defdropout_layer(one_layer: tf.tensor, dropout_probability: float): assert0 <= dropout_probability <= 1 if dropout_probability == 1: # in this case, all elements are dropped out return tf.zeros_like(one_layer) # tf.zeros_like: create a tensor with all elements set to zero
if dropout_probability == 0: # in this case, all elements are kept return one_layer
# tf.random.uniform: outputs random values from a uniform distribution. # with (1-p)'s probability that value will become x / (1-p) mask = tf.random.uniform(shape=tf.shape(one_layer), minval=0, maxval=1) < (1 - dropout_probability)
from liner_regression.fashion_mnist_dataset import *
# read data batch_size = 256 train_data_iter, test_data_iter = load_data_fashion_mnist(batch_size)
# initial model parameters # each image in dataset is a 28 * 28 image, in this section, we will flatten each image, # treat them as vectors of length 784 # so X's size is 256 * 784, W's size is 784 * 10, b's size is 1 * 10, y's size is 256 * 10 (y = softmax(XW + b)) num_inputs = 28 * 28 num_outputs = 10
W = tf.Variable(tf.random.normal(shape=(num_inputs, num_outputs), mean=0, stddev=0.01)) b = tf.Variable(tf.zeros(num_outputs))
# define softmax operation defsoftmax(linear_result: tf.Variable): # if linear_result is n * m matrix
# exped is n * m matrix exped = tf.exp(linear_result) # sum_of_each_line is n * 1 matrix, if keepdims=False, then sum_of_each_line will be 1 * n matrix sum_of_each_line = tf.reduce_sum(exped, 1, keepdims=True) return exped / sum_of_each_line
# define loss, use cross-entropy loss defcross_entropy(predicted_y, label_y): # predicted_y is a n * m matrix, then label_y is a 1 * n matrix # in this example, predicted_y is 256 * 10, label_y = 1 * 256 return -tf.math.log(tf.boolean_mask(predicted_y, tf.one_hot(label_y, depth=predicted_y.shape[-1])))
# define optimizer defstochastic_gradient_descent(params, gradients, batch_size, learning_rate: float): # Because our loss is calculated as a sum over the mini-batch of examples, # we normalize our step size by the batch size (batch_size), # so that the magnitude of a typical step size does not depend heavily on our choice of the batch size. for param, grad inzip(params, gradients): param.assign_sub(grad * learning_rate / batch_size)
# classification accuracy defaccuracy(predicted_y, label_y): # predicted_y is a n * m matrix, then label_y is a 1 * n matrix # in this example, predicted_y is 256 * 10, label_y = 1 * 256 # tf.argmax returns the index with the largest value across axes of a tensor. predicted_y = tf.argmax(predicted_y, axis=1)
# cmp is a 1 * n `boolean` matrix cmp = tf.cast(predicted_y, label_y.dtype) == label_y # return num of right predictions and the total num of predictions return tf.reduce_sum(tf.cast(cmp, label_y.dtype)), label_y.shape[0]
# training deftrain(): for _ inrange(3): num_right_predictions = 0 num_total_predictions = 0 for x, y in train_data_iter: with tf.GradientTape() as g: x = tf.reshape(x, shape=(x.shape[0], -1)) y_hat = net(x, W, b) l = cross_entropy(y_hat, y)
//other class a car builder that need classCarEngine; classGPS;
//a pure abstract class to use as an interface classCarBuilder { public: virtualvoidreset()= 0; virtualvoidsetSeats(int number)= 0; virtualvoidsetEngine(const CarEngine &engine)= 0; virtualvoidsetGPS(const GPS &gps)= 0; };
classCar; //a car builder that build car itself classCarCarBuilder: public CarBuilder { private: Car *_car; public: virtualvoidreset()override{ if (_car) { delete _car; } _car = newCar(); }
virtualvoidsetSeats(int number)override{ //set seat for car itself }
virtualvoidsetEngine(const CarEngine &engine)override{ //set engine for car itself }
virtualvoidsetGPS(const GPS &gps)override{ //set gps for car itself }
virtual Car* getResult(){ return _car; }; };
classCarManual; //a car builder that build car's manual classCarManualBuilder: public CarBuilder { private: CarManual *_manual;
//a manager class that use builder to build car classCarCarBuilderDirector { public: Car* buildSUV(CarBuilder &builder){ builder.setSeats(4); NormalEngine normalEngine; builder.setEngine(normalEngine); NormalGPS normalGps; builder.setGPS(normalGps); }
