def load_CIFAR10_data(): path_data = 'E:/DATASETS/cifar-10-batches-py' x_train, y_train, x_test, y_test = load_all(path_data) # Split data into train, validation and test set num_train = 9000 num_val = 1000 num_test = 1000 # Validation set will be num_val points from the original training set mask = range(num_train, num_train + num_val) x_val = x_train[mask] y_val = y_train[mask] # Training set will be the first num_train points from the original training set mask = range(num_train) x_train = x_train[mask] y_train = y_train[mask] # User the first num_test points of the original test set as out test set mask = range(num_test) x_test = x_test[mask] y_test = y_test[mask] # Preprocessing : reshape the image data into rows x_train = x_train.reshape(num_train, -1) x_val = x_val.reshape(num_val, -1) x_test = x_test.reshape(num_test, -1) # Preprocessing : subtract the mean image # Compute the image mean based on the training data mean_img = np.mean(x_train, axis=0) # (9000,3072) -> (3072) all training data # Subtract x_train -= mean_img x_test -= mean_img x_val -= mean_img return x_train, y_train, x_val, y_val, x_test, y_test
import load_data import tensorflow as tf import numpy as np import matplotlib.pyplot as plt #xtf.reset_default_graph() import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' ####################################################################################################### CIFAR = load_data.load_all() data = CIFAR['data'] label = CIFAR['label'] label = np.asarray(label) CIFAR = load_data.load_test() test_data = CIFAR['data'] test_label = CIFAR['label'] test_label = np.asarray(test_label) ##################################################################################################### num_training = 40000 num_validation = 10000 num_test = 10000 logs_path = '/home/naman/Repositories/CIFAR-10-Recognition/Tensorflow/examples/5' ####################################################################################################### data = np.reshape(data, (num_training + num_validation, 32, 32, 3))
arg = load_data.arg_passing(sys.argv) try: dataset = arg['-data'] dim = int(arg['-dim']) saving = arg['-saving'] dataset_path = '../Dataset/Data/' + dataset + '.pkl.gz' except: saving = 'doc2vec_test' dataset_path = '../Dataset/Data/' + 'kave_1' + '.pkl.gz' dataset_path = '/Users/Morakot/Dropbox/[github]/MSR2018/model-code/dataset/data/kave_1.pkl.gz' dim = 100 train_t, train_d, train_y, valid_t, valid_d, valid_y, test_t, test_d, test_y = load_data.load_all(dataset_path) train_x = [] valid_x = [] test_x = [] analyzedDocument = namedtuple('AnalyzedDocument', 'words tags') def trainDoc2vec(documents): taggeddocuments = [] for i, text in enumerate(documents): # words = str(text) words = ",".join(str(c) for c in text) words = words.split(',') # print words
import matplotlib # Force matplotlib to not use any Xwindows backend. matplotlib.use('Agg') import load_data as loader from svm import SVMclassifier import matplotlib.pyplot as plt import numpy as np plt.rcParams['figure.figsize'] = (10.0, 8.0) # set default size of plots plt.rcParams['image.interpolation'] = 'nearest' plt.rcParams['image.cmap'] = 'gray' data, label = loader.load_all() test_data, test_label = loader.load_test() results = {} best_val = -1 best_svm = None learning_rates = [5e-6] #[1e-6,5e-6,1e-5,7e-5,3e-4,6e-4,1e-3] regularization_strengths = [1000 ] #[0,1,10,1e2,1e3,1e4,1e5,1e6,1e7,1e-1,1e-2,1e-3] batch_sizes = [600] #[32,64,128,150,300,600,1000] for lr in learning_rates: for rs in regularization_strengths: for bs in batch_sizes: model = SVMclassifier() model.add_data(data[:48000], label[:48000], data[48000:], label[48000:], 10) model.InitializePars() model.set_lr(lr) model.set_reg(rs)
import time import numpy as np import torch import torch.nn as nn import torch.optim as optim import torch.utils.data as data from tensorboardX import SummaryWriter import parse import model import config import evaluate import load_data args = parse.args # PREPARE DATASET # train_data, test_data, user_num, item_num, train_mat = load_data.load_all() # construct the train and test datasets train_dataset = load_data.NCFData(train_data, item_num, train_mat, args.num_ng, True) test_dataset = load_data.NCFData(test_data, item_num, train_mat, 0, False) train_loader = data.DataLoader(train_dataset, batch_size=args.batch_size, shuffle=True) test_loader = data.DataLoader(test_dataset, batch_size=args.test_num_ng + 1, shuffle=False) # a batch is a testing user # CREATE MODEL # if config.model == 'NeuMF-pre': # load pretrained model assert os.path.exists(config.GMF_model_path), 'lack of GMF model'
def mean_pred(y_true, y_pred): return K.mean(y_pred) * NORM_F_PRICE * 100 * MILLION def root_mean_squared_error(y_true, y_pred): rmse = K.log(K.abs(y_true) + K.epsilon()) - K.log(K.abs(y_pred) + K.epsilon()) rmse = K.sqrt(K.mean(K.square(rmse), axis=-1)) return rmse if SEED is not None: np.random.seed(SEED) [train_in, train_out, prediction_in] = load_all() input_shape = train_in.shape[1] # Attempt 2 --------------------------------------------------------- model = Sequential() model.add( Dense(20, input_dim=input_shape, kernel_initializer='normal', activation='linear')) model.add(LeakyReLU(alpha=0.15)) model.add(Dense(1, kernel_initializer='normal', activation='linear')) model.add(LeakyReLU(alpha=0.15)) model.compile(loss=root_mean_squared_error, optimizer='rmsprop') # Attempt 1 ---------------------------------------------------------