def random_test_with_dropout_tf(): X, Y, Y_onehot = input_data.loadRandomData() layer_types = [ 'relu', 'softmax', ] hidden_layer_dims = [ 120, ] parameters = nn_model_tf.model(X, Y_onehot, hidden_layer_dims, layer_types, learning_rate=0.5, num_iterations=2001, num_batches=2, prob=0.5) Y_predict, train_accuracy = nn_model_tf.predict(X, Y_onehot, parameters, hidden_layer_dims, layer_types) train_accuracy = np.sum(Y_predict == Y) / Y.shape[1] print('Training accuracy: %f' % train_accuracy) plot.show_decision_boundry(X, Y, Y_onehot, nn_model_tf.predict, parameters, hidden_layer_dims, layer_types)
def random_test_with_dropout_adam(): X, Y, Y_onehot=input_data.loadRandomData() layer_types=['relu','softmax',] hidden_layer_dims=[120,] parameters = nn_model.model_with_dropout_adam(X, Y_onehot, hidden_layer_dims, layer_types, learning_rate=0.5, num_iterations=2001) Y_predict, train_accuracy = nn_model.predict(X, Y_onehot, parameters, hidden_layer_dims, layer_types) train_accuracy = np.sum(Y_predict==Y) / Y.shape[1] print('Training accuracy: %f' % train_accuracy)
def check_dropout(): X, Y, Y_onehot = input_data.loadRandomData() layer_types = [ 'softmax', ] layer_dims = [X.shape[0], Y_onehot.shape[0]] parameters = nn_model.init_params(layer_dims) gradient_check_with_dorpout(X, Y, layer_dims, layer_types, parameters, num_params=2)
def check_softmax(): X, Y, Y_onehot = input_data.loadRandomData() # X.shape=(2, 300), Y.shape=(1,300), Y_onehot=(3,300) # number of examples = 300, number of classes = 3 layer_types = [ 'softmax', ] layer_dims = [X.shape[0], Y_onehot.shape[0]] parameters = nn_model.init_params(layer_dims) gradient_check(X, Y_onehot, layer_dims, layer_types, parameters, epsilon=1e-7, num_params=2, lambd=1)
def random_test_tf(): X, Y, Y_onehot = input_data.loadRandomData() layer_types = [ 'relu', 'softmax', ] hidden_layer_dims = [ 120, ] parameters = nn_model_tf.model(X, Y_onehot, hidden_layer_dims, layer_types, learning_rate=0.5, num_iterations=1001, lambd=0) Y_predict, train_accuracy = nn_model_tf.predict(X, Y_onehot, parameters, hidden_layer_dims, layer_types) print('Training accuracy: %f' % train_accuracy) plot.show_decision_boundry(X, Y, Y_onehot, nn_model.predict, parameters, hidden_layer_dims, layer_types)