is a subpart of machine learning and artificial intelligence which is also known as deep neural network this networks capable of learning unsupervised from provided data which is unorganized or unlabeled. today, we will implement a neural network in 6 easy steps using TensorFlow to classify handwritten digits. Deep learning Modules required : NumPy: $ pip install numpy Matplotlib: $ pip install matplotlib Tensorflow: $ pip install tensorflow Steps to follow: Importing all dependence Step 1 : tensorflow tf numpy np matplotlib.pyplot plt import as import as import as Import data and normalize it Step 2 : mnist = tf.keras.datasets.mnist (x_train,y_train) , (x_test,y_test) = mnist.load_data() x_train = tf.keras.utils.normalize(x_train,axis= ) x_test = tf.keras.utils.normalize(x_test,axis= ) 1 1 view data Step 3 : plt.imshow(n,cmap=plt.cm.binary) plt.show() draw(x_train[ ]) : def draw (n) 0 make a neural network and train it Step 4 : model = tf.keras.models.Sequential() model.add(tf.keras.layers.Flatten(input_shape=( , ))) model.add(tf.keras.layers.Dense( ,activation=tf.nn.relu)) model.add(tf.keras.layers.Dense( ,activation=tf.nn.relu)) model.add(tf.keras.layers.Dense( ,activation=tf.nn.softmax)) model.compile(optimizer= , loss= , metrics=[ ] ) model.fit(x_train,y_train,epochs= ) #there are two types of models #sequential is most common 28 28 #reshape 128 128 10 'adam' 'sparse_categorical_crossentropy' 'accuracy' 3 check model accuracy and loss Step 5 : val_loss,val_acc = model.evaluate(x_test,y_test) print( ,val_loss, ,val_acc) "loss-> " "\nacc-> " prediction using model Step 6 : predictions=model.predict([x_test]) print( ,y_test[ ]) print( ,np.argmax(predictions[ ])) draw(x_test[ ]) 'lable -> ' 2 'prediction -> ' 2 2
