深度学习1-2

# -*- coding: utf-8 -*-
"""
Created on Thu Aug  1 16:30:55 2019

@author: Administrator
"""

import numpy as np
import matplotlib.pyplot as plt
import h5py
import scipy
from PIL import Image
from scipy import ndimage   
import scipy.misc
#from lr_utils import load_dataset


#train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()#加载数据

train_dataset = h5py.File("D:/deeplearning/dataset/train_catvnoncat.h5")
test_dataset = h5py.File("D:/deeplearning/dataset/test_catvnoncat.h5")

train_set_x_orig = np.array(train_dataset["train_set_x"][:])#加载训练数据(209, 64, 64, 3)
train_set_y_orig = np.array(train_dataset["train_set_y"][:])

test_set_x_orig = np.array(test_dataset["test_set_x"][:])
test_set_y_orig = np.array(test_dataset["test_set_y"][:])
classes = np.array(test_dataset["list_classes"][:]) # the list of classes


train_set_y = train_set_y_orig.reshape(1,train_set_y_orig.shape[0])
test_set_y = test_set_y_orig.reshape(1,test_set_y_orig.shape[0])

# Example of a picture
index = 40 #25th图
plt.imshow(train_set_x_orig[index])
print ("y = " + str(train_set_y[:, index]) + ", it's a '" + classes[np.squeeze(train_set_y[:, index])].decode("utf-8") +  "' picture.")


### START CODE HERE ### (≈ 3 lines of code)
m_train = train_set_x_orig.shape[0]
m_test = test_set_x_orig.shape[0]
num_px = train_set_x_orig.shape[1]
### END CODE HERE ###

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))

# Reshape the training and test examples

### START CODE HERE ### (≈ 2 lines of code)
train_set_x_flatten = train_set_x_orig.reshape(m_train, -1).T
test_set_x_flatten = test_set_x_orig.reshape(m_test, -1).T
### END CODE HERE ###

print ("train_set_x_flatten shape: " + str(train_set_x_flatten.shape))
print ("train_set_y shape: " + str(train_set_y.shape))
print ("test_set_x_flatten shape: " + str(test_set_x_flatten.shape))
print ("test_set_y shape: " + str(test_set_y.shape))
print ("sanity check after reshaping: " + str(train_set_x_flatten[0:5,0]))

train_set_x = train_set_x_flatten/255.
test_set_x = test_set_x_flatten/255.


#the logistic function
def sigmod(x):
    s = 1.0/ (1 + 1 / np.exp(x))
    return s
#Sigmoid gradient
def sigmod_derivative(x):
    s = 1.0 / (1 + 1/ np.exp(x))
    ds = s * (1-s)
    return ds

def image2vector(image):
    x = image.reshape(image.shape[0] * image.shape[1] * image.shape[2],1)
    return x

def normalizeRows(x):
    x_norm = np.linalg.norm(x,axis=1,keepdims=True)#计算行范数
    s = x / x_norm
    return s

# Gradient function L1
def L1(yhat,y):
    loss = np.sum(np.abs(y - yhat))
    return loss

# Gradient function L2
def L2(yhat,y):
    loss = np.sum(np.power((yhat - y),2))
    return loss

def initialize_with_zeros(dim):
    w = np.zeros((dim,1))
    b = 0
    assert(w.shape == (dim,1))
    assert(isinstance(b,float) or isinstance(b,int))
    return w,b
#propagate function
def propagate(w,b,X,Y):
    m = X.shape[1]
    A = sigmod(np.dot(w.T,X)+b)
    cost = -(1/m)*np.sum(Y*np.log(A)+(1-Y)*np.log(1-A))
    dw = 1/m*np.dot(X,(A-Y).T)
    db = 1/m*np.sum(A-Y)
    assert(dw.shape == w.shape)
    assert(db.dtype == float)
    cost == np.squeeze(cost)
    assert(cost.shape == ())
    grads = {"dw":dw,
             "db":db
            }
    return grads,cost

def optimize(w,b,X,Y,num_iterations,learning_rate):
    costs=[]
    for i in range(num_iterations):
        grads,cost = propagate(w,b,X,Y)
        dw = grads["dw"]
        db = grads["db"]
        w = w - learning_rate*dw
        b = b - learning_rate*db
        if i % 100 == 0:
            costs.append(cost)
        if i % 100 == 0:
            print ("Cost after iteration %i: %f" %(i, cost))
    params = {"w":w,
              "b":b
            }
    grads = {"dw":dw,
             "db":db
            }
    return params,grads,costs

def predict(w,b,X):
    m = X.shape[1]
    Y_prediction = np.zeros((1,m))
    w = w.reshape(X.shape[0],1)
    A = sigmod(np.dot(w.T,X)+b)
    for i in range(A.shape[1]):
        if A[0,i] > 0.5:
            Y_prediction[0,i] = 1
        else:
            Y_prediction[0,i] = 0
    assert(Y_prediction.shape == (1, m))
    return Y_prediction

def model(X_train, Y_train, X_test, Y_test, num_iterations = 2000, learning_rate = 0.5):
    w,b = initialize_with_zeros(X_train.shape[0])
    parameters, grads, costs = optimize(w,b,X_train, Y_train,num_iterations,learning_rate)
    w = parameters["w"]
    b = parameters["b"]
    Y_prediction_test = predict(w, b, X_test)
    Y_prediction_train = predict(w, b, X_train)
    print("train accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_train - Y_train)) * 100))
    print("test accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_test - Y_test)) * 100))


    d = {"costs": costs,
         "Y_prediction_test": Y_prediction_test, 
         "Y_prediction_train" : Y_prediction_train, 
         "w" : w, 
         "b" : b,
         "learning_rate" : learning_rate,
         "num_iterations": num_iterations}

    return d

d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005)
costs = np.squeeze(d["costs"])
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('iterations (per hundreds)')
plt.title("learning_rate"+str(d["learning_rate"]))
plt.show()


learning_rates = [0.01, 0.001, 0.0001]
models = {}
for i in learning_rates:
    print ("learning rate is: " + str(i))
    models[str(i)] = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 1500, learning_rate = i)
    print ('\n' + "-------------------------------------------------------" + '\n')

for i in learning_rates:
    plt.plot(np.squeeze(models[str(i)]["costs"]), label= str(models[str(i)]["learning_rate"]))

plt.ylabel('cost')
plt.xlabel('iterations')

legend = plt.legend(loc='upper center', shadow=True)
frame = legend.get_frame()
frame.set_facecolor('0.90')
plt.show()


## START CODE HERE ## (PUT YOUR IMAGE NAME) 
my_image = "Sample1.jpg"   # change this to the name of your image file 
## END CODE HERE ##

# We preprocess the image to fit your algorithm.
fname = my_image
image = np.array(ndimage.imread(fname, flatten=False))
my_image = scipy.misc.imresize(image, size=(num_px,num_px)).reshape((1, num_px*num_px*3)).T
my_predicted_image = predict(d["w"], d["b"], my_image)

plt.imshow(image)
print("y = " + str(np.squeeze(my_predicted_image)) + ", your algorithm predicts a \"" + classes[int(np.squeeze(my_predicted_image)),].decode("utf-8") +  "\" picture.")


    
    
    
    
    
    

 运行结果：

y = [0], it's a 'non-cat' picture.

 

Number of training examples: m_train = 209
Number of testing examples: m_test = 50
Height/Width of each image: num_px = 64
Each image is of size: (64, 64, 3)
train_set_x shape: (209, 64, 64, 3)
train_set_y shape: (1, 209)
test_set_x shape: (50, 64, 64, 3)
test_set_y shape: (1, 50)
train_set_x_flatten shape: (12288, 209)
train_set_y shape: (1, 209)
test_set_x_flatten shape: (12288, 50)
test_set_y shape: (1, 50)
sanity check after reshaping: [17 31 56 22 33]
Cost after iteration 0: 0.693147
Cost after iteration 100: 0.584508
Cost after iteration 200: 0.466949
Cost after iteration 300: 0.376007
Cost after iteration 400: 0.331463
Cost after iteration 500: 0.303273
Cost after iteration 600: 0.279880
Cost after iteration 700: 0.260042
Cost after iteration 800: 0.242941
Cost after iteration 900: 0.228004
Cost after iteration 1000: 0.214820
Cost after iteration 1100: 0.203078
Cost after iteration 1200: 0.192544
Cost after iteration 1300: 0.183033
Cost after iteration 1400: 0.174399
Cost after iteration 1500: 0.166521
Cost after iteration 1600: 0.159305
Cost after iteration 1700: 0.152667
Cost after iteration 1800: 0.146542
Cost after iteration 1900: 0.140872
train accuracy: 99.04306220095694 %
test accuracy: 70.0 %

learning rate is: 0.01
Cost after iteration 0: 0.693147
Cost after iteration 100: 0.823921
Cost after iteration 200: 0.418944
Cost after iteration 300: 0.617350
Cost after iteration 400: 0.522116
Cost after iteration 500: 0.387709
Cost after iteration 600: 0.236254
Cost after iteration 700: 0.154222
Cost after iteration 800: 0.135328
Cost after iteration 900: 0.124971
Cost after iteration 1000: 0.116478
Cost after iteration 1100: 0.109193
Cost after iteration 1200: 0.102804
Cost after iteration 1300: 0.097130
Cost after iteration 1400: 0.092043
train accuracy: 99.52153110047847 %
test accuracy: 68.0 %

-------------------------------------------------------

learning rate is: 0.001
Cost after iteration 0: 0.693147
Cost after iteration 100: 0.591289
Cost after iteration 200: 0.555796
Cost after iteration 300: 0.528977
Cost after iteration 400: 0.506881
Cost after iteration 500: 0.487880
Cost after iteration 600: 0.471108
Cost after iteration 700: 0.456046
Cost after iteration 800: 0.442350
Cost after iteration 900: 0.429782
Cost after iteration 1000: 0.418164
Cost after iteration 1100: 0.407362
Cost after iteration 1200: 0.397269
Cost after iteration 1300: 0.387802
Cost after iteration 1400: 0.378888
train accuracy: 88.99521531100478 %
test accuracy: 64.0 %

-------------------------------------------------------

learning rate is: 0.0001
Cost after iteration 0: 0.693147
Cost after iteration 100: 0.643677
Cost after iteration 200: 0.635737
Cost after iteration 300: 0.628572
Cost after iteration 400: 0.622040
Cost after iteration 500: 0.616029
Cost after iteration 600: 0.610455
Cost after iteration 700: 0.605248
Cost after iteration 800: 0.600354
Cost after iteration 900: 0.595729
Cost after iteration 1000: 0.591339
Cost after iteration 1100: 0.587153
Cost after iteration 1200: 0.583149
Cost after iteration 1300: 0.579307
Cost after iteration 1400: 0.575611
train accuracy: 68.42105263157895 %
test accuracy: 36.0 %

-------------------------------------------------------