Training of your first neural network: A Basic classification

Documentation on Neural Network: theroyakash

This guide trains a neural network model to classify images of clothing, like sneakers and shirts. It’s okay if you don’t understand all the details; this is a fast-paced overview of a complete TensorFlow program with the details explained as we go.This guide uses tf.keras, a high-level API to build and train models in TensorFlow,

!pip install -q tensorflow==2.0.0-alpha0from __future__ import absolute_import, division, print_function, unicode_literals# TensorFlow and tf.kerasimport tensorflow as tffrom tensorflow import keras# Helper librariesimport numpy as npimport matplotlib.pyplot as pltprint(tf.__version__)# Output Here2.0.0-alpha0

Import the Fashion MNIST dataset

This guide uses the Fashion MNISTdataset which contains 70,000 grayscale images in 10 categories. The images show individual articles of clothing at low resolution(28by 28 pixels), as seen here:

Fashion MNIST is intended as a drop-in replacement for the classic MNISTdataset—often used as the”Hello,World” of machine learning programs for computer vision. The MNIST dataset contains images of handwritten digits(0,1, 2, etc.) in a format identical to that of the articles of clothing we’ll use here.This guide uses Fashion MNIST for variety, and because it’s a slightly more challenging problem than regular MNIST. Both datasets are relatively small and are used to verify that an algorithm works as expected. They’re good starting points to test and debug code.We will use 60,000 images to train the network and 10,000 images to evaluate how accurately the network learned to classify images. You can access the Fashion MNIST directly from TensorFlow. Import and load the Fashion MNIST data directly from TensorFlow:
fashion_mnist = keras.datasets.fashion_mnist(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

Output Form Console

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz32768/29515 [=================================] - 0s 0us/stepDownloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz26427392/26421880 [==============================] - 1s 0us/stepDownloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz8192/5148 [===============================================] - 0s 0us/stepDownloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz4423680/4422102 [==============================] - 0s 0us/step
Loading the dataset returns four NumPy arrays:

• The train_imagesand train_labelsarrays are the training set—the data the model uses to learn.
• The model is tested against the test set, the test_images, and test_labelsarrays.

The images are 28×28 NumPy arrays, with pixel values ranging from 0 to 255. The labelsare an array of integers, ranging from 0 to 9. These correspond to the classof clothing the image represents:

Each image is mapped to a single label. Since the class namesare not included with the dataset, store them here to use later when plotting the images:
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

Exploring the data:

Let’s explore the format of the dataset before training the model. The following shows there are 60,000 images in the training set, with each image represented as 28 x 28 pixels:
train_images.shape//output here:(60000, 28, 28)
Likewise, there are 60,000 labels in the training set:len(train_labels)
60000
Each label is an integer between 0 and 9:train_labelsarray([9, 0, 0, ..., 3, 0, 5], dtype=uint8)
There are 10,000 images in the test set. Again, each image is represented as 28 x 28 pixels:test_images.shape(10000, 28, 28)
And the test set contains 10,000 images labels:len(test_labels)//output here10000

Preprocessing of the data:

The data must be preprocessed before training the network. If you inspect the first image in the training set, you will see that the pixel values fall in the range of 0 to 255:
plt.figure()plt.imshow(train_images[0])plt.colorbar()plt.grid(False)plt.show()
We scale these values to a range of 0 to 1 before feeding them to the neural network model. To do so, we divide the values by 255. It’s important that the training setand the testing setbe preprocessed in the same way
train_images = train_images / 255.0test_images = test_images / 255.0
To verify that the data is in the correct format and that we’re ready to build and train the network, let’s display the first 25 images from the training setand display the class name below each image.

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(train_images[i], cmap=plt.cm.binary)    plt.xlabel(class_names[train_labels[i]])plt.show()

Build the model:

Building the neural network requires configuring the layers of the model, then compiling the model.

Set up the layers:

The basic building block of a neural network is the layer. Layers extract representations from the data fed into them. Hopefully, these representations are meaningful for the problem at hand.Most of deep learning consists of chaining together simple layers. Most layers, such as tf.keras.layers.Dense, have parameters that are learned during training.
model = keras.Sequential([    keras.layers.Flatten(input_shape=(28, 28)),    keras.layers.Dense(128, activation='relu'),    keras.layers.Dense(10, activation='softmax')])
The first layer in this network, tf.keras.layers.Flatten, transforms the format of the images from a two-dimensional array(of28 by 28 pixels) to a one-dimensional array(of28 * 28 = 784 pixels). Think of this layer as unstacking rows of pixels in the image and lining them up. This layer has no parameters to learn; it only reformats the data.After the pixels are flattened, the network consists of a sequence of two tf.keras.layers.Denselayers. These are densely connected, or fully connected, neural layers. The first Denselayer has 128 nodes(orneurons). The second(andlast) layer is a 10-node softmaxlayer that returns an array of 10 probability scores that sum to 1. Each node contains a score that indicates the probability that the current image belongs to one of the 10 classes.

Compile the model:

Before the model is ready for training, it needs a few more settings. These are added during the model’s compilestep:

• Loss function—Thismeasures how accurate the model is during training. We want to minimize this function to”steer”the model in the right direction.
• Optimizer—Thisis how the model is updated based on the data it sees and its loss function.
• Metrics—Usedto monitor the training and testing steps. The following example uses accuracy, the fraction of the images that are correctly classified.

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

Training of the model:

Training the neural network model requires the following steps:

1. Feed the training data to the model. In this example, the training data is in the train_imagesand train_labelsarrays.
2. The model learns to associate images and labels.
3. We ask the model to make predictions about a test set—in this example, the test_imagesarray. We verify that the predictions match the labels from the test_labelsarray.

To start training, call the model.fitmethod—so called because it”fits”the model to the training data:
model.fit(train_images, train_labels, epochs=5)
Epoch 1/560000/60000 [==============================] - 5s 79us/sample - loss: 0.5052 - accuracy: 0.8217Epoch 2/560000/60000 [==============================] - 4s 68us/sample - loss: 0.3757 - accuracy: 0.8636Epoch 3/560000/60000 [==============================] - 5s 76us/sample - loss: 0.3361 - accuracy: 0.8770Epoch 4/560000/60000 [==============================] - 5s 77us/sample - loss: 0.3120 - accuracy: 0.8853Epoch 5/560000/60000 [==============================] - 5s 80us/sample - loss: 0.2936 - accuracy: 0.8913<tensorflow.python.keras.callbacks.History at 0x7f7014a60828>
As the model trains, the loss and accuracy metrics are displayed. This model reaches an accuracy of about 0.88(or88%) on the training data.

Evaluate the accuracy

Next, compare how the model performs on the test dataset:
test_loss, test_acc = model.evaluate(test_images, test_labels)print('\nTest accuracy:', test_acc)
10000/10000 [==============================] - 0s 47us/sample - loss: 0.3429 - accuracy: 0.8736Test accuracy: 0.8736
It turns out that the accuracy on the test dataset is a little less than the accuracy on the training dataset. This gap between training accuracy and test accuracy represents overfitting. Overfitting is when a machine learning model performs worse on new, previously unseen inputs than on the training data.

Make Predictions:

With the model trained, we can use it to make predictions about some images.
predictions = model.predict(test_images)
Here, the model has predicted the label for each image in the testing set. Let’s take a look at the first prediction:
predictions[0]
array([6.2482708e-05, 2.4860196e-08, 9.7165821e-07, 4.7436039e-08,       2.0804382e-06, 1.3316551e-02, 9.8731316e-06, 3.4591161e-02,       1.2390658e-04, 9.5189297e-01], dtype=float32)
A prediction is an array of 10 numbers. They represent the model’s”confidence”that the image corresponds to each of the 10 different articles of clothing. We can see which label has the highest confidence value:
np.argmax(predictions[0])
9
So, the model is most confident that this image is an ankle boot, or class_names[9]. Examining the test label shows that this classification is correct:
test_labels[0]
9
We can graph this to look at the full set of 10 channels.
def plot_image(i, predictions_array, true_label, img):  predictions_array, true_label, img = predictions_array[i], true_label[i], img[i]  plt.grid(False)  plt.xticks([])  plt.yticks([])  plt.imshow(img, cmap=plt.cm.binary)  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)def plot_value_array(i, predictions_array, true_label):  predictions_array, true_label = predictions_array[i], true_label[i]  plt.grid(False)  plt.xticks([])  plt.yticks([])  thisplot = plt.bar(range(10), predictions_array, color="#777777")  plt.ylim([0, 1])  predicted_label = np.argmax(predictions_array)  thisplot[predicted_label].set_color('red')  thisplot[true_label].set_color('blue')
Let’s look at the 0th image, predictions, and prediction array.i = 0plt.figure(figsize=(6,3))plt.subplot(1,2,1)plot_image(i, predictions, test_labels, test_images)plt.subplot(1,2,2)plot_value_array(i, predictions,  test_labels)plt.show()

i = 12plt.figure(figsize=(6,3))plt.subplot(1,2,1)plot_image(i, predictions, test_labels, test_images)plt.subplot(1,2,2)plot_value_array(i, predictions,  test_labels)plt.show()

Let’s plot several images with their predictions. Correct prediction labels are blue and incorrect prediction labels are red. The number gives the percentage(outof 100) for the predicted label. Note that the model can be wrong even when very confident.
# Plot the first X test images, their predicted labels, and the true labels.# Color correct predictions in blue and incorrect predictions in red.num_rows = 5num_cols = 3num_images = num_rows*num_colsplt.figure(figsize=(2*2*num_cols, 2*num_rows))for i in range(num_images):  plt.subplot(num_rows, 2*num_cols, 2*i+1)  plot_image(i, predictions, test_labels, test_images)  plt.subplot(num_rows, 2*num_cols, 2*i+2)  plot_value_array(i, predictions, test_labels)plt.show()

Finally, use the trained model to make a prediction about a single image.
# Grab an image from the test dataset.img = test_images[0]print(img.shape)(28, 28)
tf.kerasmodels are optimized to make predictions on a batch, or collection, of examples at once. Accordingly, even though we’re using a single image, we need to add it to a list:
# Add the image to a batch where it's the only member.img = (np.expand_dims(img,0))print(img.shape)
(1, 28, 28)
Now predict the correct label for this image:
predictions_single = model.predict(img)print(predictions_single)
[[6.2482643e-05 2.4860242e-08 9.7165639e-07 4.7435947e-08 2.0804341e-06  1.3316551e-02 9.8731216e-06 3.4591142e-02 1.2390669e-04 9.5189297e-01]]
plot_value_array(0, predictions_single, test_labels)_ = plt.xticks(range(10), class_names, rotation=45)

model.predictreturns a list of lists—one list for each image in the batch of data. Grab the predictions for our(only)image in the batch:
np.argmax(predictions_single[0])
9
And, as before, the model predicts a label of 9.