tf_DNN.py

# -*- coding: utf-8 -*-
"""
Created on Thu Apr 26 15:29:39 2018

@author: Administrator
"""
import math
import numpy as np
import h5py
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops

def load_dataset():
    train_dataset = h5py.File('datasets/train_signs.h5', "r")
    train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features
    train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels

    test_dataset = h5py.File('datasets/test_signs.h5', "r")
    test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features
    test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels

    classes = np.array(test_dataset["list_classes"][:]) # the list of classes
    
    train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
    test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))
    
    return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes


def random_mini_batches(X, Y, mini_batch_size = 64, seed = 0):
    """
    Creates a list of random minibatches from (X, Y)
    
    Arguments:
    X -- input data, of shape (input size, number of examples)
    Y -- true "label" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples)
    mini_batch_size - size of the mini-batches, integer
    seed -- this is only for the purpose of grading, so that you're "random minibatches are the same as ours.
    
    Returns:
    mini_batches -- list of synchronous (mini_batch_X, mini_batch_Y)
    """
    
    m = X.shape[1]                  # number of training examples
    mini_batches = []
    np.random.seed(seed)
    
    # Step 1: Shuffle (X, Y)
    permutation = list(np.random.permutation(m))
    shuffled_X = X[:, permutation]
    shuffled_Y = Y[:, permutation].reshape((Y.shape[0],m))

    # Step 2: Partition (shuffled_X, shuffled_Y). Minus the end case.
    num_complete_minibatches = math.floor(m/mini_batch_size) # number of mini batches of size mini_batch_size in your partitionning
    for k in range(0, num_complete_minibatches):
        mini_batch_X = shuffled_X[:, k * mini_batch_size : k * mini_batch_size + mini_batch_size]
        mini_batch_Y = shuffled_Y[:, k * mini_batch_size : k * mini_batch_size + mini_batch_size]
        mini_batch = (mini_batch_X, mini_batch_Y)
        mini_batches.append(mini_batch)
    
    # Handling the end case (last mini-batch < mini_batch_size)
    if m % mini_batch_size != 0:
        mini_batch_X = shuffled_X[:, num_complete_minibatches * mini_batch_size : m]
        mini_batch_Y = shuffled_Y[:, num_complete_minibatches * mini_batch_size : m]
        mini_batch = (mini_batch_X, mini_batch_Y)
        mini_batches.append(mini_batch)
    
    return mini_batches

def convert_to_one_hot(Y, C):
    #print([Y.reshape(-1)].T)
    Y = np.eye(C)[Y.reshape(-1)].T
    return Y


def init_parameters_deep(layer_dims):
    
    tf.set_random_seed(1)                   # so that your "random" numbers match ours
    parameters = {}
    L = len(layer_dims)
     
    for l in range(1, L):
        W='WWW' + str(l)
        b='bbb' + str(l)
        parameters['W' + str(l)] = tf.get_variable(W, [layer_dims[l], layer_dims[l-1]],
                   initializer = tf.contrib.layers.xavier_initializer(seed = 1))
        
        parameters['b' + str(l)] = tf.get_variable(b, [layer_dims[l], 1], initializer = tf.zeros_initializer())
            
        assert(parameters['W' + str(l)].shape == (layer_dims[l], layer_dims[l-1]))
        assert(parameters['b' + str(l)].shape == (layer_dims[l], 1))
    
    return parameters

def forward_propagation(X, parameters):
    
    A=X
    L=len(parameters)//2
    for l in range(1,L+1):
        Apre=A
        Z= tf.matmul(parameters["W" + str(l)],Apre)+parameters["b" + str(l)]
        A=tf.nn.relu(Z)
    
    return Z

def compute_cost(Z, Y):

    # to fit the tensorflow requirement for tf.nn.softmax_cross_entropy_with_logits(...,...)
    logits = tf.transpose(Z)
    labels = tf.transpose(Y)
    
    ### START CODE HERE ### (1 line of code)
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = logits, labels = labels))
    ### END CODE HERE ###
    
    return cost
def create_placeholders(n_x, n_y):

    ### START CODE HERE ### (approx. 2 lines)
    X = tf.placeholder(tf.float32, [n_x, None], name = "X")
    Y = tf.placeholder(tf.float32, [n_y, None], name = "Y")
    ### END CODE HERE ###
    
    return X, Y
def modle(X_train, Y_train, X_test, Y_test,layer_dims,learning_rate = 0.0001,
          num_epochs = 1500, minibatch_size = 32, print_cost = True):
     
    ops.reset_default_graph()                         # to be able to rerun the model without overwriting tf variables
    tf.set_random_seed(1)                             # to keep consistent results
    seed = 3                                          # to keep consistent results
    (n_x, m) = X_train.shape                          # (n_x: input size, m : number of examples in the train set)
    n_y = Y_train.shape[0]
    X, Y = create_placeholders(n_x, n_y)
    
    costs = []
    
    
    parameters=init_parameters_deep(layer_dims)

    Z = forward_propagation(X, parameters)

    cost = compute_cost(Z, Y)
    
    optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate).minimize(cost)
    
    init = tf.global_variables_initializer()
    
    
    with tf.Session() as sess:
        
        # Run the initialization
        sess.run(init)
        
        # Do the training loop
        for epoch in range(num_epochs):

            epoch_cost = 0.                       # Defines a cost related to an epoch
            num_minibatches = int(m / minibatch_size) # number of minibatches of size minibatch_size in the train set
            seed = seed + 1
            minibatches = random_mini_batches(X_train, Y_train, minibatch_size, seed)

            for minibatch in minibatches:

                # Select a minibatch
                (minibatch_X, minibatch_Y) = minibatch
                
                # IMPORTANT: The line that runs the graph on a minibatch.
                # Run the session to execute the "optimizer" and the "cost", the feedict should contain a minibatch for (X,Y).
                ### START CODE HERE ### (1 line)
                _ , minibatch_cost = sess.run([optimizer, cost], feed_dict={X: minibatch_X, Y: minibatch_Y})
                ### END CODE HERE ###
                
                epoch_cost += minibatch_cost / num_minibatches

            # Print the cost every epoch
            if print_cost == True and epoch % 100 == 0:
                print ("Cost after epoch %i: %f" % (epoch, epoch_cost))
            if print_cost == True and epoch % 5 == 0:
                costs.append(epoch_cost)
                
        # plot the cost
        plt.plot(np.squeeze(costs))
        plt.ylabel('cost')
        plt.xlabel('iterations (per tens)')
        plt.title("Learning rate =" + str(learning_rate))
        plt.show()

        # lets save the parameters in a variable
        parameters = sess.run(parameters)
        print ("Parameters have been trained!")

        # Calculate the correct predictions
        correct_prediction = tf.equal(tf.argmax(Z), tf.argmax(Y))

        # Calculate accuracy on the test set
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

        print ("Train Accuracy:", accuracy.eval({X: X_train, Y: Y_train}))
        print ("Test Accuracy:", accuracy.eval({X: X_test, Y: Y_test}))
        
        return parameters
    

def main():
    
    X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes=load_dataset()
    print(Y_test_orig)
    # Flatten the training and test images
    X_train_flatten = X_train_orig.reshape(X_train_orig.shape[0], -1).T
    X_test_flatten = X_test_orig.reshape(X_test_orig.shape[0], -1).T
    # Normalize image vectors
    X_train = X_train_flatten/255.
    X_test = X_test_flatten/255.
    # Convert training and test labels to one hot matrices
    Y_train = convert_to_one_hot(Y_train_orig, 6)
    Y_test = convert_to_one_hot(Y_test_orig, 6)

    in_n=X_train.shape[0]
    out_n=6

    layer_dims=(in_n,25,12,out_n)#任意层 
    parameters=modle(X_train,Y_train,X_test,Y_test,layer_dims)