前兩個筆記筆者集中探討了卷積神經網絡中的卷積原理，對于二維卷積和三維卷積的原理進行了深入的剖析，對 CNN 的卷積、池化、全連接、濾波器、感受野等關鍵概念進行了充分的理解。本節內容將繼續秉承之前 DNN 的學習路線，在利用Tensorflow搭建神經網絡之前，先嘗試利用numpy手動搭建卷積神經網絡，以期對卷積神經網絡的卷積機制、前向傳播和反向傳播的原理和過程有更深刻的理解。

單步卷積過程

在正式搭建 CNN 之前，我們先依據前面筆記提到的卷積機制的線性計算的理解，利用numpy定義一個單步卷積過程。代碼如下：

def conv_single_step(a_slice_prev, W, b): s = a_slice_prev * W # Sum over all entries of the volume s. Z = np.sum(s) # Add bias b to Z. Cast b to a float() so that Z results in a scalar value. Z = float(Z + b) return Z

在上述的單步卷積定義中，我們傳入了一個前一層輸入的要進行卷積的區域，即感受野 a_slice_prev，濾波器W，即卷積層的權重參數，偏差b，對其執行Z=Wx+b的線性計算即可實現一個單步的卷積過程。

CNN前向傳播過程：卷積

正如 DNN 中一樣，CNN 即使多了卷積和池化過程，模型仍然是前向傳播和反向傳播的訓練過程。CNN 的前向傳播包括卷積和池化兩個過程，我們先來看如何利用numpy基于上面定義的單步卷積實現完整的卷積過程。卷積計算并不難，我們在單步卷積中就已經實現了，難點在于如何實現濾波器在輸入圖像矩陣上的的掃描和移動過程。

這其中我們需要搞清楚一些變量和參數，以及每一個輸入輸出的shape，這對于我們執行卷積和矩陣相乘至關重要。首先我們的輸入是原始圖像矩陣，也可以是前一層經過激活后的圖像輸出矩陣，這里以前一層的激活輸出為準，輸入像素的shape我們必須明確，然后是濾波器矩陣和偏差，還需要考慮步幅和填充，在此基礎上我們基于濾波器移動和單步卷積搭建定義如下前向卷積過程：

def conv_forward(A_prev, W, b, hparameters): """ Arguments: A_prev -- output activations of the previous layer, numpy array of shape (m, n_H_prev, n_W_prev, n_C_prev) W -- Weights, numpy array of shape (f, f, n_C_prev, n_C) b -- Biases, numpy array of shape (1, 1, 1, n_C) hparameters -- python dictionary containing "stride" and "pad" Returns: Z -- conv output, numpy array of shape (m, n_H, n_W, n_C) cache -- cache of values needed for the conv_backward() function """ # 前一層輸入的shape (m, n_H_prev, n_W_prev, n_C_prev) = A_prev.shape # 濾波器權重的shape (f, f, n_C_prev, n_C) = W.shape # 步幅參數 stride = hparameters['stride'] # 填充參數 pad = hparameters['pad'] # 計算輸出圖像的高寬 n_H = int((n_H_prev + 2 * pad - f) / stride + 1) n_W = int((n_W_prev + 2 * pad - f) / stride + 1) # 初始化輸出 Z = np.zeros((m, n_H, n_W, n_C)) # 對輸入執行邊緣填充 A_prev_pad = zero_pad(A_prev, pad) for i in range(m): a_prev_pad = A_prev_pad[i, :, :, :] for h in range(n_H): for w in range(n_W): for c in range(n_C): # 濾波器在輸入圖像上掃描 vert_start = h * stride vert_end = vert_start + f horiz_start = w * stride horiz_end = horiz_start + f # 定義感受野 a_slice_prev = a_prev_pad[vert_start : vert_end, horiz_start : horiz_end, :] # 對感受野執行單步卷積 Z[i, h, w, c] = conv_single_step(a_slice_prev, W[:,:,:,c], b[:,:,:,c]) assert(Z.shape == (m, n_H, n_W, n_C)) cache = (A_prev, W, b, hparameters) return Z, cache

這樣，卷積神經網絡前向傳播中一個完整的卷積計算過程就被我們定義好了。通常而言，我們也會對卷積后輸出加一個relu激活操作，正如前面的圖2所示，這里我們就省略不加了。

CNN前向傳播過程：池化

池化簡單而言就是取局部區域最大值，池化的前向傳播跟卷積過程類似，但相對簡單一點，無需執行單步卷積那樣的乘積運算。同樣需要注意的是各參數和輸入輸出的shape，因此我們定義如下前向傳播池化過程：

def pool_forward(A_prev, hparameters, mode = "max"): """ Arguments: A_prev -- Input data, numpy array of shape (m, n_H_prev, n_W_prev, n_C_prev) hparameters -- python dictionary containing "f" and "stride" mode -- the pooling mode you would like to use, defined as a string ("max" or "average") Returns: A -- output of the pool layer, a numpy array of shape (m, n_H, n_W, n_C) cache -- cache used in the backward pass of the pooling layer, contains the input and hparameters """ # 前一層輸入的shape (m, n_H_prev, n_W_prev, n_C_prev) = A_prev.shape # 步幅和權重參數 f = hparameters["f"] stride = hparameters["stride"] # 計算輸出圖像的高寬 n_H = int(1 + (n_H_prev - f) / stride) n_W = int(1 + (n_W_prev - f) / stride) n_C = n_C_prev # 初始化輸出 A = np.zeros((m, n_H, n_W, n_C)) for i in range(m): for h in range(n_H): for w in range(n_W): for c in range (n_C): # 樹池在輸入圖像上掃描 vert_start = h * stride vert_end = vert_start + f horiz_start = w * stride horiz_end = horiz_start + f # 定義池化區域 a_prev_slice = A_prev[i, vert_start:vert_end, horiz_start:horiz_end, c] # 選擇池化類型 if mode == "max": A[i, h, w, c] = np.max(a_prev_slice) elif mode == "average": A[i, h, w, c] = np.mean(a_prev_slice) cache = (A_prev, hparameters) assert(A.shape == (m, n_H, n_W, n_C)) return A, cache

由上述代碼結構可以看出，前向傳播的池化過程的代碼結構和卷積過程非常類似。

CNN反向傳播過程：卷積

定義好前向傳播之后，難點和關鍵點就在于如何給卷積和池化過程定義反向傳播過程。卷積層的反向傳播向來是個復雜的過程，Tensorflow中我們只要定義好前向傳播過程，反向傳播會自動進行計算。但利用numpy搭建 CNN 反向傳播就還得我們自己定義了。其關鍵還是在于準確的定義損失函數對于各個變量的梯度：

由上述梯度計算公式和卷積的前向傳播過程，我們定義如下卷積的反向傳播函數：

def conv_backward(dZ, cache): """ Arguments: dZ -- gradient of the cost with respect to the output of the conv layer (Z), numpy array of shape (m, n_H, n_W, n_C) cache -- cache of values needed for the conv_backward(), output of conv_forward() Returns: dA_prev -- gradient of the cost with respect to the input of the conv layer (A_prev), numpy array of shape (m, n_H_prev, n_W_prev, n_C_prev) dW -- gradient of the cost with respect to the weights of the conv layer (W) numpy array of shape (f, f, n_C_prev, n_C) db -- gradient of the cost with respect to the biases of the conv layer (b) numpy array of shape (1, 1, 1, n_C) """ # 獲取前向傳播中存儲的cache (A_prev, W, b, hparameters) = cache # 前一層輸入的shape (m, n_H_prev, n_W_prev, n_C_prev) = A_prev.shape # 濾波器的 shape (f, f, n_C_prev, n_C) = W.shape # 步幅和權重參數 stride = hparameters['stride'] pad = hparameters['pad'] # dZ 的shape (m, n_H, n_W, n_C) = dZ.shape # 初始化 dA_prev, dW, db dA_prev = np.zeros((m, n_H_prev, n_W_prev, n_C_prev)) dW = np.zeros((f, f, n_C_prev, n_C)) db = np.zeros((1, 1, 1, n_C)) # 對A_prev 和 dA_prev 執行零填充 A_prev_pad = zero_pad(A_prev, pad) dA_prev_pad = zero_pad(dA_prev, pad) for i in range(m): # select ith training example from A_prev_pad and dA_prev_pad a_prev_pad = A_prev_pad[i,:,:,:] da_prev_pad = dA_prev_pad[i,:,:,:] for h in range(n_H): for w in range(n_W): for c in range(n_C): # 獲取當前感受野 vert_start = h * stride vert_end = vert_start + f horiz_start = w * stride horiz_end = horiz_start + f # 獲取當前濾波器矩陣 a_slice = a_prev_pad[vert_start:vert_end, horiz_start:horiz_end, :] # 梯度更新 da_prev_pad[vert_start:vert_end, horiz_start:horiz_end, :] += W[:,:,:,c] * dZ[i, h, w, c] dW[:,:,:,c] += a_slice * dZ[i, h, w, c] db[:,:,:,c] += dZ[i, h, w, c] dA_prev[i, :, :, :] = da_prev_pad[pad:-pad, pad:-pad, :] assert(dA_prev.shape == (m, n_H_prev, n_W_prev, n_C_prev)) return dA_prev, dW, db

CNN反向傳播過程：池化

反向傳播中的池化操作跟卷積也是類似的。再此之前，我們需要根據濾波器為最大池化和平均池化分別創建一個mask和一個distribute_value:

def create_mask_from_window(x): """ Creates a mask from an input matrix x, to identify the max entry of x. Arguments: x -- Array of shape (f, f) Returns: mask -- Array of the same shape as window, contains a True at the position corresponding to the max entry of x. """ mask = (x == np.max(x)) return mask

def distribute_value(dz, shape): """ Distributes the input value in the matrix of dimension shape Arguments: dz -- input scalar shape -- the shape (n_H, n_W) of the output matrix for which we want to distribute the value of dz Returns: a -- Array of size (n_H, n_W) for which we distributed the value of dz """ (n_H, n_W) = shape # Compute the value to distribute on the matrix average = dz / (n_H * n_W) # Create a matrix where every entry is the "average" value a = np.full(shape, average) return a

然后整合封裝最大池化的反向傳播過程：

def pool_backward(dA, cache, mode = "max"): """ Arguments: dA -- gradient of cost with respect to the output of the pooling layer, same shape as A cache -- cache output from the forward pass of the pooling layer, contains the layer's input and hparameters mode -- the pooling mode you would like to use, defined as a string ("max" or "average") Returns: dA_prev -- gradient of cost with respect to the input of the pooling layer, same shape as A_prev """ # Retrieve information from cache (A_prev, hparameters) = cache # Retrieve hyperparameters from "hparameters" stride = hparameters['stride'] f = hparameters['f'] # Retrieve dimensions from A_prev's shape and dA's shape m, n_H_prev, n_W_prev, n_C_prev = A_prev.shape m, n_H, n_W, n_C = dA.shape # Initialize dA_prev with zeros dA_prev = np.zeros((m, n_H_prev, n_W_prev, n_C_prev)) for i in range(m): # select training example from A_prev a_prev = A_prev[i,:,:,:] for h in range(n_H): for w in range(n_W): for c in range(n_C): # Find the corners of the current "slice" vert_start = h * stride vert_end = vert_start + f horiz_start = w * stride horiz_end = horiz_start + f # Compute the backward propagation in both modes. if mode == "max": a_prev_slice = a_prev[vert_start:vert_end, horiz_start:horiz_end, c] mask = create_mask_from_window(a_prev_slice) dA_prev[i, vert_start: vert_end, horiz_start: horiz_end, c] += np.multiply(mask, dA[i,h,w,c]) elif mode == "average": # Get the value a from dA da = dA[i,h,w,c] # Define the shape of the filter as fxf shape = (f,f) # Distribute it to get the correct slice of dA_prev. i.e. Add the distributed value of da. dA_prev[i, vert_start: vert_end, horiz_start: horiz_end, c] += distribute_value(da, shape) # Making sure your output shape is correct assert(dA_prev.shape == A_prev.shape) return dA_prev

這樣卷積神經網絡的整個前向傳播和反向傳播過程我們就搭建好了。可以說是非常費力的操作了，但我相信，經過這樣一步步的根據原理的手寫，你一定會對卷積神經網絡的原理理解更加深刻了。