import numpy as np from math import sqrt from sklearn.metrics import r2_score from sklearn.metrics import mean_squared_error from sklearn.metrics import accuracy_score from sklearn import metrics from model_OCD import OCD import checkmate as cm import data_helpers as dh # Parameters # ================================================== logger = dh.logger_fn( "tflog", "logs/training_kfold_{0}_{1}_time_{2}.log".format(sys.argv[1], sys.argv[0], int(time.time()))) kfold = int(sys.argv[1]) batch_size = int(sys.argv[2]) tf.compat.v1.flags.DEFINE_float("learning_rate", 0.001, "Learning rate") tf.compat.v1.flags.DEFINE_float("keep_prob", 0.5, "Keep probability for dropout") tf.compat.v1.flags.DEFINE_integer("hidden_size", 256, "The number of hidden nodes (Integer)") tf.compat.v1.flags.DEFINE_integer("evaluation_interval", 1, "Evaluate and print results every x epochs") tf.compat.v1.flags.DEFINE_integer("batch_size", batch_size, "Batch size for training.") tf.compat.v1.flags.DEFINE_integer("epochs", 6,
while not (TRAIN_OR_RESTORE.isalpha() and TRAIN_OR_RESTORE.upper() in ['T', 'R']): TRAIN_OR_RESTORE = input('✘ The format of your input is illegal, please re-input: ') logging.info('✔︎ The format of your input is legal, now loading to next step...') TRAIN_OR_RESTORE = TRAIN_OR_RESTORE.upper() CLASS_BIND = input("☛ Use Class Bind or Not?(Y/N) \n") while not (CLASS_BIND.isalpha() and CLASS_BIND.upper() in ['Y', 'N']): CLASS_BIND = input('✘ The format of your input is illegal, please re-input: ') logging.info('✔︎ The format of your input is legal, now loading to next step...') CLASS_BIND = CLASS_BIND.upper() if TRAIN_OR_RESTORE == 'T': logger = data_helpers.logger_fn('tflog', 'training-{}.log'.format(time.asctime())) if TRAIN_OR_RESTORE == 'R': logger = data_helpers.logger_fn('tflog', 'restore-{}.log'.format(time.asctime())) TRAININGSET_DIR = '../Train.json' VALIDATIONSET_DIR = '../Validation_bind.json' # Data loading params tf.flags.DEFINE_string("training_data_file", TRAININGSET_DIR, "Data source for the training data.") tf.flags.DEFINE_string("validation_data_file", VALIDATIONSET_DIR, "Data source for the validation data.") tf.flags.DEFINE_string("train_or_restore", TRAIN_OR_RESTORE, "Train or Restore.") tf.flags.DEFINE_string("use_classbind_or_not", CLASS_BIND, "Use the class bind info or not.") # Model Hyperparameterss tf.flags.DEFINE_float("learning_rate", 0.001, "The learning rate (default: 0.001)") tf.flags.DEFINE_integer("pad_seq_len", 150, "Recommand padding Sequence length of data (depends on the data)")
# -*- coding:utf-8 -*- import os import sys import time import tensorflow as tf import data_helpers as dh # Parameters # ================================================== logger = dh.logger_fn('tflog', 'logs/test-{0}.log'.format(time.asctime())) # Data Parameters tf.flags.DEFINE_string("training_data_file", "./data/train_data_set.txt", "Data source for the training data.") tf.flags.DEFINE_string("validation_data_file", "./data/val_data_set.txt", "Data source for the validation data") tf.flags.DEFINE_string("test_data_file", "./data/test_data_set.txt", "Data source for the test data") tf.flags.DEFINE_string("checkpoint_dir", "./", "Checkpoint directory from training run") # tf.flags.DEFINE_string("vocab_data_file", "./", "Vocabulary file") # Model Hyperparameters # tf.flags.DEFINE_integer("pad_seq_len", 100, "Recommended padding Sequence length of data (depends on the data)") tf.flags.DEFINE_integer( "embedding_dim", 128, "Dimensionality of character embedding (default: 128)") tf.flags.DEFINE_integer("embedding_type", 1, "The embedding type (default: 1)") tf.flags.DEFINE_integer(
# -*- coding:utf-8 -*- import os import time import numpy as np import tensorflow as tf import data_helpers # Parameters # ================================================== logger = data_helpers.logger_fn('tflog', 'test-{}.log'.format(time.asctime())) MODEL = input( "☛ Please input the model file you want to test, it should be like(1490175368): " ) while not (MODEL.isdigit() and len(MODEL) == 10): MODEL = input( '✘ The format of your input is illegal, it should be like(1490175368), please re-input: ' ) logger.info( '✔︎ The format of your input is legal, now loading to next step...') CLASS_BIND = input("☛ Use Class Bind or Not?(Y/N) \n") while not (CLASS_BIND.isalpha() and CLASS_BIND.upper() in ['Y', 'N']): CLASS_BIND = input( '✘ The format of your input is illegal, please re-input: ') logger.info( '✔︎ The format of your input is legal, now loading to next step...')
from batch_loader import BatchLoader, MulBatchLoader # Parameters # ================================================== # TRAIN_OR_RESTORE = input("☛ Train or Restore?(T/R) \n") TRAIN_OR_RESTORE = "T" while not (TRAIN_OR_RESTORE.isalpha() and TRAIN_OR_RESTORE.upper() in ['T', 'R']): TRAIN_OR_RESTORE = input('✘ The format of your input is illegal, please re-input: ') logging.info('✔︎ The format of your input is legal, now loading to next step...') TRAIN_OR_RESTORE = TRAIN_OR_RESTORE.upper() if TRAIN_OR_RESTORE == 'T': logger = dh.logger_fn('tflog', 'logs/training-{0}.log'.format(time.asctime())) if TRAIN_OR_RESTORE == 'R': logger = dh.logger_fn('tflog', 'logs/restore-{0}.log'.format(time.asctime())) TRAININGSET_DIR = '../data/Train.json' VALIDATIONSET_DIR = '../data/Validation.json' METADATA_DIR = '../data/metadata.tsv' parser = argparse.ArgumentParser(description="Training CNN") parser.add_argument("--training_data_file", type=str, default=TRAININGSET_DIR, help="Data source for the training data.") parser.add_argument("--validation_data_file", type=str, default=VALIDATIONSET_DIR, help="Data source for the validation data.") parser.add_argument("--metadata_file", type=str, default=METADATA_DIR, help="Metadata file for embedding visualization(Each line is a word segment in metadata_file).") parser.add_argument("--train_or_restore", type=str, default=TRAIN_OR_RESTORE, help="Train or Restore.") parser.add_argument("--data_path", type=str, default="data/train_snli.txt", help="Data path.") parser.add_argument("--pad_seq_len", type=int, default=120, help="Recommended padding Sequence length of data (depends on the data)")
import data_helpers as dh # Parameters # ================================================== TRAIN_OR_RESTORE = 'T' #input("Train or Restore?(T/R): ") while not (TRAIN_OR_RESTORE.isalpha() and TRAIN_OR_RESTORE.upper() in ['T', 'R']): TRAIN_OR_RESTORE = input("The format of your input is illegal, please re-input: ") logging.info("The format of your input is legal, now loading to next step...") TRAIN_OR_RESTORE = TRAIN_OR_RESTORE.upper() if TRAIN_OR_RESTORE == 'T': logger = dh.logger_fn("tflog", "logs/training_kfold_{0}_{1}_time_{2}.log".format(sys.argv[1], sys.argv[0], int(time.time()))) if TRAIN_OR_RESTORE == 'R': logger = dh.logger_fn("tflog", "logs/restore-{0}.log".format(time.asctime()).replace(':', '_')) kfold= int(sys.argv[1]) batch_size = int(sys.argv[2]) tf.compat.v1.flags.DEFINE_string("train_or_restore", TRAIN_OR_RESTORE, "Train or Restore.") tf.compat.v1.flags.DEFINE_float("learning_rate", 0.001, "Learning rate") tf.compat.v1.flags.DEFINE_float("norm_ratio", 5, "The ratio of the sum of gradients norms of trainable variable (default: 1.25)") tf.compat.v1.flags.DEFINE_float("keep_prob", 0.5, "Keep probability for dropout") tf.compat.v1.flags.DEFINE_float("radio", 0.6, "split radio") tf.compat.v1.flags.DEFINE_integer("hidden_size", 256, "The number of hidden nodes (Integer)") tf.compat.v1.flags.DEFINE_integer("evaluation_interval", 1, "Evaluate and print results every x epochs") tf.compat.v1.flags.DEFINE_integer("batch_size", batch_size , "Batch size for training.") tf.compat.v1.flags.DEFINE_integer("epochs", 3, "Number of epochs to train for.") tf.compat.v1.flags.DEFINE_integer("kfold", kfold, "Number of epochs to train for.")
import numpy as np import pandas as pd import tensorflow as tf from sklearn import metrics from math import sqrt from sklearn.metrics import r2_score from sklearn.metrics import mean_squared_error import checkmate as cmm import data_helpers as dh import json # Parameters # ================================================== #seq_len= int(sys.argv[1]) #batch_size = int(sys.argv[2]) logger = dh.logger_fn( "tflog", "logs/test-{0}.log".format(time.asctime()).replace(':', '_')) number = sys.argv[1] file_name = sys.argv[2] MODEL = file_name while not (MODEL.isdigit() and len(MODEL) == 10): MODEL = input( "The format of your input is illegal, it should be like(90175368), please re-input: " ) logger.info("The format of your input is legal, now loading to next step...") TESTSET_DIR = 'data/assist2009_updated_all.csv' MODEL_DIR = 'runs/' + MODEL + '/checkpoints/' BEST_MODEL_DIR = 'runs/' + MODEL + '/bestcheckpoints/' SAVE_DIR = 'results/' + MODEL