Residual Network - python01

Residual Networks

Andrew Ng deeplearning courese-4:Convolutional Neural Network

• Convolutional Neural Networks: Step by Step
• Convolutional Neural Networks: Application
• Residual Networks
• Autonomous driving - Car detection YOLO
• Face Recognition for the Happy House
• Art: Neural Style Transfer

Github地址

• Andrew Ng's coursera_deeplearning.ai
• ranjiewwen/deeplearning.ai

Residual Networks

Welcome to the second assignment of this week! You will learn how to build very deep convolutional networks, using Residual Networks (ResNets). In theory, very deep networks can represent very complex functions; but in practice, they are hard to train. Residual Networks, introduced by He et al., allow you to train much deeper networks than were previously practically feasible.

In this assignment, you will:

• Implement the basic building blocks of ResNets.
• Put together these building blocks to implement and train a state-of-the-art neural network for image classification.

This assignment will be done in Keras.

Before jumping into the problem, let's run the cell below to load the required packages.

<span style="color:#000000"><code><span style="color:#0000ff">import</span> numpy <span style="color:#0000ff">as</span> np
<span style="color:#0000ff">from</span> keras <span style="color:#0000ff">import</span> layers
<span style="color:#0000ff">from</span> keras.layers <span style="color:#0000ff">import</span> Input, Add, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D, GlobalMaxPooling2D
<span style="color:#0000ff">from</span> keras.models <span style="color:#0000ff">import</span> Model, load_model
<span style="color:#0000ff">from</span> keras.preprocessing <span style="color:#0000ff">import</span> image
<span style="color:#0000ff">from</span> keras.utils <span style="color:#0000ff">import</span> layer_utils
<span style="color:#0000ff">from</span> keras.utils.data_utils <span style="color:#0000ff">import</span> get_file
<span style="color:#0000ff">from</span> keras.applications.imagenet_utils <span style="color:#0000ff">import</span> preprocess_input
<span style="color:#0000ff">import</span> pydot
<span style="color:#0000ff">from</span> IPython.display <span style="color:#0000ff">import</span> SVG
<span style="color:#0000ff">from</span> keras.utils.vis_utils <span style="color:#0000ff">import</span> model_to_dot
<span style="color:#0000ff">from</span> keras.utils <span style="color:#0000ff">import</span> plot_model
<span style="color:#0000ff">from</span> resnets_utils <span style="color:#0000ff">import</span> *
<span style="color:#0000ff">from</span> keras.initializers <span style="color:#0000ff">import</span> glorot_uniform
<span style="color:#0000ff">import</span> scipy.misc
<span style="color:#0000ff">from</span> matplotlib.pyplot <span style="color:#0000ff">import</span> imshow
%matplotlib inline

<span style="color:#0000ff">import</span> keras.backend <span style="color:#0000ff">as</span> K
K.set_image_data_format(<span style="color:#a31515">'channels_last'</span>)
K.set_learning_phase(1)</code></span>

Using TensorFlow backend.

1 - The problem of very deep neural networks

Last week, you built your first convolutional neural network. In recent years, neural networks have become deeper, with state-of-the-art networks going from just a few layers (e.g., AlexNet) to over a hundred layers.

The main benefit of a very deep network is that it can represent very complex functions. It can also learn features at many different levels of abstraction, from edges (at the lower layers) to very complex features (at the deeper layers). However, using a deeper network doesn't always help. A huge barrier to training them is vanishing gradients: very deep networks often have a gradient signal that goes to zero quickly, thus making gradient descent unbearably slow. More specifically, during gradient descent, as you backprop from the final layer back to the first layer, you are multiplying by the weight matrix on each step, and thus the gradient can decrease exponentially quickly to zero (or, in rare cases, grow exponentially quickly and "explode" to take very large values).

During training, you might therefore see the magnitude (or norm) of the gradient for the earlier layers descrease to zero very rapidly as training proceeds:

**Figure 1** : **Vanishing gradient** 
The speed of learning decreases very rapidly for the early layers as the network trains

You are now going to solve this problem by building a Residual Network!

2 - Building a Residual Network

In ResNets, a "shortcut" or a "skip connection" allows the gradient to be directly backpropagated to earlier layers:

**Figure 2** : A ResNet block showing a **skip-connection** 

The image on the left shows the "main path" through the network. The image on the right adds a shortcut to the main path. By stacking these ResNet blocks on top of each other, you can form a very deep network.

We also saw in lecture that having ResNet blocks with the shortcut also makes it very easy for one of the blocks to learn an identity function. This means that you can stack on additional ResNet blocks with little risk of harming training set performance. (There is also some evidence that the ease of learning an identity function--even more than skip connections helping with vanishing gradients--accounts for ResNets' remarkable performance.)

Two main types of blocks are used in a ResNet, depending mainly on whether the input/output dimensions are same or different. You are going to implement both of them.

2.1 - The identity block

The identity block is the standard block used in ResNets, and corresponds to the case where the input activation (say a[l]a[l]) has the same dimension as the output activation (say a[l+2]a[l+2]). To flesh out the different steps of what happens in a ResNet's identity block, here is an alternative diagram showing the individual steps:

Figure 3 : Identity block. Skip connection "skips over" 2 layers.

 

The upper path is the "shortcut path." The lower path is the "main path." In this diagram, we have also made explicit the CONV2D and ReLU steps in each layer. To speed up training we have also added a BatchNorm step. Don't worry about this being complicated to implement--you'll see that BatchNorm is just one line of code in Keras!

In this exercise, you'll actually implement a slightly more powerful version of this identity block, in which the skip connection "skips over" 3 hidden layers rather than 2 layers. It looks like this:

Figure 4 : Identity block. Skip connection "skips over" 3 layers.

 

Here're the individual steps.

First component of main path:

• The first CONV2D has F1F1 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 F2F2 filters of shape (f,f)(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 F3F3 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.

Exercise: Implement the ResNet identity block. We have implemented the first component of the main path. Please read over this carefully to make sure you understand what it is doing. You should implement the rest.

• To implement the Conv2D step: See reference
• To implement BatchNorm: See reference (axis: Integer, the axis that should be normalized (typically the channels axis))
• For the activation, use: Activation('relu')(X)
• To add the value passed forward by the shortcut: See reference

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code><span style="color:green"># GRADED FUNCTION: identity_block</span>

<span style="color:#0000ff">def</span> <span style="color:#a31515">identity_block</span>(X, f, filters, stage, block):
    <span style="color:#a31515">"""
    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)
    """</span>
    
    <span style="color:green"># defining name basis</span>
    conv_name_base = <span style="color:#a31515">'res'</span> + str(stage) + block + <span style="color:#a31515">'_branch'</span>
    bn_name_base = <span style="color:#a31515">'bn'</span> + str(stage) + block + <span style="color:#a31515">'_branch'</span>
    
    <span style="color:green"># Retrieve Filters</span>
    F1, F2, F3 = filters
    
    <span style="color:green"># Save the input value. You'll need this later to add back to the main path. </span>
    X_shortcut = X
    
    <span style="color:green"># First component of main path</span>
    X = Conv2D(filters = F1, kernel_size = (1, 1), strides = (1,1), padding = <span style="color:#a31515">'valid'</span>, name = conv_name_base + <span style="color:#a31515">'2a'</span>, kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + <span style="color:#a31515">'2a'</span>)(X)
    X = Activation(<span style="color:#a31515">'relu'</span>)(X)
    
    <span style="color:green">### START CODE HERE ###</span>
    
    <span style="color:green"># Second component of main path (≈3 lines)</span>
    X = Conv2D(filters = F2, kernel_size = (f, f), strides = (1,1), padding = <span style="color:#a31515">'same'</span>, name = conv_name_base + <span style="color:#a31515">'2b'</span>, kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + <span style="color:#a31515">'2b'</span>)(X)
    X = Activation(<span style="color:#a31515">'relu'</span>)(X)

    <span style="color:green"># Third component of main path (≈2 lines)</span>
    X = Conv2D(filters = F3, kernel_size = (1, 1), strides = (1,1), padding = <span style="color:#a31515">'valid'</span>, name = conv_name_base + <span style="color:#a31515">'2c'</span>, kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + <span style="color:#a31515">'2c'</span>)(X)

    <span style="color:green"># Final step: Add shortcut value to main path, and pass it through a RELU activation (≈2 lines)</span>
    X =  Add()([X_shortcut, X])  <span style="color:green"># equivalent to added = keras.layers.add([x1, x2])</span>
    X = Activation(<span style="color:#a31515">'relu'</span>)(X)
    
    <span style="color:green">### END CODE HERE ###</span>
    
    <span style="color:#0000ff">return</span> X</code></span></span></span></span></span></span></span></span></span>

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>tf.reset_default_graph()

<span style="color:#0000ff">with</span> tf.Session() <span style="color:#0000ff">as</span> test:
    np.random.seed(1)
    A_prev = tf.placeholder(<span style="color:#a31515">"float"</span>, [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 = <span style="color:#a31515">'a'</span>)
    test.run(tf.global_variables_initializer())
    out = test.run([A], feed_dict={A_prev: X, K.learning_phase(): 0})
    print(<span style="color:#a31515">"out = "</span> + str(out[0][1][1][0]))</code></span></span></span></span></span></span></span></span></span>

out = [ 0.94822985 0. 1.16101444 2.747859 0. 1.36677003]

Expected Output:

**out**

[ 0.94822985 0. 1.16101444 2.747859 0. 1.36677003]

2.2 - The convolutional block

You've implemented the ResNet identity block. Next, the ResNet "convolutional block" is the other type of block. You can use this type of block when the input and output dimensions don't match up. The difference with the identity block is that there is a CONV2D layer in the shortcut path:

Figure 4 : Convolutional block

 

The CONV2D layer in the shortcut path is used to resize the input xx to a different dimension, so that the dimensions match up in the final addition needed to add the shortcut value back to the main path. (This plays a similar role as the matrix WsWs discussed in lecture.) For example, to reduce the activation dimensions's height and width by a factor of 2, you can use a 1x1 convolution with a stride of 2. The CONV2D layer on the shortcut path does not use any non-linear activation function. Its main role is to just apply a (learned) linear function that reduces the dimension of the input, so that the dimensions match up for the later addition step.

The details of the convolutional block are as follows.

First component of main path:

• The first CONV2D has F1F1 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 F2F2 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 F3F3 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 F3F3 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.

Exercise: Implement the convolutional block. We have implemented the first component of the main path; you should implement the rest. As before, always use 0 as the seed for the random initialization, to ensure consistency with our grader.

• Conv Hint
• BatchNorm Hint (axis: Integer, the axis that should be normalized (typically the features axis))
• For the activation, use: Activation('relu')(X)
• Addition Hint

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code><span style="color:green"># GRADED FUNCTION: convolutional_block</span>

<span style="color:#0000ff">def</span> <span style="color:#a31515">convolutional_block</span>(X, f, filters, stage, block, s = 2):
    <span style="color:#a31515">"""
    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)
    """</span>
    
    <span style="color:green"># defining name basis</span>
    conv_name_base = <span style="color:#a31515">'res'</span> + str(stage) + block + <span style="color:#a31515">'_branch'</span>
    bn_name_base = <span style="color:#a31515">'bn'</span> + str(stage) + block + <span style="color:#a31515">'_branch'</span>
    
    <span style="color:green"># Retrieve Filters</span>
    F1, F2, F3 = filters
    
    <span style="color:green"># Save the input value</span>
    X_shortcut = X


    <span style="color:green">##### MAIN PATH #####</span>
    <span style="color:green"># First component of main path </span>
    X = Conv2D(F1, kernel_size=(1, 1), strides = (s,s),padding = <span style="color:#a31515">'valid'</span>, name = conv_name_base + <span style="color:#a31515">'2a'</span>, kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + <span style="color:#a31515">'2a'</span>)(X)
    X = Activation(<span style="color:#a31515">'relu'</span>)(X)
    
    <span style="color:green">### START CODE HERE ###</span>

    <span style="color:green"># Second component of main path (≈3 lines)</span>
    X = Conv2D(F2,kernel_size= (f, f), strides = (1,1),padding = <span style="color:#a31515">'same'</span>, name = conv_name_base + <span style="color:#a31515">'2b'</span>, kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + <span style="color:#a31515">'2b'</span>)(X)
    X = Activation(<span style="color:#a31515">'relu'</span>)(X)

    <span style="color:green"># Third component of main path (≈2 lines)</span>
    X = Conv2D(filters = F3, kernel_size = (1, 1), strides = (1,1), padding = <span style="color:#a31515">'valid'</span>, name = conv_name_base + <span style="color:#a31515">'2c'</span>, kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + <span style="color:#a31515">'2c'</span>)(X)

    <span style="color:green">##### SHORTCUT PATH #### (≈2 lines)</span>
    X_shortcut =  Conv2D(filters = F3, kernel_size = (1, 1), strides = (s,s), padding = <span style="color:#a31515">'valid'</span>, name = conv_name_base + <span style="color:#a31515">'1'</span>, kernel_initializer = glorot_uniform(seed=0))(X_shortcut)
    X_shortcut = BatchNormalization(axis = 3, name = bn_name_base + <span style="color:#a31515">'1'</span>)(X_shortcut)

    <span style="color:green"># Final step: Add shortcut value to main path, and pass it through a RELU activation (≈2 lines)</span>
    X =  Add()([X_shortcut, X])  <span style="color:green"># equivalent to added = keras.layers.add([x1, x2])</span>
    X = Activation(<span style="color:#a31515">'relu'</span>)(X)
    
    <span style="color:green">### END CODE HERE ###</span>
    
    <span style="color:#0000ff">return</span> X</code></span></span></span></span></span></span></span></span></span></span></span>

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>tf.reset_default_graph()

<span style="color:#0000ff">with</span> tf.Session() <span style="color:#0000ff">as</span> test:
    np.random.seed(1)
    A_prev = tf.placeholder(<span style="color:#a31515">"float"</span>, [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 = <span style="color:#a31515">'a'</span>)
    test.run(tf.global_variables_initializer())
    out = test.run([A], feed_dict={A_prev: X, K.learning_phase(): 0})
    print(<span style="color:#a31515">"out = "</span> + str(out[0][1][1][0]))</code></span></span></span></span></span></span></span></span></span></span></span>

out = [ 0.09018463 1.23489773 0.46822017 0.0367176 0. 0.65516603]

Expected Output:

**out**

[ 0.09018463 1.23489773 0.46822017 0.0367176 0. 0.65516603]

3 - Building your first ResNet model (50 layers)

You now have the necessary blocks to build a very deep ResNet. The following figure describes in detail the architecture of this neural network. "ID BLOCK" in the diagram stands for "Identity block," and "ID BLOCK x3" means you should stack 3 identity blocks together.

Figure 5 : ResNet-50 model

 

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).

Exercise: Implement the ResNet with 50 layers described in the figure above. We have implemented Stages 1 and 2. Please implement the rest. (The syntax for implementing Stages 3-5 should be quite similar to that of Stage 2.) Make sure you follow the naming convention in the text above.

You'll need to use this function:

• Average pooling see reference

Here're some other functions we used in the code below:

• Conv2D: See reference
• BatchNorm: See reference (axis: Integer, the axis that should be normalized (typically the features axis))
• Zero padding: See reference
• Max pooling: See reference
• Fully conected layer: See reference
• Addition: See reference

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code><span style="color:green"># GRADED FUNCTION: ResNet50</span>

<span style="color:#0000ff">def</span> <span style="color:#a31515">ResNet50</span>(input_shape = (64, 64, 3), classes = 6):
    <span style="color:#a31515">"""
    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
    """</span>
    
    <span style="color:green"># Define the input as a tensor with shape input_shape</span>
    X_input = Input(input_shape)

    
    <span style="color:green"># Zero-Padding</span>
    X = ZeroPadding2D((3, 3))(X_input)
    
    <span style="color:green"># Stage 1</span>
    X = Conv2D(64, (7, 7), strides = (2, 2), name = <span style="color:#a31515">'conv1'</span>, kernel_initializer = glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis = 3, name = <span style="color:#a31515">'bn_conv1'</span>)(X)
    X = Activation(<span style="color:#a31515">'relu'</span>)(X)
    X = MaxPooling2D((3, 3), strides=(2, 2))(X)

    <span style="color:green"># Stage 2</span>
    X = convolutional_block(X, f = 3, filters = [64, 64, 256], stage = 2, block=<span style="color:#a31515">'a'</span>, s = 1)
    X = identity_block(X, 3, [64, 64, 256], stage=2, block=<span style="color:#a31515">'b'</span>)
    X = identity_block(X, 3, [64, 64, 256], stage=2, block=<span style="color:#a31515">'c'</span>)

    <span style="color:green">### START CODE HERE ###</span>

    <span style="color:green"># Stage 3 (≈4 lines)</span>
    X = convolutional_block(X, f = 3, filters = [128,128,512], stage = 3, block=<span style="color:#a31515">'a'</span>, s = 2)
    X = identity_block(X, 3, [128,128,512], stage=3, block=<span style="color:#a31515">'b'</span>)
    X = identity_block(X, 3, [128,128,512], stage=3, block=<span style="color:#a31515">'c'</span>)
    X = identity_block(X, 3, [128,128,512], stage=3, block=<span style="color:#a31515">'d'</span>)

    <span style="color:green"># Stage 4 (≈6 lines)</span>
    X = convolutional_block(X, f = 3, filters = [256, 256, 1024], stage = 4, block=<span style="color:#a31515">'a'</span>, s = 2)
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block=<span style="color:#a31515">'b'</span>)
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block=<span style="color:#a31515">'c'</span>)
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block=<span style="color:#a31515">'d'</span>)
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block=<span style="color:#a31515">'e'</span>)
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block=<span style="color:#a31515">'f'</span>)

    <span style="color:green"># Stage 5 (≈3 lines)</span>
    X = convolutional_block(X, f = 3, filters = [512, 512, 2048], stage = 5, block=<span style="color:#a31515">'a'</span>, s = 2)
    X = identity_block(X, 3, [512, 512, 2048], stage=5, block=<span style="color:#a31515">'b'</span>)
    X = identity_block(X, 3, [512, 512, 2048], stage=5, block=<span style="color:#a31515">'c'</span>)

    <span style="color:green"># AVGPOOL (≈1 line). Use "X = AveragePooling2D(...)(X)"</span>
    X = AveragePooling2D(pool_size=(2, 2), strides=<span style="color:#0000ff">None</span>, padding=<span style="color:#a31515">'valid'</span>,name=<span style="color:#a31515">'avg_pool'</span> )(X)
    
    <span style="color:green">### END CODE HERE ###</span>

    <span style="color:green"># output layer</span>
    X = Flatten()(X)
    X = Dense(classes, activation=<span style="color:#a31515">'softmax'</span>, name=<span style="color:#a31515">'fc'</span> + str(classes), kernel_initializer = glorot_uniform(seed=0))(X)
    
    
    <span style="color:green"># Create model</span>
    model = Model(inputs = X_input, outputs = X, name=<span style="color:#a31515">'ResNet50'</span>)

    <span style="color:#0000ff">return</span> model</code></span></span></span></span></span></span></span></span></span></span></span></span></span>

Run the following code to build the model's graph. If your implementation is not correct you will know it by checking your accuracy when running model.fit(...) below.

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>model = ResNet50(input_shape = (64, 64, 3), classes = 6)</code></span></span></span></span></span></span></span></span></span></span></span></span></span>

As seen in the Keras Tutorial Notebook, prior training a model, you need to configure the learning process by compiling the model.

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>model.compile(optimizer=<span style="color:#a31515">'adam'</span>, loss=<span style="color:#a31515">'categorical_crossentropy'</span>, metrics=[<span style="color:#a31515">'accuracy'</span>])</code></span></span></span></span></span></span></span></span></span></span></span></span></span>

The model is now ready to be trained. The only thing you need is a dataset.

Let's load the SIGNS Dataset.

Figure 6 : SIGNS dataset

 

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset()

<span style="color:green"># Normalize image vectors</span>
X_train = X_train_orig/255.
X_test = X_test_orig/255.

<span style="color:green"># Convert training and test labels to one hot matrices</span>
Y_train = convert_to_one_hot(Y_train_orig, 6).T
Y_test = convert_to_one_hot(Y_test_orig, 6).T

<span style="color:#0000ff">print</span> (<span style="color:#a31515">"number of training examples = "</span> + str(X_train.shape[0]))
<span style="color:#0000ff">print</span> (<span style="color:#a31515">"number of test examples = "</span> + str(X_test.shape[0]))
<span style="color:#0000ff">print</span> (<span style="color:#a31515">"X_train shape: "</span> + str(X_train.shape))
<span style="color:#0000ff">print</span> (<span style="color:#a31515">"Y_train shape: "</span> + str(Y_train.shape))
<span style="color:#0000ff">print</span> (<span style="color:#a31515">"X_test shape: "</span> + str(X_test.shape))
<span style="color:#0000ff">print</span> (<span style="color:#a31515">"Y_test shape: "</span> + str(Y_test.shape))</code></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span>

number of training examples = 1080 number of test examples = 120 X_train shape: (1080, 64, 64, 3) Y_train shape: (1080, 6) X_test shape: (120, 64, 64, 3) Y_test shape: (120, 6)

Run the following cell to train your model on 2 epochs with a batch size of 32. On a CPU it should take you around 5min per epoch.

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>model.fit(X_train, Y_train, epochs = 2, batch_size = 32)</code></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span>

Epoch 1/2 1080/1080 [==============================] - 276s - loss: 3.1881 - acc: 0.2528 Epoch 2/2 1080/1080 [==============================] - 266s - loss: 2.7411 - acc: 0.2806 <keras.callbacks.History at 0x7f95e117c5c0>

Expected Output:

** Epoch 1/2**	loss: between 1 and 5, acc: between 0.2 and 0.5, although your results can be different from ours.
** Epoch 2/2**	loss: between 1 and 5, acc: between 0.2 and 0.5, you should see your loss decreasing and the accuracy increasing.

Let's see how this model (trained on only two epochs) performs on the test set.

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>preds = model.evaluate(X_test, Y_test)
<span style="color:#0000ff">print</span> (<span style="color:#a31515">"Loss = "</span> + str(preds[0]))
<span style="color:#0000ff">print</span> (<span style="color:#a31515">"Test Accuracy = "</span> + str(preds[1]))</code></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span>

120/120 [==============================] - 10s Loss = 2.16483095487 Test Accuracy = 0.166666668653

Expected Output:

**Test Accuracy**

between 0.16 and 0.25

For the purpose of this assignment, we've asked you to train the model only for two epochs. You can see that it achieves poor performances. Please go ahead and submit your assignment; to check correctness, the online grader will run your code only for a small number of epochs as well.

After you have finished this official (graded) part of this assignment, you can also optionally train the ResNet for more iterations, if you want. We get a lot better performance when we train for ~20 epochs, but this will take more than an hour when training on a CPU.

Using a GPU, we've trained our own ResNet50 model's weights on the SIGNS dataset. You can load and run our trained model on the test set in the cells below. It may take ≈1min to load the model.

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>model = load_model(<span style="color:#a31515">'ResNet50.h5'</span>) </code></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span>

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>preds = model.evaluate(X_test, Y_test)
<span style="color:#0000ff">print</span> (<span style="color:#a31515">"Loss = "</span> + str(preds[0]))
<span style="color:#0000ff">print</span> (<span style="color:#a31515">"Test Accuracy = "</span> + str(preds[1]))</code></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span>

120/120 [==============================] - 10s Loss = 0.530178320408 Test Accuracy = 0.866666662693

ResNet50 is a powerful model for image classification when it is trained for an adequate number of iterations. We hope you can use what you've learnt and apply it to your own classification problem to perform state-of-the-art accuracy.

Congratulations on finishing this assignment! You've now implemented a state-of-the-art image classification system!

4 - Test on your own image (Optional/Ungraded)

If you wish, you can also take a picture of your own hand and see the output of the model. To do this:
1. Click on "File" in the upper bar of this notebook, then click "Open" to go on your Coursera Hub.
2. Add your image to this Jupyter Notebook's directory, in the "images" folder
3. Write your image's name in the following code
4. Run the code and check if the algorithm is right!

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>img_path = <span style="color:#a31515">'images/my_image.jpg'</span>
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(<span style="color:#a31515">'Input image shape:'</span>, x.shape)
my_image = scipy.misc.imread(img_path)
imshow(my_image)
print(<span style="color:#a31515">"class prediction vector [p(0), p(1), p(2), p(3), p(4), p(5)] = "</span>)
print(model.predict(x))</code></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span>

Input image shape: (1, 64, 64, 3) class prediction vector [p(0), p(1), p(2), p(3), p(4), p(5)] = [[ 1. 0. 0. 0. 0. 0.]]

You can also print a summary of your model by running the following code.

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>model.summary()</code></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span>

____________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ==================================================================================================== input_1 (InputLayer) (None, 64, 64, 3) 0 ____________________________________________________________________________________________________ zero_padding2d_1 (ZeroPadding2D) (None, 70, 70, 3) 0 input_1[0][0] ____________________________________________________________________________________________________ conv1 (Conv2D) (None, 32, 32, 64) 9472 zero_padding2d_1[0][0] ____________________________________________________________________________________________________ bn_conv1 (BatchNormalization) (None, 32, 32, 64) 256 conv1[0][0] ____________________________________________________________________________________________________ activation_4 (Activation) (None, 32, 32, 64) 0 bn_conv1[0][0] ____________________________________________________________________________________________________ max_pooling2d_1 (MaxPooling2D) (None, 15, 15, 64) 0 activation_4[0][0] ____________________________________________________________________________________________________ res2a_branch2a (Conv2D) (None, 15, 15, 64) 4160 max_pooling2d_1[0][0] ____________________________________________________________________________________________________ bn2a_branch2a (BatchNormalizatio (None, 15, 15, 64) 256 res2a_branch2a[0][0] ____________________________________________________________________________________________________ activation_5 (Activation) (None, 15, 15, 64) 0 bn2a_branch2a[0][0] ____________________________________________________________________________________________________ res2a_branch2b (Conv2D) (None, 15, 15, 64) 36928 activation_5[0][0] ____________________________________________________________________________________________________ bn2a_branch2b (BatchNormalizatio (None, 15, 15, 64) 256 res2a_branch2b[0][0] ____________________________________________________________________________________________________ activation_6 (Activation) (None, 15, 15, 64) 0 bn2a_branch2b[0][0] ____________________________________________________________________________________________________ res2a_branch2c (Conv2D) (None, 15, 15, 256) 16640 activation_6[0][0] ____________________________________________________________________________________________________ res2a_branch1 (Conv2D) (None, 15, 15, 256) 16640 max_pooling2d_1[0][0] ____________________________________________________________________________________________________ bn2a_branch2c (BatchNormalizatio (None, 15, 15, 256) 1024 res2a_branch2c[0][0] ____________________________________________________________________________________________________ bn2a_branch1 (BatchNormalization (None, 15, 15, 256) 1024 res2a_branch1[0][0] ____________________________________________________________________________________________________ add_2 (Add) (None, 15, 15, 256) 0 bn2a_branch2c[0][0] bn2a_branch1[0][0] ____________________________________________________________________________________________________ activation_7 (Activation) (None, 15, 15, 256) 0 add_2[0][0] ____________________________________________________________________________________________________ res2b_branch2a (Conv2D) (None, 15, 15, 64) 16448 activation_7[0][0] ____________________________________________________________________________________________________ bn2b_branch2a (BatchNormalizatio (None, 15, 15, 64) 256 res2b_branch2a[0][0] ____________________________________________________________________________________________________ activation_8 (Activation) (None, 15, 15, 64) 0 bn2b_branch2a[0][0] ____________________________________________________________________________________________________ res2b_branch2b (Conv2D) (None, 15, 15, 64) 36928 activation_8[0][0] ____________________________________________________________________________________________________ bn2b_branch2b (BatchNormalizatio (None, 15, 15, 64) 256 res2b_branch2b[0][0] ____________________________________________________________________________________________________ activation_9 (Activation) (None, 15, 15, 64) 0 bn2b_branch2b[0][0] ____________________________________________________________________________________________________ res2b_branch2c (Conv2D) (None, 15, 15, 256) 16640 activation_9[0][0] ____________________________________________________________________________________________________ bn2b_branch2c (BatchNormalizatio (None, 15, 15, 256) 1024 res2b_branch2c[0][0] ____________________________________________________________________________________________________ add_3 (Add) (None, 15, 15, 256) 0 bn2b_branch2c[0][0] activation_7[0][0] ____________________________________________________________________________________________________ activation_10 (Activation) (None, 15, 15, 256) 0 add_3[0][0] ____________________________________________________________________________________________________ res2c_branch2a (Conv2D) (None, 15, 15, 64) 16448 activation_10[0][0] ____________________________________________________________________________________________________ bn2c_branch2a (BatchNormalizatio (None, 15, 15, 64) 256 res2c_branch2a[0][0] ____________________________________________________________________________________________________ activation_11 (Activation) (None, 15, 15, 64) 0 bn2c_branch2a[0][0] ____________________________________________________________________________________________________ res2c_branch2b (Conv2D) (None, 15, 15, 64) 36928 activation_11[0][0] ____________________________________________________________________________________________________ bn2c_branch2b (BatchNormalizatio (None, 15, 15, 64) 256 res2c_branch2b[0][0] ____________________________________________________________________________________________________ activation_12 (Activation) (None, 15, 15, 64) 0 bn2c_branch2b[0][0] ____________________________________________________________________________________________________ res2c_branch2c (Conv2D) (None, 15, 15, 256) 16640 activation_12[0][0] ____________________________________________________________________________________________________ bn2c_branch2c (BatchNormalizatio (None, 15, 15, 256) 1024 res2c_branch2c[0][0] ____________________________________________________________________________________________________ add_4 (Add) (None, 15, 15, 256) 0 bn2c_branch2c[0][0] activation_10[0][0] ____________________________________________________________________________________________________ activation_13 (Activation) (None, 15, 15, 256) 0 add_4[0][0] ____________________________________________________________________________________________________ res3a_branch2a (Conv2D) (None, 8, 8, 128) 32896 activation_13[0][0] ____________________________________________________________________________________________________ bn3a_branch2a (BatchNormalizatio (None, 8, 8, 128) 512 res3a_branch2a[0][0] ____________________________________________________________________________________________________ activation_14 (Activation) (None, 8, 8, 128) 0 bn3a_branch2a[0][0] ____________________________________________________________________________________________________ res3a_branch2b (Conv2D) (None, 8, 8, 128) 147584 activation_14[0][0] ____________________________________________________________________________________________________ bn3a_branch2b (BatchNormalizatio (None, 8, 8, 128) 512 res3a_branch2b[0][0] ____________________________________________________________________________________________________ activation_15 (Activation) (None, 8, 8, 128) 0 bn3a_branch2b[0][0] ____________________________________________________________________________________________________ res3a_branch2c (Conv2D) (None, 8, 8, 512) 66048 activation_15[0][0] ____________________________________________________________________________________________________ res3a_branch1 (Conv2D) (None, 8, 8, 512) 131584 activation_13[0][0] ____________________________________________________________________________________________________ bn3a_branch2c (BatchNormalizatio (None, 8, 8, 512) 2048 res3a_branch2c[0][0] ____________________________________________________________________________________________________ bn3a_branch1 (BatchNormalization (None, 8, 8, 512) 2048 res3a_branch1[0][0] ____________________________________________________________________________________________________ add_5 (Add) (None, 8, 8, 512) 0 bn3a_branch2c[0][0] bn3a_branch1[0][0] ____________________________________________________________________________________________________ activation_16 (Activation) (None, 8, 8, 512) 0 add_5[0][0] ____________________________________________________________________________________________________ res3b_branch2a (Conv2D) (None, 8, 8, 128) 65664 activation_16[0][0] ____________________________________________________________________________________________________ bn3b_branch2a (BatchNormalizatio (None, 8, 8, 128) 512 res3b_branch2a[0][0] ____________________________________________________________________________________________________ activation_17 (Activation) (None, 8, 8, 128) 0 bn3b_branch2a[0][0] ____________________________________________________________________________________________________ res3b_branch2b (Conv2D) (None, 8, 8, 128) 147584 activation_17[0][0] ____________________________________________________________________________________________________ bn3b_branch2b (BatchNormalizatio (None, 8, 8, 128) 512 res3b_branch2b[0][0] ____________________________________________________________________________________________________ activation_18 (Activation) (None, 8, 8, 128) 0 bn3b_branch2b[0][0] ____________________________________________________________________________________________________ res3b_branch2c (Conv2D) (None, 8, 8, 512) 66048 activation_18[0][0] ____________________________________________________________________________________________________ bn3b_branch2c (BatchNormalizatio (None, 8, 8, 512) 2048 res3b_branch2c[0][0] ____________________________________________________________________________________________________ add_6 (Add) (None, 8, 8, 512) 0 bn3b_branch2c[0][0] activation_16[0][0] ____________________________________________________________________________________________________ activation_19 (Activation) (None, 8, 8, 512) 0 add_6[0][0] ____________________________________________________________________________________________________ res3c_branch2a (Conv2D) (None, 8, 8, 128) 65664 activation_19[0][0] ____________________________________________________________________________________________________ bn3c_branch2a (BatchNormalizatio (None, 8, 8, 128) 512 res3c_branch2a[0][0] ____________________________________________________________________________________________________ activation_20 (Activation) (None, 8, 8, 128) 0 bn3c_branch2a[0][0] ____________________________________________________________________________________________________ res3c_branch2b (Conv2D) (None, 8, 8, 128) 147584 activation_20[0][0] ____________________________________________________________________________________________________ bn3c_branch2b (BatchNormalizatio (None, 8, 8, 128) 512 res3c_branch2b[0][0] ____________________________________________________________________________________________________ activation_21 (Activation) (None, 8, 8, 128) 0 bn3c_branch2b[0][0] ____________________________________________________________________________________________________ res3c_branch2c (Conv2D) (None, 8, 8, 512) 66048 activation_21[0][0] ____________________________________________________________________________________________________ bn3c_branch2c (BatchNormalizatio (None, 8, 8, 512) 2048 res3c_branch2c[0][0] ____________________________________________________________________________________________________ add_7 (Add) (None, 8, 8, 512) 0 bn3c_branch2c[0][0] activation_19[0][0] ____________________________________________________________________________________________________ activation_22 (Activation) (None, 8, 8, 512) 0 add_7[0][0] ____________________________________________________________________________________________________ res3d_branch2a (Conv2D) (None, 8, 8, 128) 65664 activation_22[0][0] ____________________________________________________________________________________________________ bn3d_branch2a (BatchNormalizatio (None, 8, 8, 128) 512 res3d_branch2a[0][0] ____________________________________________________________________________________________________ activation_23 (Activation) (None, 8, 8, 128) 0 bn3d_branch2a[0][0] ____________________________________________________________________________________________________ res3d_branch2b (Conv2D) (None, 8, 8, 128) 147584 activation_23[0][0] ____________________________________________________________________________________________________ bn3d_branch2b (BatchNormalizatio (None, 8, 8, 128) 512 res3d_branch2b[0][0] ____________________________________________________________________________________________________ activation_24 (Activation) (None, 8, 8, 128) 0 bn3d_branch2b[0][0] ____________________________________________________________________________________________________ res3d_branch2c (Conv2D) (None, 8, 8, 512) 66048 activation_24[0][0] ____________________________________________________________________________________________________ bn3d_branch2c (BatchNormalizatio (None, 8, 8, 512) 2048 res3d_branch2c[0][0] ____________________________________________________________________________________________________ add_8 (Add) (None, 8, 8, 512) 0 bn3d_branch2c[0][0] activation_22[0][0] ____________________________________________________________________________________________________ activation_25 (Activation) (None, 8, 8, 512) 0 add_8[0][0] ____________________________________________________________________________________________________ res4a_branch2a (Conv2D) (None, 4, 4, 256) 131328 activation_25[0][0] ____________________________________________________________________________________________________ bn4a_branch2a (BatchNormalizatio (None, 4, 4, 256) 1024 res4a_branch2a[0][0] ____________________________________________________________________________________________________ activation_26 (Activation) (None, 4, 4, 256) 0 bn4a_branch2a[0][0] ____________________________________________________________________________________________________ res4a_branch2b (Conv2D) (None, 4, 4, 256) 590080 activation_26[0][0] ____________________________________________________________________________________________________ bn4a_branch2b (BatchNormalizatio (None, 4, 4, 256) 1024 res4a_branch2b[0][0] ____________________________________________________________________________________________________ activation_27 (Activation) (None, 4, 4, 256) 0 bn4a_branch2b[0][0] ____________________________________________________________________________________________________ res4a_branch2c (Conv2D) (None, 4, 4, 1024) 263168 activation_27[0][0] ____________________________________________________________________________________________________ res4a_branch1 (Conv2D) (None, 4, 4, 1024) 525312 activation_25[0][0] ____________________________________________________________________________________________________ bn4a_branch2c (BatchNormalizatio (None, 4, 4, 1024) 4096 res4a_branch2c[0][0] ____________________________________________________________________________________________________ bn4a_branch1 (BatchNormalization (None, 4, 4, 1024) 4096 res4a_branch1[0][0] ____________________________________________________________________________________________________ add_9 (Add) (None, 4, 4, 1024) 0 bn4a_branch2c[0][0] bn4a_branch1[0][0] ____________________________________________________________________________________________________ activation_28 (Activation) (None, 4, 4, 1024) 0 add_9[0][0] ____________________________________________________________________________________________________ res4b_branch2a (Conv2D) (None, 4, 4, 256) 262400 activation_28[0][0] ____________________________________________________________________________________________________ bn4b_branch2a (BatchNormalizatio (None, 4, 4, 256) 1024 res4b_branch2a[0][0] ____________________________________________________________________________________________________ activation_29 (Activation) (None, 4, 4, 256) 0 bn4b_branch2a[0][0] ____________________________________________________________________________________________________ res4b_branch2b (Conv2D) (None, 4, 4, 256) 590080 activation_29[0][0] ____________________________________________________________________________________________________ bn4b_branch2b (BatchNormalizatio (None, 4, 4, 256) 1024 res4b_branch2b[0][0] ____________________________________________________________________________________________________ activation_30 (Activation) (None, 4, 4, 256) 0 bn4b_branch2b[0][0] ____________________________________________________________________________________________________ res4b_branch2c (Conv2D) (None, 4, 4, 1024) 263168 activation_30[0][0] ____________________________________________________________________________________________________ bn4b_branch2c (BatchNormalizatio (None, 4, 4, 1024) 4096 res4b_branch2c[0][0] ____________________________________________________________________________________________________ add_10 (Add) (None, 4, 4, 1024) 0 bn4b_branch2c[0][0] activation_28[0][0] ____________________________________________________________________________________________________ activation_31 (Activation) (None, 4, 4, 1024) 0 add_10[0][0] ____________________________________________________________________________________________________ res4c_branch2a (Conv2D) (None, 4, 4, 256) 262400 activation_31[0][0] ____________________________________________________________________________________________________ bn4c_branch2a (BatchNormalizatio (None, 4, 4, 256) 1024 res4c_branch2a[0][0] ____________________________________________________________________________________________________ activation_32 (Activation) (None, 4, 4, 256) 0 bn4c_branch2a[0][0] ____________________________________________________________________________________________________ res4c_branch2b (Conv2D) (None, 4, 4, 256) 590080 activation_32[0][0] ____________________________________________________________________________________________________ bn4c_branch2b (BatchNormalizatio (None, 4, 4, 256) 1024 res4c_branch2b[0][0] ____________________________________________________________________________________________________ activation_33 (Activation) (None, 4, 4, 256) 0 bn4c_branch2b[0][0] ____________________________________________________________________________________________________ res4c_branch2c (Conv2D) (None, 4, 4, 1024) 263168 activation_33[0][0] ____________________________________________________________________________________________________ bn4c_branch2c (BatchNormalizatio (None, 4, 4, 1024) 4096 res4c_branch2c[0][0] ____________________________________________________________________________________________________ add_11 (Add) (None, 4, 4, 1024) 0 bn4c_branch2c[0][0] activation_31[0][0] ____________________________________________________________________________________________________ activation_34 (Activation) (None, 4, 4, 1024) 0 add_11[0][0] ____________________________________________________________________________________________________ res4d_branch2a (Conv2D) (None, 4, 4, 256) 262400 activation_34[0][0] ____________________________________________________________________________________________________ bn4d_branch2a (BatchNormalizatio (None, 4, 4, 256) 1024 res4d_branch2a[0][0] ____________________________________________________________________________________________________ activation_35 (Activation) (None, 4, 4, 256) 0 bn4d_branch2a[0][0] ____________________________________________________________________________________________________ res4d_branch2b (Conv2D) (None, 4, 4, 256) 590080 activation_35[0][0] ____________________________________________________________________________________________________ bn4d_branch2b (BatchNormalizatio (None, 4, 4, 256) 1024 res4d_branch2b[0][0] ____________________________________________________________________________________________________ activation_36 (Activation) (None, 4, 4, 256) 0 bn4d_branch2b[0][0] ____________________________________________________________________________________________________ res4d_branch2c (Conv2D) (None, 4, 4, 1024) 263168 activation_36[0][0] ____________________________________________________________________________________________________ bn4d_branch2c (BatchNormalizatio (None, 4, 4, 1024) 4096 res4d_branch2c[0][0] ____________________________________________________________________________________________________ add_12 (Add) (None, 4, 4, 1024) 0 bn4d_branch2c[0][0] activation_34[0][0] ____________________________________________________________________________________________________ activation_37 (Activation) (None, 4, 4, 1024) 0 add_12[0][0] ____________________________________________________________________________________________________ res4e_branch2a (Conv2D) (None, 4, 4, 256) 262400 activation_37[0][0] ____________________________________________________________________________________________________ bn4e_branch2a (BatchNormalizatio (None, 4, 4, 256) 1024 res4e_branch2a[0][0] ____________________________________________________________________________________________________ activation_38 (Activation) (None, 4, 4, 256) 0 bn4e_branch2a[0][0] ____________________________________________________________________________________________________ res4e_branch2b (Conv2D) (None, 4, 4, 256) 590080 activation_38[0][0] ____________________________________________________________________________________________________ bn4e_branch2b (BatchNormalizatio (None, 4, 4, 256) 1024 res4e_branch2b[0][0] ____________________________________________________________________________________________________ activation_39 (Activation) (None, 4, 4, 256) 0 bn4e_branch2b[0][0] ____________________________________________________________________________________________________ res4e_branch2c (Conv2D) (None, 4, 4, 1024) 263168 activation_39[0][0] ____________________________________________________________________________________________________ bn4e_branch2c (BatchNormalizatio (None, 4, 4, 1024) 4096 res4e_branch2c[0][0] ____________________________________________________________________________________________________ add_13 (Add) (None, 4, 4, 1024) 0 bn4e_branch2c[0][0] activation_37[0][0] ____________________________________________________________________________________________________ activation_40 (Activation) (None, 4, 4, 1024) 0 add_13[0][0] ____________________________________________________________________________________________________ res4f_branch2a (Conv2D) (None, 4, 4, 256) 262400 activation_40[0][0] ____________________________________________________________________________________________________ bn4f_branch2a (BatchNormalizatio (None, 4, 4, 256) 1024 res4f_branch2a[0][0] ____________________________________________________________________________________________________ activation_41 (Activation) (None, 4, 4, 256) 0 bn4f_branch2a[0][0] ____________________________________________________________________________________________________ res4f_branch2b (Conv2D) (None, 4, 4, 256) 590080 activation_41[0][0] ____________________________________________________________________________________________________ bn4f_branch2b (BatchNormalizatio (None, 4, 4, 256) 1024 res4f_branch2b[0][0] ____________________________________________________________________________________________________ activation_42 (Activation) (None, 4, 4, 256) 0 bn4f_branch2b[0][0] ____________________________________________________________________________________________________ res4f_branch2c (Conv2D) (None, 4, 4, 1024) 263168 activation_42[0][0] ____________________________________________________________________________________________________ bn4f_branch2c (BatchNormalizatio (None, 4, 4, 1024) 4096 res4f_branch2c[0][0] ____________________________________________________________________________________________________ add_14 (Add) (None, 4, 4, 1024) 0 bn4f_branch2c[0][0] activation_40[0][0] ____________________________________________________________________________________________________ activation_43 (Activation) (None, 4, 4, 1024) 0 add_14[0][0] ____________________________________________________________________________________________________ res5a_branch2a (Conv2D) (None, 2, 2, 512) 524800 activation_43[0][0] ____________________________________________________________________________________________________ bn5a_branch2a (BatchNormalizatio (None, 2, 2, 512) 2048 res5a_branch2a[0][0] ____________________________________________________________________________________________________ activation_44 (Activation) (None, 2, 2, 512) 0 bn5a_branch2a[0][0] ____________________________________________________________________________________________________ res5a_branch2b (Conv2D) (None, 2, 2, 512) 2359808 activation_44[0][0] ____________________________________________________________________________________________________ bn5a_branch2b (BatchNormalizatio (None, 2, 2, 512) 2048 res5a_branch2b[0][0] ____________________________________________________________________________________________________ activation_45 (Activation) (None, 2, 2, 512) 0 bn5a_branch2b[0][0] ____________________________________________________________________________________________________ res5a_branch2c (Conv2D) (None, 2, 2, 2048) 1050624 activation_45[0][0] ____________________________________________________________________________________________________ res5a_branch1 (Conv2D) (None, 2, 2, 2048) 2099200 activation_43[0][0] ____________________________________________________________________________________________________ bn5a_branch2c (BatchNormalizatio (None, 2, 2, 2048) 8192 res5a_branch2c[0][0] ____________________________________________________________________________________________________ bn5a_branch1 (BatchNormalization (None, 2, 2, 2048) 8192 res5a_branch1[0][0] ____________________________________________________________________________________________________ add_15 (Add) (None, 2, 2, 2048) 0 bn5a_branch2c[0][0] bn5a_branch1[0][0] ____________________________________________________________________________________________________ activation_46 (Activation) (None, 2, 2, 2048) 0 add_15[0][0] ____________________________________________________________________________________________________ res5b_branch2a (Conv2D) (None, 2, 2, 512) 1049088 activation_46[0][0] ____________________________________________________________________________________________________ bn5b_branch2a (BatchNormalizatio (None, 2, 2, 512) 2048 res5b_branch2a[0][0] ____________________________________________________________________________________________________ activation_47 (Activation) (None, 2, 2, 512) 0 bn5b_branch2a[0][0] ____________________________________________________________________________________________________ res5b_branch2b (Conv2D) (None, 2, 2, 512) 2359808 activation_47[0][0] ____________________________________________________________________________________________________ bn5b_branch2b (BatchNormalizatio (None, 2, 2, 512) 2048 res5b_branch2b[0][0] ____________________________________________________________________________________________________ activation_48 (Activation) (None, 2, 2, 512) 0 bn5b_branch2b[0][0] ____________________________________________________________________________________________________ res5b_branch2c (Conv2D) (None, 2, 2, 2048) 1050624 activation_48[0][0] ____________________________________________________________________________________________________ bn5b_branch2c (BatchNormalizatio (None, 2, 2, 2048) 8192 res5b_branch2c[0][0] ____________________________________________________________________________________________________ add_16 (Add) (None, 2, 2, 2048) 0 bn5b_branch2c[0][0] activation_46[0][0] ____________________________________________________________________________________________________ activation_49 (Activation) (None, 2, 2, 2048) 0 add_16[0][0] ____________________________________________________________________________________________________ res5c_branch2a (Conv2D) (None, 2, 2, 512) 1049088 activation_49[0][0] ____________________________________________________________________________________________________ bn5c_branch2a (BatchNormalizatio (None, 2, 2, 512) 2048 res5c_branch2a[0][0] ____________________________________________________________________________________________________ activation_50 (Activation) (None, 2, 2, 512) 0 bn5c_branch2a[0][0] ____________________________________________________________________________________________________ res5c_branch2b (Conv2D) (None, 2, 2, 512) 2359808 activation_50[0][0] ____________________________________________________________________________________________________ bn5c_branch2b (BatchNormalizatio (None, 2, 2, 512) 2048 res5c_branch2b[0][0] ____________________________________________________________________________________________________ activation_51 (Activation) (None, 2, 2, 512) 0 bn5c_branch2b[0][0] ____________________________________________________________________________________________________ res5c_branch2c (Conv2D) (None, 2, 2, 2048) 1050624 activation_51[0][0] ____________________________________________________________________________________________________ bn5c_branch2c (BatchNormalizatio (None, 2, 2, 2048) 8192 res5c_branch2c[0][0] ____________________________________________________________________________________________________ add_17 (Add) (None, 2, 2, 2048) 0 bn5c_branch2c[0][0] activation_49[0][0] ____________________________________________________________________________________________________ activation_52 (Activation) (None, 2, 2, 2048) 0 add_17[0][0] ____________________________________________________________________________________________________ avg_pool (AveragePooling2D) (None, 1, 1, 2048) 0 activation_52[0][0] ____________________________________________________________________________________________________ flatten_1 (Flatten) (None, 2048) 0 avg_pool[0][0] ____________________________________________________________________________________________________ fc6 (Dense) (None, 6) 12294 flatten_1[0][0] ==================================================================================================== Total params: 23,600,006 Trainable params: 23,546,886 Non-trainable params: 53,120 ____________________________________________________________________________________________________

Finally, run the code below to visualize your ResNet50. You can also download a .png picture of your model by going to "File -> Open...-> model.png".

<span style="color:#000000"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><span style="color:purple"><code>plot_model(model, to_file=<span style="color:#a31515">'model.png'</span>)
SVG(model_to_dot(model).create(prog=<span style="color:#a31515">'dot'</span>, format=<span style="color:#a31515">'svg'</span>))</code></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span>

What you should remember:

• Very deep "plain" networks don't work in practice because they are hard to train due to vanishing gradients.
• The skip-connections help to address the Vanishing Gradient problem. They also make it easy for a ResNet block to learn an identity function.
• There are two main type of blocks: The identity block and the convolutional block.
• Very deep Residual Networks are built by stacking these blocks together.

References

This notebook presents the ResNet algorithm due to He et al. (2015). The implementation here also took significant inspiration and follows the structure given in the github repository of Francois Chollet:

• Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun - Deep Residual Learning for Image Recognition (2015)
• Francois Chollet's github repository: https://github.com/fchollet/deep-learning-models/blob/master/resnet50.py
• https://www.cnblogs.com/ranjiewen/p/7889401.html