吴恩达深度学习第四课第二周（2）

本次的完整代码已上传至github：https://github.com/CrazyKKK/course4_week2-2

对于其中一些不懂得函数方法，我已加上了注释。

import numpy as np
from keras import layers
from keras.layers import Input, Add, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D, GlobalMaxPooling2D
from keras.models import Model, load_model
from keras.preprocessing import image
from keras.utils import layer_utils
from keras.utils.data_utils import get_file
from keras.applications.imagenet_utils import preprocess_input
import pydot
from IPython.display import SVG
from keras.utils.vis_utils import model_to_dot
from keras.utils import plot_model
from resnets_utils import *
from keras.initializers import glorot_uniform
import scipy.misc
from matplotlib.pyplot import imshow

import keras.backend as K
K.set_image_data_format('channels_last')
K.set_learning_phase(1) #1为训练模式，0为工作模式

K.clear_session()
"""
Implement the ResNet identity block:
First component of main path: 
- The first CONV2D has F1 filters of shape (1,1) and a stride of (1,1). Its padding is “valid” and its name should be conv_name_base + '2a'. Use 0 as the seed for the random initialization. 
- The first BatchNorm is normalizing the channels axis. Its name should be bn_name_base + '2a'. 
- Then apply the ReLU activation function. This has no name and no hyperparameters.

Second component of main path: 
- The second CONV2D has F2 filters of shape (f,f) and a stride of (1,1). Its padding is “same” and its name should be conv_name_base + '2b'. Use 0 as the seed for the random initialization. 
- The second BatchNorm is normalizing the channels axis. Its name should be bn_name_base + '2b'. 
- Then apply the ReLU activation function. This has no name and no hyperparameters.

Third component of main path: 
- The third CONV2D has F3 filters of shape (1,1) and a stride of (1,1). Its padding is “valid” and its name should be conv_name_base + '2c'. Use 0 as the seed for the random initialization. 
- The third BatchNorm is normalizing the channels axis. Its name should be bn_name_base + '2c'. Note that there is no ReLU activation function in this component.

Final step: 
- The shortcut and the input are added together. 
- Then apply the ReLU activation function. This has no name and no hyperparameters.
"""
# GRADED FUNCTION: identity_block
def identity_block(X, f, filters, stage, block):

    """
    Implementation of the identity block as defined in Figure 3

    Arguments:
    X -- input tensor of shape (m, n_H_prev, n_W_prev, n_C_prev)
    f -- integer, specifying the shape of the middle CONV's window for the main path
    filters -- python list of integers, defining the number of filters in the CONV layers of the main path
    stage -- integer, used to name the layers, depending on their position in the network
    block -- string/character, used to name the layers, depending on their position in the network

    Returns:
    X -- output of the identity block, tensor of shape (n_H, n_W, n_C)
    """
    # defining name basis
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    # Retrieve Filters
    F1,F2,F3 = filters


    # Save the input value. You'll need this later to add back to the main path.
    X_shortcut = X

    #Glorot均匀分布初始化方法，又成Xavier均匀初始化，参数从[-limit, limit]的均匀分布产生，其中limit为sqrt(6 / (fan_in + fan_out))。
    # fan_in为权值张量的输入单元数，fan_out是权重张量的输出单元数。
    # First component of main path
    X = Conv2D(filters = F1, kernel_size = (1, 1), strides = (1,1), padding = 'valid', name = conv_name_base + '2a', kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3,name=bn_name_base + '2a')(X)
    X = Activation('relu')(X)

    # Second component of main path
    X = Conv2D(filters=F2,kernel_size=(f,f),strides=(1,1),padding='same',name=conv_name_base+'2b',kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3,name=bn_name_base + '2b')(X)
    X = Activation('relu')(X)

    # Third component of main path
    X = Conv2D(filters=F3,kernel_size=(1,1),strides=(1,1),padding='valid',name=conv_name_base+'2c',kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3,name=bn_name_base + '2c')(X)

    # Final step: Add shortcut value to main path, and pass it through a RELU activation
    X = Add()([X,X_shortcut])
    X = Activation('relu')(X)

    return X

tf.reset_default_graph()
"""
with tf.Session() as test:
    np.random.seed(1)
    A_prev = tf.placeholder("float", [3, 4, 4, 6])
    X = np.random.randn(3, 4, 4, 6)
    A = identity_block(A_prev, f = 2, filters = [2, 4, 6], stage = 1, block = 'a')
    test.run(tf.global_variables_initializer())
    out = test.run([A], feed_dict={A_prev: X, K.learning_phase(): 0})
    print("out = " + str(out[0][1][1][0]))
"""

"""
The details of the convolutional block are as follows.

First component of main path: 
- The first CONV2D has F1 filters of shape (1,1) and a stride of (s,s). Its padding is “valid” and its name should be conv_name_base + '2a'. 
- The first BatchNorm is normalizing the channels axis. Its name should be bn_name_base + '2a'. 
- Then apply the ReLU activation function. This has no name and no hyperparameters.

Second component of main path: 
- The second CONV2D has F2 filters of (f,f) and a stride of (1,1). Its padding is “same” and it’s name should be conv_name_base + '2b'. 
- The second BatchNorm is normalizing the channels axis. Its name should be bn_name_base + '2b'. 
- Then apply the ReLU activation function. This has no name and no hyperparameters.

Third component of main path: 
- The third CONV2D has F3 filters of (1,1) and a stride of (1,1). Its padding is “valid” and it’s name should be conv_name_base + '2c'. 
- The third BatchNorm is normalizing the channels axis. Its name should be bn_name_base + '2c'. Note that there is no ReLU activation function in this component.

Shortcut path: 
- The CONV2D has F3 filters of shape (1,1) and a stride of (s,s). Its padding is “valid” and its name should be conv_name_base + '1'. 
- The BatchNorm is normalizing the channels axis. Its name should be bn_name_base + '1'.

Final step: 
- The shortcut and the main path values are added together. 
- Then apply the ReLU activation function. This has no name and no hyperparameters.
"""

# GRADED FUNCTION: convolutional_block

def convolutional_block(X ,f, filters ,stage, block,s =2):
    """
    Implementation of the convolutional block as defined in Figure 4

    Arguments:
    X -- input tensor of shape (m, n_H_prev, n_W_prev, n_C_prev)
    f -- integer, specifying the shape of the middle CONV's window for the main path
    filters -- python list of integers, defining the number of filters in the CONV layers of the main path
    stage -- integer, used to name the layers, depending on their position in the network
    block -- string/character, used to name the layers, depending on their position in the network
    s -- Integer, specifying the stride to be used

    Returns:
    X -- output of the convolutional block, tensor of shape (n_H, n_W, n_C)
    """
    # defining name basis
    conv_name_base = 'res' + str(stage) + '_branch'
    bn_name_base = 'bn' + str(stage) + '_branch'

    # Retrieve Filters
    F1, F2, F3 = filters

    # Save the input value
    X_shortcut = X

    ##### MAIN PATH #####
    # First component of main path
    X = Conv2D(F1, (1, 1), strides=(s, s), name=conv_name_base + '2a' ,kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3,name=bn_name_base + '2a')(X)
    X = Activation('relu')(X)

    # Second component of main path (≈3 lines)
    X = Conv2D(F2,(f,f),strides=(1,1),name=conv_name_base + '2b',padding='same',kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3,name=bn_name_base + '2b')(X)
    X = Activation('relu')(X)

    # Third component of main path
    X = Conv2D(F3,(1,1),strides=(1,1),name=conv_name_base + '2c',kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3,name=bn_name_base + '2c')(X)

    ##### SHORTCUT PATH ####
    X_shortcut = Conv2D(F3,(1,1),strides=(s,s),name=conv_name_base + '1',kernel_initializer=glorot_uniform(seed=0))(X_shortcut)
    X_shortcut = BatchNormalization(axis=3,name=bn_name_base + '1')(X_shortcut)

    # Final step: Add shortcut value to main path, and pass it through a RELU activation
    X = Add()([X, X_shortcut])
    X = Activation('relu')(X)

    return X
'''
tf.reset_default_graph()

with tf.Session() as test:
    np.random.seed(1)
    A_prev = tf.placeholder("float", [3, 4, 4, 6])
    X = np.random.randn(3, 4, 4, 6)
    A = convolutional_block(A_prev, f = 2, filters = [2, 4, 6], stage = 1, block = 'a')
    test.run(tf.global_variables_initializer())
    out = test.run([A], feed_dict={A_prev: X, K.learning_phase(): 0})
    print("out = " + str(out[0][1][1][0]))
'''


#Building your first ResNet model (50 layers)

"""
The details of this ResNet-50 model are: 
- Zero-padding pads the input with a pad of (3,3) 
- Stage 1: 
- The 2D Convolution has 64 filters of shape (7,7) and uses a stride of (2,2). Its name is “conv1”. 
- BatchNorm is applied to the channels axis of the input. 
- MaxPooling uses a (3,3) window and a (2,2) stride. 
- Stage 2: 
- The convolutional block uses three set of filters of size [64,64,256], “f” is 3, “s” is 1 and the block is “a”. 
- The 2 identity blocks use three set of filters of size [64,64,256], “f” is 3 and the blocks are “b” and “c”. 
- Stage 3: 
- The convolutional block uses three set of filters of size [128,128,512], “f” is 3, “s” is 2 and the block is “a”. 
- The 3 identity blocks use three set of filters of size [128,128,512], “f” is 3 and the blocks are “b”, “c” and “d”. 
- Stage 4: 
- The convolutional block uses three set of filters of size [256, 256, 1024], “f” is 3, “s” is 2 and the block is “a”. 
- The 5 identity blocks use three set of filters of size [256, 256, 1024], “f” is 3 and the blocks are “b”, “c”, “d”, “e” and “f”. 
- Stage 5: 
- The convolutional block uses three set of filters of size [512, 512, 2048], “f” is 3, “s” is 2 and the block is “a”. 
- The 2 identity blocks use three set of filters of size [512, 512, 2048], “f” is 3 and the blocks are “b” and “c”. 
- The 2D Average Pooling uses a window of shape (2,2) and its name is “avg_pool”. 
- The flatten doesn’t have any hyperparameters or name. 
- The Fully Connected (Dense) layer reduces its input to the number of classes using a softmax activation. Its name should be 'fc' + str(classes).
"""



# GRADED FUNCTION: ResNet50

def ResNet50(input_shape = (64,64,3),classes = 6):
    """
       Implementation of the popular ResNet50 the following architecture:
       CONV2D -> BATCHNORM -> RELU -> MAXPOOL -> CONVBLOCK -> IDBLOCK*2 -> CONVBLOCK -> IDBLOCK*3
       -> CONVBLOCK -> IDBLOCK*5 -> CONVBLOCK -> IDBLOCK*2 -> AVGPOOL -> TOPLAYER

       Arguments:
       input_shape -- shape of the images of the dataset
       classes -- integer, number of classes

       Returns:
       model -- a Model() instance in Keras
       """
    # Define the input as a tensor with shape input_shap
    # Define the input as a tensor with shape input_shape
    X_input = Input(input_shape)

    # Zero-Padding
    X = ZeroPadding2D((3, 3))(X_input)

    # Stage 1
    X = Conv2D(64, (7, 7), strides=(2, 2), name='conv1', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name='bn_conv1')(X)
    X = Activation('relu')(X)
    X = MaxPooling2D((3, 3), strides=(2, 2))(X)

    # Stage 2
    X = convolutional_block(X, f=3, filters=[64, 64, 256], stage=2, block='a', s=1)
    X = identity_block(X, 3, [64, 64, 256], stage=2, block='b')
    X = identity_block(X, 3, [64, 64, 256], stage=2, block='c')

    ### START CODE HERE ###

    # Stage 3 (≈4 lines)
    X = convolutional_block(X, f=3, filters=[128, 128, 512], stage=3, block='a', s=2)
    X = identity_block(X, 3, [128, 128, 512], stage=3, block='b')
    X = identity_block(X, 3, [128, 128, 512], stage=3, block='c')
    X = identity_block(X, 3, [128, 128, 512], stage=3, block='d')

    # Stage 4 (≈6 lines)
    X = convolutional_block(X, f=3, filters=[256, 256, 1024], stage=4, block='a', s=2)
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='b')
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='c')
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='d')
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='e')
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='f')

    # Stage 5 (≈3 lines)
    X = convolutional_block(X, f=3, filters=[512, 512, 2048], stage=5, block='a', s=2)
    X = identity_block(X, 3, [512, 512, 2048], stage=5, block='b')
    X = identity_block(X, 3, [512, 512, 2048], stage=5, block='c')

    # AVGPOOL (≈1 line). Use "X = AveragePooling2D(...)(X)"
    X = AveragePooling2D((2, 2), name='avg_pool')(X)

    ### END CODE HERE ###

    # output layer
    X = Flatten()(X)
    X = Dense(classes, activation='softmax', name='fc' + str(classes), kernel_initializer=glorot_uniform(seed=0))(X)

    # Create model
    model = Model(inputs=X_input, outputs=X, name='ResNet50')

    return model

model = ResNet50(input_shape = (64, 64, 3), classes = 6)

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset()

# Normalize image vectors
X_train = X_train_orig/255.
X_test = X_test_orig/255.

# Convert training and test labels to one hot matrices
Y_train = convert_to_one_hot(Y_train_orig, 6).T
Y_test = convert_to_one_hot(Y_test_orig, 6).T

"""
print ("number of training examples = " + str(X_train.shape[0]))
print ("number of test examples = " + str(X_test.shape[0]))
print ("X_train shape: " + str(X_train.shape))
print ("Y_train shape: " + str(Y_train.shape))
print ("X_test shape: " + str(X_test.shape))
print ("Y_test shape: " + str(Y_test.shape))
"""


model.fit(X_train, Y_train, epochs = 5, batch_size = 32)
preds = model.evaluate(X_test, Y_test)
print ("MyLoss = " + str(preds[0]))
print ("MyTest Accuracy = " + str(preds[1]))
"""
model = load_model('ResNet50.h5')
preds = model.evaluate(X_test, Y_test)
print ("NgLoss = " + str(preds[0]))
print ("NgTest Accuracy = " + str(preds[1]))
"""
img_path = 'images/my_image.jpg'
img = image.load_img(img_path, target_size=(64, 64))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
print('Input image shape:', x.shape)
my_image = scipy.misc.imread(img_path)
imshow(my_image)
print("class prediction vector [p(0), p(1), p(2), p(3), p(4), p(5)] = ")
print(model.predict(x))