from deepbelief.layers import gplvm from deepbelief.plotting import LatentPointPlotter from deepbelief.plotting import LatentSamplePlotter from deepbelief.util import init_logging # Import local flags.py module without specifying absolute path import importlib.util module_spec = importlib.util.spec_from_file_location('flags', 'flags.py') module = importlib.util.module_from_spec(module_spec) module_spec.loader.exec_module(module) flags = module.flags # Note, this script will train the model and create an output folder containing # checkpoint files and a summary for TensorBoard. init_logging(flags['training_log_file']) lp_plotter = LatentPointPlotter(xlim=flags['xlim'], ylim=flags['ylim'], delta=flags['delta_lp'], output_dir=flags['latent_points_dir'], fig_ext=flags['lp_plotter_fig_ext']) ls_plotter = LatentSamplePlotter( image_shape=flags['img_shape'], xlim=flags['xlim'], ylim=flags['ylim'], delta=flags['delta_ls'], num_samples_to_average=flags['num_samples_to_average'], output_dir=flags['latent_samples_dir'])
# Import local flags.py module without specifying absolute path import importlib.util module_spec = importlib.util.spec_from_file_location('flags', 'flags.py') module = importlib.util.module_from_spec(module_spec) module_spec.loader.exec_module(module) flags = module.flags # Note, this script should be run after the model is trained (run train.py first). # Basically, the generalisation experiment consist in trying to "reconstruct" the # test data as closely as possible. The output of this script will be two Numpy arrays, # one simply containing the test data and the other one the corresponding data generated # by the model. init_logging(flags['test_log_file']) test_data = Data(flags['test_data'], shuffle_first=False, batch_size=flags['test_generalisation_batch_size'], log_epochs=flags['data_log_epochs'], name='TestData') test_data_batch = test_data.next_batch() config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True)) session = tf.Session(config=config) layer1 = SBM_Lower(session=session, side=flags['img_shape'][0], side_overlap=flags['layer_1_side_overlap'],