使用TensorFlow Function构建ResNet

原理

Residual Network的基本原理就是跳跃传播，和传统的CNN网络（作为Residual Network的mainly road），Residaul 添加了新的传播通道（shortcut），具体可以参看下面的图片：

• 中间加入BN层提高速度（As you want）
• shortcut具体跳跃几个层由自己决定，一般总的层数越多，跳跃的也越多。
• shortcut份两种，一种是$X$经过这几层之后尺寸不变，可以直接相加，另一种是$X$经过几次CN层尺寸发生变化（如前两张图），$X$需要经过CN层变换之后相加（第三张图）。
• 我们将跳跃的几个层封装起来，如果输入和输出尺寸相等（也就是前面的尺寸不变），我们称为$IdentityBlock$，如果尺寸变化则称为$ConvolutionBlock$.

Identity Block

# UNQ_C1
# GRADED FUNCTION: identity_block

def identity_block(X, f, filters, training=True, initializer=random_uniform):
    """
    Implementation of the identity 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
    training -- True: Behave in training mode
                False: Behave in inference mode
    initializer -- to set up the initial weights of a layer. Equals to random uniform initializer
    
    Returns:
    X -- output of the identity block, tensor of shape (m, n_H, n_W, n_C)
    """
    
    # 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
    
    # First component of main path
    X = Conv2D(filters = F1, kernel_size = 1, strides = (1,1), padding = 'valid', kernel_initializer = initializer(seed=0))(X)
    X = BatchNormalization(axis = 3)(X, training = training) # Default axis
    X = Activation('relu')(X)
    
    ### START CODE HERE
    ## Second component of main path (≈3 lines)
    X = Conv2D(filters=F2,kernel_size=f,strides=(1,1),padding='same',kernel_initializer=initializer(seed=0))(X)
    X = BatchNormalization(axis=3)(X,training=training)
    X = Activation('relu')(X)

    ## Third component of main path (≈2 lines)
    X = Conv2D(filters=F3,kernel_size=1,strides=(1,1),padding='valid',kernel_initializer=initializer(seed=0))(X)
    X = BatchNormalization(axis=3)(X,training=training)
    
    ## Final step: Add shortcut value to main path, and pass it through a RELU activation (≈2 lines)
    X = Add()([X,X_shortcut])
    X = Activation('relu')(X)
    ### END CODE HERE

    return X

Convolutional Block

# UNQ_C2
# GRADED FUNCTION: convolutional_block

def convolutional_block(X, f, filters, s = 2, training=True, initializer=glorot_uniform):
    """
    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
    s -- Integer, specifying the stride to be used
    training -- True: Behave in training mode
                False: Behave in inference mode
    initializer -- to set up the initial weights of a layer. Equals to Glorot uniform initializer, 
                   also called Xavier uniform initializer.
    
    Returns:
    X -- output of the convolutional block, tensor of shape (n_H, n_W, n_C)
    """
    
    # Retrieve Filters
    F1, F2, F3 = filters
    
    # Save the input value
    X_shortcut = X


    ##### MAIN PATH #####
    
    # First component of main path glorot_uniform(seed=0)
    X = Conv2D(filters = F1, kernel_size = 1, strides = (s, s), padding='valid', kernel_initializer = initializer(seed=0))(X)
    X = BatchNormalization(axis = 3)(X, training=training)
    X = Activation('relu')(X)

    ### START CODE HERE
    
    ## Second component of main path (≈3 lines)
    X = Conv2D(filters=F2,kernel_size=f,strides=(1,1),padding='same',kernel_initializer=initializer(seed=0))(X)
    X = BatchNormalization(axis=3)(X,training=training)
    X = Activation('relu')(X)

    ## Third component of main path (≈2 lines)
    X = Conv2D(filters=F3,kernel_size=1,strides=(1,1),padding='valid',kernel_initializer=initializer(seed=0))(X)
    X = BatchNormalization(axis=3)(X,training=training)
    
    ##### SHORTCUT PATH ##### (≈2 lines)
    X_shortcut = Conv2D(filters=F3,kernel_size=1,strides=(s,s),padding='valid',kernel_initializer=initializer(seed=0))(X_shortcut)
    X_shortcut = BatchNormalization(axis=3)(X_shortcut,training=training)
    
    ### END CODE HERE

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

ResNet(50 layers)

# UNQ_C3
# GRADED FUNCTION: ResNet50

def ResNet50(input_shape = (64, 64, 3), classes = 6):
    """
    Stage-wise implementation of the architecture of the popular ResNet50:
    CONV2D -> BATCHNORM -> RELU -> MAXPOOL -> CONVBLOCK -> IDBLOCK*2 -> CONVBLOCK -> IDBLOCK*3
    -> CONVBLOCK -> IDBLOCK*5 -> CONVBLOCK -> IDBLOCK*2 -> AVGPOOL -> FLATTEN -> DENSE 

    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_shape
    X_input = Input(input_shape)

    
    # Zero-Padding
    X = ZeroPadding2D((3, 3))(X_input)
    
    # Stage 1
    X = Conv2D(64, (7, 7), strides = (2, 2), kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis = 3)(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], s = 1)
    X = identity_block(X, 3, [64, 64, 256])
    X = identity_block(X, 3, [64, 64, 256])

    ### START CODE HERE
    
    ## Stage 3 (≈4 lines)
    X = convolutional_block(X,f=3,s=2,filters=[128,128,512])
    X = identity_block(X,3,[128,128,512])
    X = identity_block(X,3,[128,128,512])
    X = identity_block(X,3,[128,128,512])
    
    ## Stage 4 (≈6 lines)
    X = convolutional_block(X,f=3,s=2,filters=[256,256,1024])
    X = identity_block(X,3,[256,256,1024])
    X = identity_block(X,3,[256,256,1024])
    X = identity_block(X,3,[256,256,1024])
    X = identity_block(X,3,[256,256,1024])
    X = identity_block(X,3,[256,256,1024])

    ## Stage 5 (≈3 lines)
    X = convolutional_block(X,f=3,s=2,filters=[512,512,2048])
    X = identity_block(X,3,[512,512,2048])
    X = identity_block(X,3,[512,512,2048])

    ## AVGPOOL (≈1 line). Use "X = AveragePooling2D(...)(X)"
    X = AveragePooling2D(pool_size=(2,2))(X)
    
    ### END CODE HERE

    # output layer
    X = Flatten()(X)
    X = Dense(classes, activation='softmax', kernel_initializer = glorot_uniform(seed=0))(X)
    
    
    # Create model
    model = Model(inputs = X_input, outputs = X)

    return model
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(X_train, Y_train, epochs = 10, batch_size = 32)
preds = model.evaluate(X_test, Y_test)
print ("Loss = " + str(preds[0]))
print ("Test Accuracy = " + str(preds[1]))