# -*- coding: utf-8 -*-
"""Classification_Fashion_MNIST.ipynb

"""

!pip uninstall tensorflow

"""Installing TensorFlow 2.0.0."""

!pip install tensorflow===2.0.0

"""Check TensorFolow Version:"""

import tensorflow as tf
print(tf.__version__)

"""Now the next step is to load MNIST dataset and then prepare it. As a part of data preparation process integers from the sample data set has to be converted to floating-point numbers. Here is the code:"""

import tensorflow as tf

mnist = tf.keras.datasets.fashion_mnist

(x_train, labels_train), (x_test, labels_test) = mnist.load_data()

x_train, x_test = x_train/225.0, x_test/255.0

"""Variables to hold image categories:"""

class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress','Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

"""Check shape of the image:"""

print(x_train[0].shape)

"""Print Image:"""

import matplotlib.pyplot as plt

plt.figure()
plt.imshow(x_train[0])
plt.colorbar()
plt.grid(False)
plt.show()

"""Images categories:

Print some of the images with category name:
"""

plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(x_train[i])
    plt.xlabel(class_names[labels_train[i]])
plt.show()

"""If you want to show the grey image use following code:"""

plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(x_train[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[labels_train[i]])
plt.show()

"""Now we will create model with following code:"""

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10, activation='softmax')
])

"""Here is the code to display model summary:"""

model.summary()

"""Now we will compile our model with following code:"""

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

"""Finally run the training with following code:"""

model.fit(x_train, y_train, epochs=5)

"""Now let's evaluate our model with following code:"""

model.evaluate(x_test, y_test)

"""Run the predictions on the test data with following code:"""

predictions = model.predict(x_test)

"""Print the pridiction result:"""

print(predictions[3])

"""Print"""

import numpy as np

def plot_image(i, predictions_array, true_label, img):
  predictions_array, true_label, img = predictions_array, true_label[i], img[i]
  plt.grid(False)
  plt.xticks([])
  plt.yticks([])
  plt.imshow(img)
  predicted_label = np.argmax(predictions_array)
  if predicted_label == true_label:
    color = 'blue'
  else:
    color = 'red'
  plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],
                                100*np.max(predictions_array),
                                class_names[true_label]),
                                color=color)

#print the images
num_rows = 5
num_cols = 4
num_images = num_rows*num_cols
plt.figure(figsize=(2*num_cols, 2*num_rows))
for i in range(num_images):
  plt.subplot(num_rows, num_cols, i+1)
  plot_image(i, predictions[i], labels_test, x_test)
plt.tight_layout()
plt.show()