# Training parameters tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (default: 64)") tf.flags.DEFINE_integer("num_epochs", 50, "Number of training epochs (default: 200)") tf.flags.DEFINE_integer( "evaluate_every", 100, "Evaluate model on dev set after this many steps (default: 100)") tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps (default: 100)") # Misc Parameters tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement") tf.flags.DEFINE_boolean("log_device_placement", True, "Log placement of ops on devices") data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor()) data_loader.define_flags() FLAGS = tf.flags.FLAGS FLAGS(sys.argv) print("\nParameters:") for attr, value in sorted(FLAGS.__flags.items()): print("{}={}".format(attr.upper(), value)) print("") # Data Preparatopn # ================================================== # Load data print("Loading data...") x_train, y_train, x_dev, y_dev = data_loader.prepare_data()
# Parameters # ================================================== # Eval Parameters tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (default: 64)") tf.flags.DEFINE_string("checkpoint_dir", "", "Checkpoint directory from training run") tf.flags.DEFINE_boolean("eval_train", False, "Evaluate on all training data") # Misc Parameters tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement") tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices") data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor()) data_loader.define_flags() FLAGS = tf.flags.FLAGS FLAGS._parse_flags() print("\nParameters:") for attr, value in sorted(FLAGS.__flags.items()): print("{}={}".format(attr.upper(), value)) print("") if FLAGS.eval_train: x_raw, y_test = data_loader.load_data_and_labels() y_test = np.argmax(y_test, axis=1) else: x_raw, y_test = data_loader.load_dev_data_and_labels() y_test = np.argmax(y_test, axis=1)
# -*- coding: utf-8 -*- import os import socket import tensorflow as tf import numpy as np import data_helpers from multi_class_data_loader import MultiClassDataLoader from word_data_processor import WordDataProcessor from config import FLAGS import csv data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor()) data_loader.define_flags() # If no checkpoint_dir exists, extract the most recent dir and set it if FLAGS.checkpoint_dir == "": all_subdirs = ["./runs/" + d for d in os.listdir('./runs/.') if os.path.isdir("./runs/" + d)] latest_subdir = max(all_subdirs, key=os.path.getmtime) FLAGS.checkpoint_dir = latest_subdir + "/checkpoints/" # Map data into vocabulary vocab_path = os.path.join(FLAGS.checkpoint_dir, "..", "vocab") vocab_processor = data_loader.restore_vocab_processor(vocab_path) # Evaluation # ================================================== checkpoint_file = tf.train.latest_checkpoint(FLAGS.checkpoint_dir) graph = tf.Graph() with graph.as_default():
from multi_class_data_loader import MultiClassDataLoader from word_data_processor import WordDataProcessor # Eval Parameters tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (default: 64)") tf.flags.DEFINE_string("checkpoint_dir", "", "Checkpoint directory from training run") tf.flags.DEFINE_boolean("eval_train", False, "Evaluate on all training data") # Misc Parameters tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement") tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices") data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor()) data_loader.define_flags() """ data_loader.define_flags() 메소드 실행할시 코드 self.__flags.DEFINE_string("train_data_file", "./data/kkk.train", "Data source for the training data.") self.__flags.DEFINE_string("dev_data_file", "./data/kkk.dev", "Data source for the cross validation data.") self.__flags.DEFINE_string("class_data_file", "./data/kkk.cls", "Data source for the class list.") """ def eval(input_data): FLAGS = tf.flags.FLAGS FLAGS._parse_flags() print("\nParameters:")
def startTrain(): # Parameters # ================================================== del_all_flags(tf.flags.FLAGS) # Model Hyperparameters tf.flags.DEFINE_integer( "embedding_dim", 128, "Dimensionality of character embedding (default: 128)") tf.flags.DEFINE_string("filter_sizes", "3,4,5", "Comma-separated filter sizes (default: '3,4,5')") tf.flags.DEFINE_integer( "num_filters", 128, "Number of filters per filter size (default: 128)") tf.flags.DEFINE_float("dropout_keep_prob", 0.5, "Dropout keep probability (default: 0.5)") tf.flags.DEFINE_float("l2_reg_lambda", 0.0, "L2 regularizaion lambda (default: 0.0)") # Training parameters tf.flags.DEFINE_integer("batch_size", 128, "Batch Size (default: 64)") tf.flags.DEFINE_integer("num_epochs", 200, "Number of training epochs (default: 200)") tf.flags.DEFINE_integer( "evaluate_every", 100, "Evaluate model on dev set after this many steps (default: 100)") tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps (default: 100)") # Misc Parameters tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement") tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices") data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor()) data_loader.define_flags() FLAGS = tf.flags.FLAGS # FLAGS._parse_flags() FLAGS(sys.argv) print("\nParameters:") for attr, value in sorted(FLAGS.__flags.items()): print("{}={}".format(attr.upper(), value)) print("") # Data Preparatopn # ================================================== # Load data print("Loading data...") x_train, y_train, x_dev, y_dev = data_loader.prepare_data() vocab_processor = data_loader.vocab_processor print("Vocabulary Size: {:d}".format(len(vocab_processor.vocabulary_))) print("Train/Dev split: {:d}/{:d}".format(len(y_train), len(y_dev))) # Training # ================================================== with tf.Graph().as_default(): session_conf = tf.ConfigProto( allow_soft_placement=FLAGS.allow_soft_placement, log_device_placement=FLAGS.log_device_placement) sess = tf.Session(config=session_conf) with sess.as_default(): cnn = TextCNN(sequence_length=x_train.shape[1], num_classes=y_train.shape[1], vocab_size=len(vocab_processor.vocabulary_), embedding_size=FLAGS.embedding_dim, filter_sizes=list( map(int, FLAGS.filter_sizes.split(","))), num_filters=FLAGS.num_filters, l2_reg_lambda=FLAGS.l2_reg_lambda) # Define Training procedure global_step = tf.Variable(0, name="global_step", trainable=False) optimizer = tf.train.AdamOptimizer(1e-3) grads_and_vars = optimizer.compute_gradients(cnn.loss) train_op = optimizer.apply_gradients(grads_and_vars, global_step=global_step) # Keep track of gradient values and sparsity (optional) grad_summaries = [] for g, v in grads_and_vars: if g is not None: grad_hist_summary = tf.summary.histogram( "{}/grad/hist".format(v.name), g) sparsity_summary = tf.summary.scalar( "{}/grad/sparsity".format(v.name), tf.nn.zero_fraction(g)) grad_summaries.append(grad_hist_summary) grad_summaries.append(sparsity_summary) grad_summaries_merged = tf.summary.merge(grad_summaries) # Output directory for models and summaries timestamp = str(int(time.time())) out_dir = os.path.abspath( os.path.join(os.path.curdir, "runs", timestamp)) # out_dir = '/home/taihoinst/icrRest/labelTrain/runs/' + timestamp print("Writing to {}\n".format(out_dir)) # Summaries for loss and accuracy loss_summary = tf.summary.scalar("loss", cnn.loss) acc_summary = tf.summary.scalar("accuracy", cnn.accuracy) # Train Summaries train_summary_op = tf.summary.merge( [loss_summary, acc_summary, grad_summaries_merged]) train_summary_dir = os.path.join(out_dir, "summaries", "train") train_summary_writer = tf.summary.FileWriter( train_summary_dir, sess.graph) # Dev summaries dev_summary_op = tf.summary.merge([loss_summary, acc_summary]) dev_summary_dir = os.path.join(out_dir, "summaries", "dev") dev_summary_writer = tf.summary.FileWriter(dev_summary_dir, sess.graph) # Checkpoint directory. Tensorflow assumes this directory already exists so we need to create it checkpoint_dir = os.path.abspath( os.path.join(out_dir, "checkpoints")) checkpoint_prefix = os.path.join(checkpoint_dir, "model") if not os.path.exists(checkpoint_dir): os.makedirs(checkpoint_dir) saver = tf.train.Saver(tf.global_variables()) # Write vocabulary vocab_processor.save(os.path.join(out_dir, "vocab")) # Initialize all variables sess.run(tf.global_variables_initializer()) def train_step(x_batch, y_batch): """ A single training step """ feed_dict = { cnn.input_x: x_batch, cnn.input_y: y_batch, cnn.dropout_keep_prob: FLAGS.dropout_keep_prob } _, step, summaries, loss, accuracy = sess.run([ train_op, global_step, train_summary_op, cnn.loss, cnn.accuracy ], feed_dict) time_str = datetime.datetime.now().isoformat() print("{}: step {}, loss {:g}, acc {:g}".format( time_str, step, loss, accuracy)) train_summary_writer.add_summary(summaries, step) def dev_step(x_batch, y_batch, writer=None): """ Evaluates model on a dev set """ feed_dict = { cnn.input_x: x_batch, cnn.input_y: y_batch, cnn.dropout_keep_prob: 1.0 } step, summaries, loss, accuracy = sess.run( [global_step, dev_summary_op, cnn.loss, cnn.accuracy], feed_dict) time_str = datetime.datetime.now().isoformat() print("{}: step {}, loss {:g}, acc {:g}".format( time_str, step, loss, accuracy)) if writer: writer.add_summary(summaries, step) # Generate batches batches = data_helpers.batch_iter(list(zip(x_train, y_train)), FLAGS.batch_size, FLAGS.num_epochs) # Training loop. For each batch... for batch in batches: x_batch, y_batch = zip(*batch) train_step(x_batch, y_batch) current_step = tf.train.global_step(sess, global_step) if current_step % FLAGS.evaluate_every == 0: print("\nEvaluation:") dev_step(x_dev, y_dev, writer=dev_summary_writer) print("") if current_step % FLAGS.checkpoint_every == 0: path = saver.save(sess, checkpoint_prefix, global_step=current_step) print("Saved model checkpoint to {}\n".format(path))
def startEval(ocrData): # Parameters # ================================================== del_all_flags(tf.flags.FLAGS) ocrData = json.loads( '[{"location":"1018,240,411,87","text":"APEX"},{"location":"1019,338,409,23","text":"Partner of Choice"},{"location":"1562,509,178,25","text":"Voucher No"},{"location":"1562,578,206,25","text":"Voucher Date"},{"location":"206,691,274,27","text":"4153 Korean Re"},{"location":"208,756,525,34","text":"Proportional Treaty Statement"},{"location":"1842,506,344,25","text":"BV/HEO/2018/05/0626"},{"location":"1840,575,169,25","text":"01105/2018"},{"location":"206,848,111,24","text":"Cedant"},{"location":"206,908,285,24","text":"Class of Business"},{"location":"210,963,272,26","text":"Period of Quarter"},{"location":"207,1017,252,31","text":"Period of Treaty"},{"location":"206,1066,227,24","text":"Our Reference"},{"location":"226,1174,145,31","text":"Currency"},{"location":"227,1243,139,24","text":"Premium"},{"location":"226,1303,197,24","text":"Commission"},{"location":"226,1366,107,24","text":"Claims"},{"location":"227,1426,126,24","text":"Reserve"},{"location":"227,1489,123,24","text":"Release"},{"location":"227,1549,117,24","text":"Interest"},{"location":"227,1609,161,31","text":"Brokerage"},{"location":"233,1678,134,24","text":"Portfolio"},{"location":"227,1781,124,24","text":"Balance"},{"location":"574,847,492,32","text":": Solidarity- First Insurance 2018"},{"location":"574,907,568,32","text":": Marine Cargo Surplus 2018 - Inward"},{"location":"598,959,433,25","text":"01-01-2018 TO 31-03-2018"},{"location":"574,1010,454,25","text":": 01-01-2018 TO 31-12-2018"},{"location":"574,1065,304,25","text":": APEX/BORD/2727"},{"location":"629,1173,171,25","text":"JOD 1.00"},{"location":"639,1239,83,25","text":"25.53"},{"location":"639,1299,64,25","text":"5.74"},{"location":"639,1362,64,25","text":"0.00"},{"location":"639,1422,64,25","text":"7.66"},{"location":"639,1485,64,25","text":"0.00"},{"location":"639,1545,64,25","text":"0.00"},{"location":"639,1605,64,25","text":"0.64"},{"location":"648,1677,64,25","text":"0.00"},{"location":"641,1774,81,25","text":"11 .49"},{"location":"1706,1908,356,29","text":"APEX INSURANCE"}]' ) # print('============startEval================') # ocrData = json.loads(ocrData) # print(ocrData) # Eval Parameters tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (default: 64)") tf.flags.DEFINE_string("checkpoint_dir", "", "Checkpoint directory from training run") tf.flags.DEFINE_boolean("eval_train", False, "Evaluate on all training data") # Misc Parameters tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement") tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices") data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor()) data_loader.define_flags() FLAGS = tf.flags.FLAGS # FLAGS._parse_flags() FLAGS(sys.argv) print("\nParameters:") for attr, value in sorted(FLAGS.__flags.items()): print("{}={}".format(attr.upper(), value)) print("") if FLAGS.eval_train: x_raw, y_test = data_loader.load_data_and_labels() y_test = np.argmax(y_test, axis=1) else: # x_raw, y_test = data_loader.load_dev_data_and_labels() x_raw, y_test = data_loader.load_dev_data_and_labels_json(ocrData) y_test = np.argmax(y_test, axis=1) # checkpoint_dir이 없다면 가장 최근 dir 추출하여 셋팅 if FLAGS.checkpoint_dir == "": all_subdirs = [ "./runs/" + d for d in os.listdir('./runs/.') if os.path.isdir("./runs/" + d) ] latest_subdir = max(all_subdirs, key=os.path.getmtime) FLAGS.checkpoint_dir = latest_subdir + "/checkpoints/" # Map data into vocabulary vocab_path = os.path.join(FLAGS.checkpoint_dir, "..", "vocab") vocab_processor = data_loader.restore_vocab_processor(vocab_path) x_test = np.array(list(vocab_processor.transform(x_raw))) print("\nEvaluating...\n") # Evaluation # ================================================== checkpoint_file = tf.train.latest_checkpoint(FLAGS.checkpoint_dir) graph = tf.Graph() with graph.as_default(): session_conf = tf.ConfigProto( allow_soft_placement=FLAGS.allow_soft_placement, log_device_placement=FLAGS.log_device_placement) sess = tf.Session(config=session_conf) with sess.as_default(): # Load the saved meta graph and restore variables saver = tf.train.import_meta_graph( "{}.meta".format(checkpoint_file)) saver.restore(sess, checkpoint_file) # Get the placeholders from the graph by name input_x = graph.get_operation_by_name("input_x").outputs[0] # input_y = graph.get_operation_by_name("input_y").outputs[0] dropout_keep_prob = graph.get_operation_by_name( "dropout_keep_prob").outputs[0] # Tensors we want to evaluate predictions = graph.get_operation_by_name( "output/predictions").outputs[0] # Generate batches for one epoch batches = data_helpers.batch_iter(list(x_test), FLAGS.batch_size, 1, shuffle=False) # Collect the predictions here all_predictions = [] for x_test_batch in batches: batch_predictions = sess.run(predictions, { input_x: x_test_batch, dropout_keep_prob: 1.0 }) all_predictions = np.concatenate( [all_predictions, batch_predictions]) # Print accuracy if y_test is defined if y_test is not None: correct_predictions = float(sum(all_predictions == y_test)) print("Total number of test examples: {}".format(len(y_test))) print("Accuracy: {:g}".format(correct_predictions / float(len(y_test)))) # Save the evaluation to a csv class_predictions = data_loader.class_labels(all_predictions.astype(int)) predictions_human_readable = np.column_stack( (np.array(x_raw), class_predictions)) out_path = os.path.join(FLAGS.checkpoint_dir, "../../../", "prediction.csv") print("Saving evaluation to {0}".format(out_path)) for i in predictions_human_readable: for row in ocrData: if i[0].lower() == row['text'].lower(): row['colLbl'] = i[1] print(ocrData) return ocrData
tf.flags.DEFINE_integer("num_epochs", 500, "Number of training epochs (default: 200)") tf.flags.DEFINE_integer("evaluate_every", 100, "Evaluate model on dev set after this many steps (default: 100)") tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps (default: 100)") tf.flags.DEFINE_string("activation_function", "relu", "select activation_function (default: 'relu'), leaky_relu, elu, swish") tf.flags.DEFINE_boolean("batch_normalization", False, "Do batch normalization") # Misc Parameters tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement") tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices") # how many stay epoch when increase loss or decrease accuracy epoch_1 = 4000# 1epoch=2000steps stay_epochs = 2.5 save_npy = True _gap = 10000 data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor()) data_loader.define_flags() FLAGS = tf.flags.FLAGS FLAGS.mark_as_parsed() print("\nParameters:") p_param = list() for attr, value in sorted(FLAGS.flag_values_dict().items()): print("{}={}".format(attr.upper(), value)) p_param.append('{}={}'.format(attr.upper(), value)) print("") # Data Preparatopn # ================================================== # Load data
# Eval Parameters tf.flags.DEFINE_integer("batch_size", 256, "Batch Size (default: 64)") # tf.flags.DEFINE_string("checkpoint_dir", "./runs/1509332332/checkpoints/", "") # tf.flags.DEFINE_string("checkpoint_dir", "./runs/1510118340/checkpoints/", "") tf.flags.DEFINE_string("checkpoint_dir", "", "Checkpoint directory from training run") tf.flags.DEFINE_boolean("eval_train", False, "Evaluate on all training data") # Misc Parameters tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement") tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices") data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor()) data_loader.define_flags() FLAGS = tf.flags.FLAGS FLAGS._parse_flags() print("\nParameters:") for attr, value in sorted(FLAGS.__flags.items()): print("{}={}".format(attr.upper(), value)) print("") if FLAGS.eval_train: x_raw, y_test = data_loader.load_data_and_labels() y_test = np.argmax(y_test, axis=1) else: x_raw, y_test = data_loader.load_dev_data_and_labels() y_test = np.argmax(y_test, axis=1)