def load_dkf(dataset, runme_path, conf_path, weight_path): # This is pretty much just copied from train.py. Mostly voodoo. params = parse_dkf_args(runme_path, conf_path, weight_path) # Add dataset and NADE parameters, which will become part of the model for k in ['dim_observations', 'data_type']: params[k] = dataset[k] if params['use_nade']: params['data_type'] = 'real_nade' # Remove from params removeIfExists('./NOSUCHFILE') reloadFile = params.pop('reloadFile') pfile = params.pop('paramFile') assert os.path.exists(pfile), pfile + ' not found. Need paramfile' dkf = DKF(params, paramFile=pfile, reloadFile=reloadFile) return dkf
mapPrint('Options: ', params) if params['use_nade']: params['data_type'] = 'binary_nade' """ import DKF + learn/evaluate functions """ start_time = time.time() from stinfmodel.dkf import DKF import stinfmodel.learning as DKF_learn import stinfmodel.evaluate as DKF_evaluate displayTime('import DKF', start_time, time.time()) dkf = None #Remove from params start_time = time.time() removeIfExists('./NOSUCHFILE') reloadFile = params.pop('reloadFile') """ Reload parameters if reloadFile exists otherwise setup model from scratch and initialize parameters randomly. """ if os.path.exists(reloadFile): pfile = params.pop('paramFile') """ paramFile is set inside the BaseClass in theanomodels to point to the pickle file containing params""" assert os.path.exists(pfile), pfile + ' not found. Need paramfile' print 'Reloading trained model from : ', reloadFile print 'Assuming ', pfile, ' corresponds to model' dkf = DKF(params, paramFile=pfile, reloadFile=reloadFile) else: pfile = params['savedir'] + '/' + params['unique_id'] + '-config.pkl' print 'Training model from scratch. Parameters in: ', pfile