def main(_): tf.logging.set_verbosity(tf.logging.INFO) tokenizer = tokenization.FullTokenizer(vocab_file=FLAGS.vocab_file, do_lower_case=FLAGS.do_lower_case) input_files = [] for input_pattern in FLAGS.input_file.split(","): input_files.extend(tf.gfile.Glob(input_pattern)) tf.logging.info("*** Reading from input files ***") for input_file in input_files: tf.logging.info(" %s", input_file) rng = random.Random(FLAGS.random_seed) instances = create_training_instances(input_files, tokenizer, FLAGS.max_seq_length, FLAGS.dupe_factor, FLAGS.short_seq_prob, FLAGS.masked_lm_prob, FLAGS.max_predictions_per_seq, rng) output_files = FLAGS.output_file.split(",") tf.logging.info("*** Writing to output files ***") for output_file in output_files: tf.logging.info(" %s", output_file) write_instance_to_example_files(instances, tokenizer, FLAGS.max_seq_length, FLAGS.max_predictions_per_seq, output_files)
def main(_): tf.logging.set_verbosity(tf.logging.INFO) if not FLAGS.do_train and not FLAGS.do_eval and not FLAGS.do_predict: raise ValueError( "At least one of `do_train`, `do_eval` or `do_predict' must be True." ) bert_config = modeling.BertConfig.from_json_file(FLAGS.bert_config_file) if FLAGS.max_seq_length > bert_config.max_position_embeddings: raise ValueError( "Cannot use sequence length %d because the BERT model " "was only trained up to sequence length %d" % (FLAGS.max_seq_length, bert_config.max_position_embeddings)) tf.gfile.MakeDirs(FLAGS.output_dir) processor = SIQAProcessor(variant=FLAGS.variant) label_list = processor.get_labels() tokenizer = tokenization.FullTokenizer(vocab_file=FLAGS.vocab_file, do_lower_case=FLAGS.do_lower_case) tpu_cluster_resolver = None if FLAGS.use_tpu and FLAGS.tpu_name: tpu_cluster_resolver = tf.contrib.cluster_resolver.TPUClusterResolver( FLAGS.tpu_name, zone=FLAGS.tpu_zone, project=FLAGS.gcp_project) is_per_host = tf.contrib.tpu.InputPipelineConfig.PER_HOST_V2 run_config = tf.contrib.tpu.RunConfig( cluster=tpu_cluster_resolver, master=FLAGS.master, model_dir=FLAGS.output_dir, save_checkpoints_steps=FLAGS.save_checkpoints_steps, tpu_config=tf.contrib.tpu.TPUConfig( iterations_per_loop=FLAGS.iterations_per_loop, num_shards=FLAGS.num_tpu_cores, per_host_input_for_training=is_per_host)) train_examples = None num_train_steps = None num_warmup_steps = None if FLAGS.do_train: train_examples = processor.get_train_examples(FLAGS.data_dir) num_train_steps = int( len(train_examples) / FLAGS.train_batch_size * FLAGS.num_train_epochs) num_warmup_steps = int(num_train_steps * FLAGS.warmup_proportion) model_fn = model_fn_builder(bert_config=bert_config, num_labels=len(label_list), init_checkpoint=FLAGS.init_checkpoint, learning_rate=FLAGS.learning_rate, num_train_steps=num_train_steps, num_warmup_steps=num_warmup_steps, use_tpu=FLAGS.use_tpu, use_one_hot_embeddings=FLAGS.use_tpu) # If TPU is not available, this will fall back to normal Estimator on CPU # or GPU. estimator = tf.contrib.tpu.TPUEstimator( use_tpu=FLAGS.use_tpu, model_fn=model_fn, config=run_config, train_batch_size=FLAGS.train_batch_size, eval_batch_size=FLAGS.eval_batch_size, predict_batch_size=FLAGS.predict_batch_size) if FLAGS.do_train: train_file = os.path.join(FLAGS.output_dir, "train.tf_record") train_seq_length = file_based_convert_examples_to_features( train_examples, label_list, FLAGS.max_seq_length, tokenizer, train_file) tf.logging.info("***** Running training *****") tf.logging.info(" Num examples = %d", len(train_examples)) tf.logging.info(" Batch size = %d", FLAGS.train_batch_size) tf.logging.info(" Num steps = %d", num_train_steps) tf.logging.info(" Longest training sequence = %d", train_seq_length) train_input_fn = file_based_input_fn_builder( input_file=train_file, seq_length=FLAGS.max_seq_length, is_training=True, drop_remainder=True) estimator.train(input_fn=train_input_fn, max_steps=num_train_steps) if FLAGS.do_eval: eval_examples = processor.get_dev_examples(FLAGS.data_dir) eval_file = os.path.join(FLAGS.output_dir, "eval.tf_record") eval_seq_length = file_based_convert_examples_to_features( eval_examples, label_list, FLAGS.max_seq_length, tokenizer, eval_file) tf.logging.info("***** Running evaluation *****") tf.logging.info(" Num examples = %d", len(eval_examples)) tf.logging.info(" Batch size = %d", FLAGS.eval_batch_size) tf.logging.info(" Longest eval sequence = %d", eval_seq_length) # This tells the estimator to run through the entire set. eval_steps = None # However, if running eval on the TPU, you will need to specify the # number of steps. if FLAGS.use_tpu: # Eval will be slightly WRONG on the TPU because it will truncate # the last batch. eval_steps = int(len(eval_examples) / FLAGS.eval_batch_size) eval_drop_remainder = True if FLAGS.use_tpu else False eval_input_fn = file_based_input_fn_builder( input_file=eval_file, seq_length=FLAGS.max_seq_length, is_training=False, drop_remainder=eval_drop_remainder) result = estimator.evaluate(input_fn=eval_input_fn, steps=eval_steps) output_eval_file = os.path.join(FLAGS.output_dir, "eval_results.txt") with tf.gfile.GFile(output_eval_file, "w") as writer: tf.logging.info("***** Eval results *****") for key in sorted(result.keys()): tf.logging.info(" %s = %s", key, str(result[key])) writer.write("%s = %s\n" % (key, str(result[key]))) if FLAGS.do_predict: predict_examples = processor.get_test_examples(FLAGS.data_dir) predict_file = os.path.join(FLAGS.output_dir, "predict.tf_record") predict_seq_length = file_based_convert_examples_to_features( predict_examples, label_list, FLAGS.max_seq_length, tokenizer, predict_file) tf.logging.info("***** Running prediction*****") tf.logging.info(" Num examples = %d", len(predict_examples)) tf.logging.info(" Batch size = %d", FLAGS.predict_batch_size) tf.logging.info(" Longest predict sequence = %d", predict_seq_length) if FLAGS.use_tpu: # Warning: According to tpu_estimator.py Prediction on TPU is an # experimental feature and hence not supported here raise ValueError("Prediction in TPU not supported") predict_drop_remainder = True if FLAGS.use_tpu else False predict_input_fn = file_based_input_fn_builder( input_file=predict_file, seq_length=FLAGS.max_seq_length, is_training=False, drop_remainder=predict_drop_remainder) result = estimator.predict(input_fn=predict_input_fn) test_predictions_file = os.path.join(FLAGS.output_dir, "test_results.csv") with tf.gfile.GFile(test_predictions_file, "w") as writer: tf.logging.info("***** Predict results *****") for example, prediction in zip(predict_examples, result): output_line = ",".join([ str(example.qid), str(SIQAProcessor.LABELS[np.argmax(prediction)]) ] + [ str(class_probability) for class_probability in prediction ]) + "\n" writer.write(output_line)
def main_run_classifier(_, config_str, train_batch_size, learning_rate, num_train_epochs): tf.logging.set_verbosity(tf.logging.INFO) processors = { "cola": ColaProcessor, "stsb": STSBProcessor, } if not FLAGS.do_train and not FLAGS.do_eval and not FLAGS.do_predict: raise ValueError( "At least one of `do_train`, `do_eval` or `do_predict' must be True.") bert_config = modeling.BertConfig.from_json_file(FLAGS.bert_config_file) if FLAGS.max_seq_length > bert_config.max_position_embeddings: raise ValueError( "Cannot use sequence length %d because the BERT model " "was only trained up to sequence length %d" % (FLAGS.max_seq_length, bert_config.max_position_embeddings)) output_dir = FLAGS.output_dir + "_" + config_str tf.gfile.MakeDirs(output_dir) task_name = FLAGS.task_name.lower() if task_name not in processors: raise ValueError("Task not found: %s" % (task_name)) processor = processors[task_name]() #label_list = processor.get_labels() label_list = None tokenizer = tokenization.FullTokenizer( vocab_file=FLAGS.vocab_file, do_lower_case=FLAGS.do_lower_case) tpu_cluster_resolver = None if FLAGS.use_tpu and FLAGS.tpu_name: tpu_cluster_resolver = tf.contrib.cluster_resolver.TPUClusterResolver( FLAGS.tpu_name, zone=FLAGS.tpu_zone, project=FLAGS.gcp_project) is_per_host = tf.contrib.tpu.InputPipelineConfig.PER_HOST_V2 run_config = tf.contrib.tpu.RunConfig( cluster=tpu_cluster_resolver, master=FLAGS.master, model_dir=output_dir, save_checkpoints_steps=FLAGS.save_checkpoints_steps, keep_checkpoint_max=3, tpu_config=tf.contrib.tpu.TPUConfig( iterations_per_loop=FLAGS.iterations_per_loop, num_shards=FLAGS.num_tpu_cores, per_host_input_for_training=is_per_host)) train_examples = None num_train_steps = None num_warmup_steps = None if FLAGS.do_train: train_examples = processor.get_train_examples(FLAGS.data_dir) num_train_steps = int( len(train_examples) / train_batch_size * num_train_epochs) num_warmup_steps = int(num_train_steps * FLAGS.warmup_proportion) model_fn = model_fn_builder( bert_config=bert_config, #num_labels=len(label_list), init_checkpoint=FLAGS.init_checkpoint, learning_rate=learning_rate, num_train_steps=num_train_steps, num_warmup_steps=num_warmup_steps, use_tpu=FLAGS.use_tpu, use_one_hot_embeddings=FLAGS.use_tpu) # If TPU is not available, this will fall back to normal Estimator on CPU # or GPU. estimator = tf.contrib.tpu.TPUEstimator( use_tpu=FLAGS.use_tpu, model_fn=model_fn, config=run_config, train_batch_size=train_batch_size, eval_batch_size=FLAGS.eval_batch_size, predict_batch_size=FLAGS.predict_batch_size) if FLAGS.do_train: train_file = os.path.join(output_dir, "train.tf_record") file_based_convert_examples_to_features( train_examples, FLAGS.max_seq_length, tokenizer, train_file) tf.logging.info("***** Running training *****") tf.logging.info(" Num examples = %d", len(train_examples)) tf.logging.info(" Batch size = %d", train_batch_size) tf.logging.info(" Num steps = %d", num_train_steps) train_input_fn = file_based_input_fn_builder( input_file=train_file, seq_length=FLAGS.max_seq_length, is_training=True, drop_remainder=True) if FLAGS.do_early_stopping: assert(FLAGS.do_eval == False) raise NotImplementedError # eval_examples = processor.get_dev_examples(FLAGS.data_dir) # eval_file = os.path.join(output_dir, "eval.tf_record") # file_based_convert_examples_to_features(eval_examples, FLAGS.max_seq_length, tokenizer, eval_file) # # eval_hook_listener = EvalRoutineCheckpointSaverListener(model_dir=output_dir, # path_eval_script=c.PATH_EVAL_SCRIPT, # server=c.DEV_SERVER, # gpu_fraction=c.DEV_CUDA_GPU_FRAC, # cuda_visible_devices=c.DEV_CUDA_VISIBLE_DEVICES, # params={}, # input_file=eval_file, # bert_config_file=FLAGS.bert_config_file, # eval_batch_size=FLAGS.eval_batch_size, # max_sequence_length=FLAGS.max_seq_length, # model_fn=model_fn_builder, # input_fn=file_based_input_fn_builder, # ) # #num_labels=len(processor.get_labels())) # # estimator.train(input_fn=train_input_fn, max_steps=num_train_steps, # saving_listeners=[eval_hook_listener], hooks=[eval_hook_listener]) # # # # Now lets run the evaluation again, but in another output dir # best_checkpoint = checkmate.get_best_checkpoint(output_dir + "/eval/best_model/", select_maximum_value=False) # # model_fn = model_fn_builder(bert_config=bert_config, # init_checkpoint=best_checkpoint, # learning_rate=0.0, # num_train_steps=0, # num_warmup_steps=0, # #num_labels=len(label_list), # use_one_hot_embeddings=True, # use_tpu=False) # # run_config = tf.contrib.tpu.RunConfig( # cluster=None, # master=None, # model_dir=output_dir + "/final", # tpu_config=None # ) # # estimator = tf.contrib.tpu.TPUEstimator( # use_tpu=False, # model_fn=model_fn, # config=run_config, # train_batch_size=train_batch_size, # eval_batch_size=FLAGS.eval_batch_size, # predict_batch_size=FLAGS.predict_batch_size) # # eval_input_fn = file_based_input_fn_builder( # input_file=eval_file, # seq_length=FLAGS.max_seq_length, # is_training=False, # drop_remainder=False) # # result = estimator.evaluate(input_fn=eval_input_fn, steps=None) # # output_eval_file = os.path.join(output_dir + "/final", "eval_results.txt") # with tf.gfile.GFile(output_eval_file, "w") as writer: # tf.logging.info("***** Eval results *****") # for key in sorted(result.keys()): # tf.logging.info(" %s = %s", key, str(result[key])) # writer.write("%s = %s\n" % (key, str(result[key]))) else: estimator.train(input_fn=train_input_fn, max_steps=num_train_steps) if FLAGS.do_eval: eval_examples = processor.get_dev_examples(FLAGS.data_dir) eval_file = os.path.join(output_dir, "eval.tf_record") file_based_convert_examples_to_features( eval_examples, FLAGS.max_seq_length, tokenizer, eval_file) tf.logging.info("***** Running evaluation *****") tf.logging.info(" Num examples = %d", len(eval_examples)) tf.logging.info(" Batch size = %d", FLAGS.eval_batch_size) # This tells the estimator to run through the entire set. eval_steps = None # However, if running eval on the TPU, you will need to specify the # number of steps. if FLAGS.use_tpu: # Eval will be slightly WRONG on the TPU because it will truncate # the last batch. eval_steps = int(len(eval_examples) / FLAGS.eval_batch_size) eval_drop_remainder = True if FLAGS.use_tpu else False eval_input_fn = file_based_input_fn_builder( input_file=eval_file, seq_length=FLAGS.max_seq_length, is_training=False, drop_remainder=eval_drop_remainder) result = estimator.evaluate(input_fn=eval_input_fn, steps=eval_steps) output_eval_file = os.path.join(output_dir, "eval_results.txt") with tf.gfile.GFile(output_eval_file, "w") as writer: tf.logging.info("***** Eval results *****") for key in sorted(result.keys()): tf.logging.info(" %s = %s", key, str(result[key])) writer.write("%s = %s\n" % (key, str(result[key]))) if FLAGS.do_predict: predict_examples = processor.get_test_examples(FLAGS.data_dir) predict_file = os.path.join(output_dir, "predict.tf_record") file_based_convert_examples_to_features(predict_examples, FLAGS.max_seq_length, tokenizer, predict_file) tf.logging.info("***** Running prediction*****") tf.logging.info(" Num examples = %d", len(predict_examples)) tf.logging.info(" Batch size = %d", FLAGS.predict_batch_size) if FLAGS.use_tpu: # Warning: According to tpu_estimator.py Prediction on TPU is an # experimental feature and hence not supported here raise ValueError("Prediction in TPU not supported") predict_drop_remainder = True if FLAGS.use_tpu else False predict_input_fn = file_based_input_fn_builder( input_file=predict_file, seq_length=FLAGS.max_seq_length, is_training=False, drop_remainder=predict_drop_remainder) result = estimator.predict(input_fn=predict_input_fn) output_predict_file = os.path.join(output_dir, "test_results.tsv") with tf.gfile.GFile(output_predict_file, "w") as writer: tf.logging.info("***** Predict results *****") for prediction in result: output_line = str(prediction) + "\n" writer.write(output_line)