机器学习_多层神经网络

cd D:/DATASET/model2

import time
import numpy as np
import h5py
import matplotlib.pyplot as plt
import scipy
from PIL import Image
from scipy import ndimage
from m2_uits import *

%matplotlib inline
plt.rcParams['figure.figsize'] = (5.0, 4.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

%load_ext autoreload
%autoreload 2

np.random.seed(1)

# Loading the data (cat/non-cat)
train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()

#查看数据集大小
m_train = train_set_x_orig.shape[0]
m_test = test_set_x_orig.shape[0]
num_px = train_set_x_orig.shape[1]

print ("Number of training examples: m_train = " + str(m_train))
print ("Number of testing examples: m_test = " + str(m_test))
print ("Height/Width of each image: num_px = " + str(num_px))
print ("Each image is of size: (" + str(num_px) + ", " + str(num_px) + ", 3)")
print ("train_set_x shape: " + str(train_set_x_orig.shape))
print ("train_set_y shape: " + str(train_set_y.shape))
print ("test_set_x shape: " + str(test_set_x_orig.shape))
print ("test_set_y shape: " + str(test_set_y.shape))

# 对数据集回炉重造--测试集和训练集
train_set_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0], -1).T   # The "-1" makes reshape flatten the remaining dimensions
test_set_x_flatten = test_set_x_orig.reshape(test_set_x_orig.shape[0], -1).T

# 标准化
train_set_x = train_set_x_flatten/255.
test_set_x = test_set_x_flatten/255.

#12288=64*64*3
print ("train_set_x's shape: " + str(train_set_x.shape))
print ("test_set_x's shape: " + str(test_set_x.shape))

### 把该自己写的常量写出来，长宽深 ####
n_x = 12288     # num_px * num_px * 3
n_h = 7
n_y = 1
layers_dims = (n_x, n_h, n_y)

# 注意注意建模了 two_layer_model
#长征第三步

def two_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):
    np.random.seed(1)
    grads = {}
    costs = []                              # to keep track of the cost
    m = X.shape[1]                           # number of examples
    (n_x, n_h, n_y) = layers_dims
    
    # 从Initialize parameters 来的
    parameters = initialize_parameters(n_x, n_h, n_y)

    # 从定义的parameters中得到这几个值
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]
    
    # Loop (gradient descent)
    for i in range(0, num_iterations):

        # Forward propagation: LINEAR -> RELU -> LINEAR -> SIGMOID. Inputs: "X, W1, b1". Output: "A1, cache1, A2, cache2".
        A1, cache1 =linear_activation_forward(X, W1, b1, activation = "relu")
        A2, cache2 = linear_activation_forward(A1, W2, b2, activation = "sigmoid")
       
        # Compute cost
        cost = compute_cost(A2, Y)
              
        # Initializing backward propagation
        dA2 = - (np.divide(Y, A2) - np.divide(1 - Y, 1 - A2))
        
        # Backward propagation. Inputs: "dA2, cache2, cache1". Outputs: "dA1, dW2, db2; also dA0 (not used), dW1, db1".
        dA1, dW2, db2 = linear_activation_backward(dA2, cache2, activation = "sigmoid")
        dA0, dW1, db1 = linear_activation_backward(dA1, cache1, activation = "relu")
       
        # Set grads['dWl'] to dW1, grads['db1'] to db1, grads['dW2'] to dW2, grads['db2'] to db2
        grads['dW1'] = dW1
        grads['db1'] = db1
        grads['dW2'] = dW2
        grads['db2'] = db2
        
        # Update parameters.
        parameters = update_parameters(parameters, grads, learning_rate)
  
        # Retrieve W1, b1, W2, b2 from parameters
        W1 = parameters["W1"]
        b1 = parameters["b1"]
        W2 = parameters["W2"]
        b2 = parameters["b2"]
        
        # Print the cost every 100 training example
        if print_cost and i % 100 == 0:
            print("Cost after iteration {}: {}".format(i, np.squeeze(cost)))
        if print_cost and i % 100 == 0:
            costs.append(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()
    
    return parameters

parameters = two_layer_model(train_set_x, train_set_y, layers_dims = (n_x, n_h, n_y), num_iterations = 2500, print_cost=True)

predictions_train = predict(train_set_x, train_set_y, parameters)

predictions_test = predict(test_set_x, test_set_y, parameters)

#5-layers-model
### CONSTANTS ###
layers_dims = [12288, 20, 7, 5, 1] #  5-layer model
# GRADED FUNCTION: L_layer_model
def L_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):#lr可以多试试几个
    np.random.seed(1)
    costs = []                         # keep track of cost
    
    # Parameters initialization.
    parameters = initialize_parameters_deep(layers_dims)

    
    # Loop (gradient descent)
    for i in range(0, num_iterations):
        # Forward propagation: [LINEAR -> RELU]*(L-1) -> LINEAR -> SIGMOID.     
        AL, caches = L_model_forward(X, parameters)
      
        # Compute cost.       
        cost = compute_cost(AL, Y)
            
        # Backward propagation.       
        grads = L_model_backward(AL, Y, caches)
         
        # Update parameters.        
        parameters = update_parameters(parameters, grads, learning_rate)
                       
        # Print the cost every 100 training example
        if print_cost and i % 100 == 0:
            print ("Cost after iteration %i: %f" %(i, cost))
        if print_cost and i % 100 == 0:
            costs.append(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()
    
    return parameters

parameters = L_layer_model(train_set_x, train_set_y, layers_dims, num_iterations = 2500, print_cost = True)

pred_train = predict(train_set_x, train_set_y, parameters)

pred_test = predict(test_set_x, test_set_y, parameters)

print_mislabeled_images(classes, test_set_x, test_set_y, pred_test)

#用model来测测
my_image = "dogcheck.jpg" 
my_label_y = [1] 
fname = my_image
image = np.array(plt.imread(fname))
my_image = np.array(Image.fromarray(image).resize(size=(num_px,num_px))).reshape((num_px*num_px*3,1))
my_predicted_image = predict(my_image, my_label_y, parameters)
plt.imshow(image)
print ("y = " + str(np.squeeze(my_predicted_image)) + ", your L-layer model predicts a \"" + classes[int(np.squeeze(my_predicted_image)),].decode("utf-8") +  "\" picture.")