TensorFlow to predict if an underwater object is Rock or Mine¶

A naval mine is a self-contained explosive device placed in water to damage or destroy ships or submarines.

Situation: You have been hired by US Navy to create a model that can detect the difference between an underwater mine and a rock, because a mine dangerous but a rock is not. And it is difficult for humans to judge if an underwater object is rock or a mine.

Solution: We will write a model in TensorFlow to make the prediction for us if the underwater object is rock or a mine.

Dataset used is Sonar.csv, downloaded from the GitHub loccation:
https://github.com/selva86/datasets/blob/master/Sonar.csv

Creating and Training the Model¶

# Importing the libraries
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split

# Reading the dataset
def read_dataset():
    dir_path = "./MLData/00_Misc/"
    df = pd.read_csv(dir_path + "Sonar.csv")
    X = df[df.columns[0:60]].values
    y = df[df.columns[60]]

    # Encode the labels
    encoder = LabelEncoder()
    encoder.fit(y)
    y = encoder.transform(y)
    Y = one_hot_encode(y)
    return (X, Y)

# Define the encoder function
def one_hot_encode(labels):
    n_labels = len(labels)
    n_unique_lables = len(np.unique(labels))
    encode = np.zeros((n_labels, n_unique_lables))
    encode[np.arange(n_labels), labels] = 1
    return encode

# Read the datset
X, Y = read_dataset()

# Shuffle the dataset to mix up the rows
X, Y = shuffle(X, Y, random_state=1)

# Convert the dataset into train and test sets
train_x, test_x, train_y, test_y = train_test_split(X, Y, test_size=0.20, random_state=415)

# Inspect the shape of the training and testing sets
print('Shape of train_x:', train_x.shape)
print('Shape of train_y:', train_y.shape)
print('Shape of test_x:', test_x.shape)
print('Shape of test_y:', test_y.shape)

Shape of train_x: (165, 60)
Shape of train_y: (165, 2)
Shape of test_x: (42, 60)
Shape of test_y: (42, 2)

# Define the important parameters and variable to work with the tensors
learning_rate = 0.3
training_epochs = 1000
cost_history = np.empty(shape=[1], dtype=float) # loss function

n_dim = X.shape[1]
print('Dimention n_dim =', n_dim)
n_class = 2
# Save model in NMI (Naval Mine Identifier) folder
model_path = './TensorFlow/NMI/'

# Define the number of hidden layers and neurons for each layer
n_hidden_1 = 60
n_hidden_2 = 60
n_hidden_3 = 60
n_hidden_4 = 60

# Inputs and outputs
x = tf.placeholder(tf.float32, [None, n_dim])
y_ = tf.placeholder(tf.float32, [None, n_class])

# Model parameters
W = tf.Variable(tf.zeros([n_dim, n_class]))
b = tf.Variable(tf.zeros([n_class]))

Dimention n_dim = 60

# Define the model
def multilayer_perceptron(x, weights, biases):

    # Hidden layer with sigmoid activations
    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
    layer_1 = tf.nn.sigmoid(layer_1)

    # Hidden layer with sigmoid activations
    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
    layer_2 = tf.nn.sigmoid(layer_2)

    # Hidden layer with sigmoid activations
    layer_3 = tf.add(tf.matmul(layer_2, weights['h3']), biases['b3'])
    layer_3 = tf.nn.sigmoid(layer_3)

    # Hidden layer with RELU activations
    layer_4 = tf.add(tf.matmul(layer_3, weights['h4']), biases['b4'])
    layer_4 = tf.nn.relu(layer_4)

    # Output layer with linear activations
    out_layer = tf.matmul(layer_4, weights['out']) + biases['out']
    return out_layer

# Define the weights and the biases for each layer
weights = {
    'h1': tf.Variable(tf.truncated_normal([n_dim, n_hidden_1])),
    'h2': tf.Variable(tf.truncated_normal([n_hidden_1, n_hidden_2])),
    'h3': tf.Variable(tf.truncated_normal([n_hidden_2, n_hidden_3])),
    'h4': tf.Variable(tf.truncated_normal([n_hidden_3, n_hidden_4])),
    'out': tf.Variable(tf.truncated_normal([n_hidden_4, n_class])),
}
biases = {
    'b1': tf.Variable(tf.truncated_normal([n_hidden_1])),
    'b2': tf.Variable(tf.truncated_normal([n_hidden_2])),
    'b3': tf.Variable(tf.truncated_normal([n_hidden_3])),
    'b4': tf.Variable(tf.truncated_normal([n_hidden_4])),
    'out': tf.Variable(tf.truncated_normal([n_class])),
}

# Initialize all the variables
init = tf.global_variables_initializer()
saver = tf.train.Saver()

# Call your model defined
y = multilayer_perceptron(x, weights, biases)

# Define the cost function and optimizer
cost_function = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=y, labels=y_))
training_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost_function)

# Launch the graph
sess = tf.Session()
sess.run(init)

mse_history = []
accuracy_history = []

# Calculate the cost and accuracy of each epoch
for epoch in range(training_epochs):
    sess.run(training_step, feed_dict={x: test_x, y_: test_y})
    cost = sess.run(cost_function, feed_dict={x: test_x, y_: test_y})
    cost_history = np.append(cost_history, cost)
    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    pred_y = sess.run(y, feed_dict={x: test_x})
    mse = tf.reduce_mean(tf.square(pred_y - test_y))
    mse_ = sess.run(mse)
    mse_history.append(mse_)
    accuracy = (sess.run(accuracy, feed_dict={x: test_x, y_: test_y}))
    accuracy_history.append(accuracy)

    print('Epoch: {:<6} Cost: {:<25} MSE: {:<22} Training Accuracy: {:<5}'.format(epoch, cost, mse_, accuracy))

save_path = saver.save(sess, model_path)
print('\nModel saved in folder:', save_path)

Epoch: 0      Cost: 87.35811614990234         MSE: 7626.536575162109      Training Accuracy: 0.5  
Epoch: 1      Cost: 6.894620418548584         MSE: 50.3020761355475       Training Accuracy: 0.5  
Epoch: 2      Cost: 3.361487865447998         MSE: 30.955426477005094     Training Accuracy: 0.5  
Epoch: 3      Cost: 0.7260686159133911        MSE: 0.5013900211897269     Training Accuracy: 0.5  
Epoch: 4      Cost: 0.6929373741149902        MSE: 0.4070605510426611     Training Accuracy: 0.5  
Epoch: 5      Cost: 0.6781018376350403        MSE: 0.3915892640169834     Training Accuracy: 0.5  
Epoch: 6      Cost: 0.6673206686973572        MSE: 0.413629547479418      Training Accuracy: 0.5476190447807312
Epoch: 7      Cost: 0.6539391875267029        MSE: 0.43283417493563126    Training Accuracy: 0.5714285969734192
Epoch: 8      Cost: 0.6401854157447815        MSE: 0.7254811923994738     Training Accuracy: 0.8095238208770752
Epoch: 9      Cost: 0.6277029514312744        MSE: 0.712054768438198      Training Accuracy: 0.7142857313156128
Epoch: 10     Cost: 0.6079661846160889        MSE: 0.6807539846352033     Training Accuracy: 0.7142857313156128
Epoch: 11     Cost: 0.5888373255729675        MSE: 0.6808916494234316     Training Accuracy: 0.6904761791229248
Epoch: 12     Cost: 0.5802644491195679        MSE: 0.9947860587779411     Training Accuracy: 0.761904776096344
Epoch: 13     Cost: 0.691802442073822         MSE: 1.2704975080195413     Training Accuracy: 0.5952380895614624
Epoch: 14     Cost: 1.0724416971206665        MSE: 7.073339179326677      Training Accuracy: 0.5  
Epoch: 15     Cost: 0.7017775774002075        MSE: 0.32697795582732325    Training Accuracy: 0.3333333432674408
Epoch: 16     Cost: 0.6909409165382385        MSE: 0.30531752647624294    Training Accuracy: 0.5  
Epoch: 17     Cost: 0.6857782006263733        MSE: 0.29894629882540735    Training Accuracy: 0.5  
Epoch: 18     Cost: 0.6818772554397583        MSE: 0.2998910234735752     Training Accuracy: 0.5  
Epoch: 19     Cost: 0.6782846450805664        MSE: 0.304250631405728      Training Accuracy: 0.6428571343421936
Epoch: 20     Cost: 0.6729066371917725        MSE: 0.30683943536091124    Training Accuracy: 0.6666666865348816
... ... ...
... ... ...  
Epoch: 980    Cost: 0.0004381746693979949     MSE: 65.1975496060161       Training Accuracy: 1.0  
Epoch: 981    Cost: 0.00043725321302190423    MSE: 65.23066313808093      Training Accuracy: 1.0  
Epoch: 982    Cost: 0.00043633501627482474    MSE: 65.24792157525519      Training Accuracy: 1.0  
Epoch: 983    Cost: 0.0004354701086413115     MSE: 65.28058534778091      Training Accuracy: 1.0  
Epoch: 984    Cost: 0.0004345519992057234     MSE: 65.29738636418675      Training Accuracy: 1.0  
Epoch: 985    Cost: 0.00043365085730329156    MSE: 65.31476968373434      Training Accuracy: 1.0  
Epoch: 986    Cost: 0.0004327717761043459     MSE: 65.34742013339917      Training Accuracy: 1.0  
Epoch: 987    Cost: 0.0004318650171626359     MSE: 65.36430631560093      Training Accuracy: 1.0  
Epoch: 988    Cost: 0.00043099772301502526    MSE: 65.38175463251966      Training Accuracy: 1.0  
Epoch: 989    Cost: 0.00043012158130295575    MSE: 65.414328670666        Training Accuracy: 1.0  
Epoch: 990    Cost: 0.00042922041029669344    MSE: 65.4312450261207       Training Accuracy: 1.0  
Epoch: 991    Cost: 0.00042836731881834567    MSE: 65.44871264235509      Training Accuracy: 1.0  
Epoch: 992    Cost: 0.0004275025276001543     MSE: 65.4811798462491       Training Accuracy: 1.0  
Epoch: 993    Cost: 0.0004266126488801092     MSE: 65.49808408031514      Training Accuracy: 1.0  
Epoch: 994    Cost: 0.0004257822292856872     MSE: 65.51554527402554      Training Accuracy: 1.0  
Epoch: 995    Cost: 0.0004249004414305091     MSE: 65.54788411123789      Training Accuracy: 1.0  
Epoch: 996    Cost: 0.0004240360576659441     MSE: 65.56476974501572      Training Accuracy: 1.0  
Epoch: 997    Cost: 0.0004232137289363891     MSE: 65.59666945461045      Training Accuracy: 1.0  
Epoch: 998    Cost: 0.0004223266732878983     MSE: 65.61311084598309      Training Accuracy: 1.0  
Epoch: 999    Cost: 0.0004214906657580286     MSE: 65.6301134269209       Training Accuracy: 1.0  

Model saved in folder: ./TensorFlow/NMI/

# Print the final accuracy
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print('Test Accuracy: ',(sess.run(accuracy, feed_dict={x: test_x, y_: test_y})))

# Print the final mean square error
pred_y = sess.run(y, feed_dict={x: test_x})
mse = tf.reduce_mean(tf.square(pred_y - test_y))
print('Mean Square Error: %.4f' % sess.run(mse))

Test Accuracy:  1.0
Mean Square Error: 65.6301

# Plot Accuracy graph
fig = plt.figure(figsize=(10,7))
plt.plot(accuracy_history)
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.show()

# Plot Loss graph
fig = plt.figure(figsize=(10,7))
plt.plot(range(len(cost_history)),cost_history)
plt.axis([0,training_epochs,0,np.max(cost_history)/100])
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.show()

Using the Model to make Prediction if Rock or Mine¶

# Reading the new dataset
def read_dataset():
    dir_path = "./MLData/00_Misc/"
    df = pd.read_csv(dir_path + "Sonar_new.csv")
    X_new = df[df.columns[0:60]].values
    y_new = df[df.columns[60]]

    # Encode the labels
    encoder = LabelEncoder()
    encoder.fit(y_new)
    y_new = encoder.transform(y_new)
    Y_new = one_hot_encode(y_new)
    return (X_new, Y_new)

# Define the encoder function
def one_hot_encode(labels):
    n_labels = len(labels)
    n_unique_lables = len(np.unique(labels))
    encode = np.zeros((n_labels, n_unique_lables))
    encode[np.arange(n_labels), labels] = 1
    return encode

# Read the datset
X_new, Y_new = read_dataset()

X_new.shape, Y_new.shape

((15, 60), (15, 2))

saver.restore(sess, model_path)

prediction = tf.argmax(y, 1)
correct_prediction = tf.equal(prediction, tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

print("**************************************************************")
print("* 1 stands for M, (i.e. Mine) and 0 stands for R (i.e. Rock) *")
print("**************************************************************")
for i in range(1,15):
    prediction_run = sess.run(prediction, feed_dict={x:X_new[i].reshape(1,60)})
    accuracy_run = sess.run(accuracy, feed_dict={x:X_new[i].reshape(1,60), y_:Y_new[i].reshape(1,2)})
    print(i,"Original Class: ", int(sess.run(y_[i][1],feed_dict={y_:Y_new})), " Predicted Values: ", prediction_run[0] )
    print("Accuracy: ",str(accuracy_run*100)+"%")

INFO:tensorflow:Restoring parameters from ./TensorFlow/NMI/
**************************************************************
* 1 stands for M, (i.e. Mine) and 0 stands for R (i.e. Rock) *
**************************************************************
1 Original Class:  0  Predicted Values:  0
Accuracy:  100.0%
2 Original Class:  1  Predicted Values:  1
Accuracy:  100.0%
3 Original Class:  0  Predicted Values:  0
Accuracy:  100.0%
4 Original Class:  1  Predicted Values:  1
Accuracy:  100.0%
5 Original Class:  0  Predicted Values:  1
Accuracy:  0.0%
6 Original Class:  1  Predicted Values:  1
Accuracy:  100.0%
7 Original Class:  1  Predicted Values:  1
Accuracy:  100.0%
8 Original Class:  1  Predicted Values:  0
Accuracy:  0.0%
9 Original Class:  0  Predicted Values:  0
Accuracy:  100.0%
10 Original Class:  0  Predicted Values:  0
Accuracy:  100.0%
11 Original Class:  1  Predicted Values:  0
Accuracy:  0.0%
12 Original Class:  1  Predicted Values:  1
Accuracy:  100.0%
13 Original Class:  0  Predicted Values:  0
Accuracy:  100.0%
14 Original Class:  1  Predicted Values:  1
Accuracy:  100.0%

Pages

Aug 22, 2020

Example 21: WordCloud in Python

Nov 24, 2018

Example 20: TensorFlow - Rock or Mine Prediction

Using TensorFlow to Create a Model for Making Predictions

TensorFlow to predict if an underwater object is Rock or Mine¶

Creating and Training the Model¶

Using the Model to make Prediction if Rock or Mine¶