3/28/2024 0 Comments Super vectorizer 2 car# Display the images where the algorithm got wrongĭisplayData(images_training)ĭef ave_percep(train_path, test_path, category, k): Print '\nAccuracy on test set: ' + str(mean(labels_test = pred) * 100) Print '\nAccuracy on training set: ' + str(mean(labels_training = pred_training) * 100) Pred_training = predict(Theta, images_training) Res = fmin_l_bfgs_b(costFunction, nn_weights, fprime=backwards, args=(layers, images_training, labels_training, num_labels, lambd), maxfun = num_iterations, factr = 1., disp = True) # Fill the randInitializeWeights.py in order to initialize the neural network weights. Num_of_hidden_layers = len(hidden_layers) Num_labels = 10 # 10 labels, from 0 to 9 (one label for each digit) Input_layer_size = 784 # 28x28 Input Images of Digits ![]() # Setup the parameters you will use for this exercise Images_training, labels_training, images_test, labels_test = read_dataset(size_training, size_test) Def finalTest(size_training, size_test, hidden_layers, lambd, num_iterations):
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |