Created
March 13, 2019 08:10
-
-
Save Tooluloope/109f24e2089f41fc1be8a3383ab1c3ab to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def linear_activation_forward(W,A_prev,b, activation): | |
| """ | |
| Implement the linear part of a layer's forward propagation. | |
| Arguments: | |
| A_prev -- activations from previous layer (or input data): (size of previous layer, number of examples) | |
| W -- weights matrix: numpy array of shape (size of current layer, size of previous layer) | |
| b -- bias vector, numpy array of shape (size of the current layer, 1) | |
| activation -- either Sigmoid or Relu | |
| Returns: | |
| A -- the Activations for the next layer | |
| cache -- a python dictionary containing Linear_cache, activation_cache ; stored for computing the backward pass efficiently | |
| """ | |
| if activation == 'relu': | |
| Z,Linear_cache = linear_forward(W,A_prev,b) | |
| A,activation_cache = relu(Z) | |
| if activation == 'sigmoid': | |
| Z,Linear_cache = linear_forward(W,A_prev,b) | |
| A,activation_cache = sigmoid(Z) | |
| cache = (Linear_cache, activation_cache) | |
| return A, cache | |
| def L_model_forward(X, parameters): | |
| """ | |
| Implement forward propagation for the [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID computation | |
| Arguments: | |
| X -- data, numpy array of shape (input size, number of examples) | |
| layers_dim: represents the dimension of each hidden layer in the neural network, the index(i) represents the | |
| layer while layers_dim[i] represents the number of nodes in that layer | |
| Returns: | |
| AL -- last post-activation value | |
| caches -- list of caches containing: | |
| every cache of linear_activation_forward() (there are L-1 of them, indexed from 0 to L-1) | |
| """ | |
| caches = [] | |
| A = X # Here the A is the input layer | |
| L = len(parameters)//2 # Dividing it by two since parameter contains both W and b for each layer | |
| # SInce its only the output layer that requires the Sigmoid Function, All layers from 1 - L-1 would use Relu function | |
| for l in range(1,L): | |
| A_prev = A | |
| A, cache = linear_activation_forward(parameters['W'+str(l)],A_prev,parameters['b'+str(l)],activation ='relu') | |
| caches.append(cache) | |
| # for the output layer that requires sigmoid function | |
| Al, cache = linear_activation_forward(parameters['W'+str(L)],A,parameters['b'+str(L)],activation ='sigmoid') | |
| caches.append(cache) | |
| return Al, caches | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment