MODEL_DIR = '/content/imagenet-vgg-f.mat' DATA_DIR = '/content/mirflickr25k.mat' phase = 'train' checkpoint_dir = './checkpoint' Savecode = './Savecode' dataset_dir = 'Flickr' netStr = 'alex' SEMANTIC_EMBED = 512 MAX_ITER = 100 batch_size = 128 image_size = 224 images, tags, labels = loading_data(DATA_DIR) dimTxt = tags.shape[1] dimLab = labels.shape[1] DATABASE_SIZE = 18015 TRAINING_SIZE = 10000 QUERY_SIZE = 2000 VERIFICATION_SIZE = 1000 X, Y, L = split_data(images, tags, labels, QUERY_SIZE, TRAINING_SIZE, DATABASE_SIZE) train_L = L['train'] train_x = X['train'] train_y = Y['train'] query_L = L['query'] query_x = X['query']
# Adding parameters from other python files
# parser = add_parms_supervised(parser)
parser = add_params_data(parser)
parser = add_params_report(parser)
parser = add_params_noise(parser)
# parser = add_params_mt(parser)
args = parser.parse_args()
# lr=0.0001
# epochs=30
# batch_size= 64
# #for mean teacher
# ratio =0.5
# alpha=0.99 #(0.90-0.99)
# maxlen=100
x_train, y_train, x_test, y_test, x_unlabel = loading_data(args)
x_train, x_test, x_unlabel, vocab_size, tokenizer = tokenization(
args, x_train, x_test, x_unlabel, args.maxlen)
for i in range(0, 1):
x_train, y_train, x_test, y_test = Kfold_crossvalidation(
args, x_train, y_train, x_test, y_test)
print("train Data_Size:", np.shape(x_train))
print("test Data_Size:", np.shape(x_test))
print('Train Label count: True, Fake', np.count_nonzero(y_train == 1),
np.count_nonzero(y_train == 0))
print('Test Label count : True, Fake', np.count_nonzero(y_test == 1),
np.count_nonzero(y_test == 0))
# train_supervised(epochs, batch_size, lr,x_train, y_train, x_test, y_test,maxlen,vocab_size)