Daisy_fight的博客

Common steps for pre-processing a new dataset are:1.  Figure out the dimensions and shapes of the problem(m_train, m_test, num_px, ...)2. Reshape the datasets such that each example is now avector of ...

1.Package 导入模块2.Dataset 导入数据3.Neural Network Model神经网络模型1）layer_size(X, Y) --> n_x, n_h, n_y 输入数据返回神经网络每层的节点个数2）initial_parameters(n_x, n_h, n_y) --> parameters(是一个字典，包括了W1,W2,b1,b2)3）forward_pr...

1.Packages：导入模块2.Outline of the Assignment：介绍整体框架3.初始化工作1）2-layer Neural Network：定义一个2层的神经网络，其实就是给个简单的事例，后面不会用到2）L-layer Neural Network：定义一个层网络initialize_parameters_deep(layer_dims) --> parameters ...

1 - L2 Regularization# GRADED FUNCTION: compute_cost_with_regularizationdef compute_cost_with_regularization(A3, Y, parameters, lambd): m = Y.shape[1] W1 = parameters["W1"] W2 = paramete...

# GRADED FUNCTION: forward_propagationdef forward_propagation(x, theta): """ Implement the linear forward propagation (compute J) presented in Figure 1 (J(theta) = theta * x) """ J ...

1 - Gradient Descent(Batch) Gradient Descent:X = data_inputY = labelsparameters = initialize_parameters(layers_dims)for i in range(0, num_iterations): # Forward propagation a, caches = forw...

Convolution functions, including:Zero PaddingConvolve windowConvolution forwardConvolution backward (optional)Pooling functions, including:Pooling forwardCreate maskDistribute valuePooling backward (o...

X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset()# Normalize image vectorsX_train = X_train_orig/255.X_test = X_test_orig/255.# ReshapeY_train = Y_train_orig.TY_te...