def load_dataset(): train_dataset = h5py.File('D:/PyWorkspace/DeepLearning/datasets/train_catvnoncat.h5', "r") train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels
test_dataset = h5py.File('D:/PyWorkspace/DeepLearning/datasets/test_catvnoncat.h5', "r") test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels
classes = np.array(test_dataset["list_classes"][:]) # the list of classes
# GRADED FUNCTION: initialize_parameters_he def initialize_parameters_he(layers_dims): """ Arguments: layer_dims -- python array (list) containing the size of each layer.
Returns: parameters -- python dictionary containing your parameters "W1", "b1", ..., "WL", "bL": W1 -- weight matrix of shape (layers_dims[1], layers_dims[0]) b1 -- bias vector of shape (layers_dims[1], 1) ... WL -- weight matrix of shape (layers_dims[L], layers_dims[L-1]) bL -- bias vector of shape (layers_dims[L], 1) """
np.random.seed(3) parameters = {} L = len(layers_dims) - 1 # integer representing the number of layers
for l in range(1, L + 1): ### START CODE HERE ### (≈ 2 lines of code) parameters['W' + str(l)] = np.random.randn(layers_dims[l], layers_dims[l - 1]) * np.sqrt(2.0 / layers_dims[l - 1]) parameters['b' + str(l)] = np.zeros((layers_dims[l], 1)) ### END CODE HERE ###
return parameters
forward
前向传播比较简单，就是： *W * X + b* 矩阵相乘的过程，只是激活单元非线性函数再做一个处理。 最终到输出层，输出值与真实标签算一个损失。
算损失又有不同的策略，常见的交叉熵损失，平方损失等等。
注意：绝对值损失不怎么用的原因就是因为不好求导，而平方便于求导
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
def compute_cost(AL, Y): """ Implement the cost function defined by equation (7). Arguments: AL -- probability vector corresponding to your label predictions, shape (1, number of examples) Y -- true "label" vector (for example: containing 0 if non-cat, 1 if cat), shape (1, number of examples) Returns: cost -- cross-entropy cost """ m = Y.shape[1] # Compute loss from aL and y. ### START CODE HERE ### ( 1 lines of code) cost = -(np.dot(Y,np.log(AL.T))+np.dot(1-Y,np.log(1-AL).T))/m ### END CODE HERE ### cost = np.squeeze(cost) # To make sure your cost's shape is what we expect (e.g. this turns [[17]] into 17) assert(cost.shape == ()) return cost
def L_model_backward(AL, Y, caches): """ Implement the backward propagation for the [LINEAR->RELU] * (L-1) -> LINEAR -> SIGMOID group
Arguments: AL -- probability vector, output of the forward propagation (L_model_forward()) Y -- true "label" vector (containing 0 if non-cat, 1 if cat) caches -- list of caches containing: every cache of linear_activation_forward() with "relu" (it's caches[l], for l in range(L-1) i.e l = 0...L-2) the cache of linear_activation_forward() with "sigmoid" (it's caches[L-1])
Returns: grads -- A dictionary with the gradients grads["dA" + str(l)] = ... grads["dW" + str(l)] = ... grads["db" + str(l)] = ... """ grads = {} L = len(caches) # the number of layers m = AL.shape[1] Y = Y.reshape(AL.shape) # after this line, Y is the same shape as AL
# Initializing the backpropagation ### START CODE HERE ### (1 line of code) dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL)) ### END CODE HERE ###
