Update ch 1 and 2

.gitignore

@@ -25,6 +25,8 @@ checkpoint
 *.pos
 **/temp/
 **/temp
+**/tmp/
+**/tmp
 */tensorboard_logs/*
 */tensorboard_logs/
 */tensorboard_logs
@@ -137,8 +139,13 @@ celerybeat-schedule
 venv/
 ENV/
 
-# Spyder project settings
+# Spyder/pycharm project settings
 .spyderproject
+.idea/
 
 # Rope project settings
 .ropeproject
+
+# Ignore data sources
+*/MNIST_data/*
+*/birthweight_data/*

01_Introduction/02_Creating_and_Using_Tensors/02_tensors.py

@@ -59,7 +59,6 @@
 merged = tf.summary.merge_all()
 
 # Initialize graph writer:
-
 writer = tf.summary.FileWriter("/tmp/variable_logs", graph=sess.graph)
 
 # Initialize operation

01_Introduction/03_Using_Variables_and_Placeholders/03_placeholders.py

@@ -19,6 +19,6 @@
 
 merged = tf.summary.merge_all()
 
-writer = tf.summary.FileWriter("/tmp/variable_logs", sess.graph_def)
+writer = tf.summary.FileWriter("/tmp/variable_logs", sess.graph)
 
 print(sess.run(y, feed_dict={x: rand_array}))

01_Introduction/04_Working_with_Matrices/04_matrices.py

@@ -28,8 +28,7 @@
 
 # 3x2 random uniform matrix
 C = tf.random_uniform([3,2])
-print(sess.run(C))
-print(sess.run(C)) # Note that we are reinitializing, hence the new random variabels
+print(sess.run(C))  # Note that we are reinitializing, hence the new random variables
 
 # Create matrix from np array
 D = tf.convert_to_tensor(np.array([[1., 2., 3.], [-3., -7., -1.], [0., 5., -2.]]))

01_Introduction/05_Declaring_Operations/05_operations.py

@@ -5,8 +5,6 @@
 # in TensorFlow
 
 # Declaring Operations
-import matplotlib.pyplot as plt
-import numpy as np
 import tensorflow as tf
 from tensorflow.python.framework import ops
 ops.reset_default_graph()
@@ -15,31 +13,31 @@
 sess = tf.Session()
 
 # div() vs truediv() vs floordiv()
-print(sess.run(tf.div(3,4)))
-print(sess.run(tf.truediv(3,4)))
-print(sess.run(tf.floordiv(3.0,4.0)))
+print(sess.run(tf.div(3, 4)))
+print(sess.run(tf.truediv(3, 4)))
+print(sess.run(tf.floordiv(3.0, 4.0)))
 
 # Mod function
-print(sess.run(tf.mod(22.0,5.0)))
+print(sess.run(tf.mod(22.0, 5.0)))
 
 # Cross Product
-print(sess.run(tf.cross([1.,0.,0.],[0.,1.,0.])))
+print(sess.run(tf.cross([1., 0., 0.], [0., 1., 0.])))
 
 # Trig functions
 print(sess.run(tf.sin(3.1416)))
 print(sess.run(tf.cos(3.1416)))
-# Tangent
-print(sess.run(tf.div(tf.sin(3.1416/4.), tf.cos(3.1416/4.))))
+print(sess.run(tf.tan(3.1416/4.)))
 
 # Custom operation
 test_nums = range(15)
-#from tensorflow.python.ops import math_ops
-#print(sess.run(tf.equal(test_num, 3)))
+
+
 def custom_polynomial(x_val):
     # Return 3x^2 - x + 10
-    return(tf.subtract(3 * tf.square(x_val), x_val) + 10)
+    return tf.subtract(3 * tf.square(x_val), x_val) + 10
 
 print(sess.run(custom_polynomial(11)))
+
 # What should we get with list comprehension
 expected_output = [3*x*x-x+10 for x in test_nums]
 print(expected_output)

01_Introduction/06_Implementing_Activation_Functions/06_activation_functions.py

@@ -51,12 +51,12 @@
 plt.plot(x_vals, y_relu6, 'g-.', label='ReLU6', linewidth=2)
 plt.plot(x_vals, y_elu, 'k-', label='ExpLU', linewidth=0.5)
 plt.ylim([-1.5,7])
-plt.legend(loc='top left')
+plt.legend(loc='upper left')
 plt.show()
 
 plt.plot(x_vals, y_sigmoid, 'r--', label='Sigmoid', linewidth=2)
 plt.plot(x_vals, y_tanh, 'b:', label='Tanh', linewidth=2)
 plt.plot(x_vals, y_softsign, 'g-.', label='Softsign', linewidth=2)
 plt.ylim([-2,2])
-plt.legend(loc='top left')
+plt.legend(loc='upper left')
 plt.show()

01_Introduction/07_Working_with_Data_Sources/07_data_gathering.py

@@ -6,7 +6,6 @@
 
 # Data Gathering
 import matplotlib.pyplot as plt
-import numpy as np
 import tensorflow as tf
 from tensorflow.python.framework import ops
 ops.reset_default_graph()
@@ -64,11 +63,10 @@
 
 print(X_train.shape)
 print(y_train.shape)
-print(y_train[0,]) # this is a frog
+print(y_train[0,])  # this is a frog
 
 # Plot the 0-th image (a frog)
 from PIL import Image
-%matplotlib inline
 img = Image.fromarray(X_train[0,:,:,:])
 plt.imshow(img)
 

02_TensorFlow_Way/01_Operations_as_a_Computational_Graph/01_operations_on_a_graph.py

@@ -1,5 +1,5 @@
 # Operations on a Computational Graph
-import matplotlib.pyplot as plt
+import os
 import numpy as np
 import tensorflow as tf
 from tensorflow.python.framework import ops
@@ -13,13 +13,16 @@
 # Create data to feed in
 x_vals = np.array([1., 3., 5., 7., 9.])
 x_data = tf.placeholder(tf.float32)
-m = tf.constant(3.)
+m_const = tf.constant(3.)
 
 # Multiplication
-prod = tf.multiply(x_data, m)
+my_product = tf.multiply(x_data, m_const)
 for x_val in x_vals:
-    print(sess.run(prod, feed_dict={x_data: x_val}))
+    print(sess.run(my_product, feed_dict={x_data: x_val}))
 
+# View the tensorboard graph by running the following code and then
+#    going to the terminal and typing:
+#    $ tensorboard --logdir=tensorboard_logs
 merged = tf.summary.merge_all()
 if not os.path.exists('tensorboard_logs/'):
     os.makedirs('tensorboard_logs/')

02_TensorFlow_Way/02_Layering_Nested_Operations/02_layering_nested_operations.ipynb

@@ -202,7 +202,9 @@
     "collapsed": true
    },
    "outputs": [],
-   "source": []
+   "source": [
+    ""
+   ]
   }
  ],
  "metadata": {
@@ -214,7 +216,7 @@
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 3
+    "version": 3.0
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
@@ -225,5 +227,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
-}
+ "nbformat_minor": 0
+}

02_TensorFlow_Way/02_Layering_Nested_Operations/02_layering_nested_operations.py

@@ -0,0 +1,40 @@
+# Layering Nested Operations
+
+import os
+import numpy as np
+import tensorflow as tf
+from tensorflow.python.framework import ops
+ops.reset_default_graph()
+
+# Start a graph session
+sess = tf.Session()
+
+# Create the data and variables
+my_array = np.array([[1., 3., 5., 7., 9.],
+                   [-2., 0., 2., 4., 6.],
+                   [-6., -3., 0., 3., 6.]])
+x_vals = np.array([my_array, my_array + 1])
+x_data = tf.placeholder(tf.float32, shape=(3, 5))
+
+# Constants for matrix multiplication:
+m1 = tf.constant([[1.], [0.], [-1.], [2.], [4.]])
+m2 = tf.constant([[2.]])
+a1 = tf.constant([[10.]])
+
+# Create our multiple operations
+prod1 = tf.matmul(x_data, m1)
+prod2 = tf.matmul(prod1, m2)
+add1 = tf.add(prod2, a1)
+
+# Now feed data through placeholder and print results
+for x_val in x_vals:
+    print(sess.run(add1, feed_dict={x_data: x_val}))
+
+# View the tensorboard graph by running the following code and then
+#    going to the terminal and typing:
+#    $ tensorboard --logdir=tensorboard_logs
+merged = tf.summary.merge_all()
+if not os.path.exists('tensorboard_logs/'):
+    os.makedirs('tensorboard_logs/')
+
+my_writer = tf.summary.FileWriter('tensorboard_logs/', sess.graph)

02_TensorFlow_Way/03_Working_with_Multiple_Layers/03_multiple_layers.py

@@ -1,6 +1,5 @@
 # Working with Multiple Layers
 
-import matplotlib.pyplot as plt
 import numpy as np
 import tensorflow as tf
 import os
@@ -41,7 +40,7 @@ def custom_layer(input_matrix):
     custom_layer1 = custom_layer(mov_avg_layer)
 
 # The output should be an array that is 2x2, but size (1,2,2,1)
-#print(sess.run(mov_avg_layer, feed_dict={x_data: x_val}))
+print(sess.run(mov_avg_layer, feed_dict={x_data: x_val}))
 
 # After custom operation, size is now 2x2 (squeezed out size 1 dims)
 print(sess.run(custom_layer1, feed_dict={x_data: x_val}))

02_TensorFlow_Way/04_Implementing_Loss_Functions/04_loss_functions.py

@@ -44,6 +44,7 @@
 plt.plot(x_array, phuber2_y_out, 'g:', label='P-Huber Loss (5.0)')
 plt.ylim(-0.2, 0.4)
 plt.legend(loc='lower right', prop={'size': 11})
+plt.grid()
 plt.show()
 
 
@@ -68,15 +69,18 @@
 # L = max(actual, 0) - actual * pred + log(1 + exp(-abs(actual)))
 x_val_input = tf.expand_dims(x_vals, 1)
 target_input = tf.expand_dims(targets, 1)
-xentropy_sigmoid_y_vals = tf.nn.softmax_cross_entropy_with_logits(logits=x_val_input, labels=target_input)
+xentropy_sigmoid_y_vals = tf.nn.softmax_cross_entropy_with_logits_v2(logits=x_val_input,
+                                                                     labels=target_input)
 xentropy_sigmoid_y_out = sess.run(xentropy_sigmoid_y_vals)
 
 # Weighted (softmax) cross entropy loss
 # L = -actual * (log(pred)) * weights - (1-actual)(log(1-pred))
 # or
 # L = (1 - pred) * actual + (1 + (weights - 1) * pred) * log(1 + exp(-actual))
 weight = tf.constant(0.5)
-xentropy_weighted_y_vals = tf.nn.weighted_cross_entropy_with_logits(x_vals, targets, weight)
+xentropy_weighted_y_vals = tf.nn.weighted_cross_entropy_with_logits(logits=x_vals,
+                                                                    targets=targets,
+                                                                    pos_weight=weight)
 xentropy_weighted_y_out = sess.run(xentropy_weighted_y_vals)
 
 # Plot the output
@@ -87,15 +91,16 @@
 plt.plot(x_array, xentropy_weighted_y_out, 'g:', label='Weighted Cross Entropy Loss (x0.5)')
 plt.ylim(-1.5, 3)
 #plt.xlim(-1, 3)
+plt.grid()
 plt.legend(loc='lower right', prop={'size': 11})
 plt.show()
 
 # Softmax entropy loss
 # L = -actual * (log(softmax(pred))) - (1-actual)(log(1-softmax(pred)))
 unscaled_logits = tf.constant([[1., -3., 10.]])
 target_dist = tf.constant([[0.1, 0.02, 0.88]])
-softmax_xentropy = tf.nn.softmax_cross_entropy_with_logits(logits=unscaled_logits,
-                                                           labels=target_dist)
+softmax_xentropy = tf.nn.softmax_cross_entropy_with_logits_v2(logits=unscaled_logits,
+                                                              labels=target_dist)
 print(sess.run(softmax_xentropy))
 
 # Sparse entropy loss

02_TensorFlow_Way/05_Implementing_Back_Propagation/05_back_propagation.py

@@ -4,7 +4,6 @@
 # This python function shows how to implement back propagation
 # in regression and classification models.
 
-import matplotlib.pyplot as plt
 import numpy as np
 import tensorflow as tf
 from tensorflow.python.framework import ops
@@ -36,14 +35,14 @@
 # Add L2 loss operation to graph
 loss = tf.square(my_output - y_target)
 
-# Initialize variables
-init = tf.global_variables_initializer()
-sess.run(init)
-
 # Create Optimizer
 my_opt = tf.train.GradientDescentOptimizer(0.02)
 train_step = my_opt.minimize(loss)
 
+# Initialize variables
+init = tf.global_variables_initializer()
+sess.run(init)
+
 # Run Loop
 for i in range(100):
     rand_index = np.random.choice(100)
@@ -108,7 +107,7 @@
     if (i+1)%200==0:
         print('Step #' + str(i+1) + ' A = ' + str(sess.run(A)))
         print('Loss = ' + str(sess.run(xentropy, feed_dict={x_data: rand_x, y_target: rand_y})))
-        
+
 # Evaluate Predictions
 predictions = []
 for i in range(len(x_vals)):

02_TensorFlow_Way/06_Working_with_Batch_and_Stochastic_Training/06_batch_stochastic_training.py

@@ -32,14 +32,14 @@
 # Add L2 loss operation to graph
 loss = tf.square(my_output - y_target)
 
-# Initialize variables
-init = tf.global_variables_initializer()
-sess.run(init)
-
 # Create Optimizer
 my_opt = tf.train.GradientDescentOptimizer(0.02)
 train_step = my_opt.minimize(loss)
 
+# Initialize variables
+init = tf.global_variables_initializer()
+sess.run(init)
+
 loss_stochastic = []
 # Run Loop
 for i in range(100):
@@ -77,14 +77,14 @@
 # Add L2 loss operation to graph
 loss = tf.reduce_mean(tf.square(my_output - y_target))
 
-# Initialize variables
-init = tf.global_variables_initializer()
-sess.run(init)
-
 # Create Optimizer
 my_opt = tf.train.GradientDescentOptimizer(0.02)
 train_step = my_opt.minimize(loss)
 
+# Initialize variables
+init = tf.global_variables_initializer()
+sess.run(init)
+
 loss_batch = []
 # Run Loop
 for i in range(100):

02_TensorFlow_Way/08_Evaluating_Models/08_evaluating_models.py

@@ -150,7 +150,7 @@
 # Plot classification result
 A_result = -sess.run(A)
 bins = np.linspace(-5, 5, 50)
-plt.hist(x_vals[0:50], bins, alpha=0.5, label='N(-1,1)', color='white')
+plt.hist(x_vals[0:50], bins, alpha=0.5, label='N(-1,1)', color='blue')
 plt.hist(x_vals[50:100], bins[0:50], alpha=0.5, label='N(2,1)', color='red')
 plt.plot((A_result, A_result), (0, 8), 'k--', linewidth=3, label='A = '+ str(np.round(A_result, 2)))
 plt.legend(loc='upper right')

requirements.txt

@@ -1,7 +1,8 @@
-tensorflow
-numpy
-scipy
-sklearn
-requests
-jupyter
-matplotlib
+tensorflow==1.6.0
+numpy==1.14.2
+scipy==1.0.0
+sklearn==0.19.1
+jupyter==1.0.0
+matplotlib==2.2.2
+requests==2.18.4
+Pillow==5.0.0