_cost - testing_cost)
7180

72-
#Graphic display
73-
plt.plot(train_X, train_Y, 'ro', label='Original data')
7481
plt.plot(test_X, test_Y, 'bo', label='Testing data')
7582
plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
7683
plt.legend()
77-
plt.show()
84+
plt.show()

0 commit comments

Comments
 (0)