test

example/ner/standard/conf/config.yaml

@@ -0,0 +1,11 @@
+# ??? is a mandatory value.
+# you should be able to set it without open_dict
+# but if you try to read it before it's set an error will get thrown.
+
+# populated at runtime
+cwd: ???
+
+defaults:
+    - hydra/output: custom
+    - train
+    - predict

example/ner/standard/conf/hydra/output/custom.yaml

@@ -0,0 +1,11 @@
+hydra:
+
+  run:
+    # Output directory for normal runs
+    dir: logs/${now:%Y-%m-%d_%H-%M-%S}
+
+  sweep:
+    # Output directory for sweep runs
+    dir: logs/${now:%Y-%m-%d_%H-%M-%S}
+    # Output sub directory for sweep runs.
+    subdir: ${hydra.job.num}_${hydra.job.id}

example/ner/standard/conf/predict.yaml

@@ -0,0 +1 @@
+text: "秦始皇兵马俑位于陕西省西安市，1961年被国务院公布为第一批全国重点文物保护单位，是世界八大奇迹之一。"

example/ner/standard/conf/train.yaml

@@ -0,0 +1,25 @@
+data_dir: "data/"
+bert_model: "bert-base-chinese"    # ["bert-base-chinese", "bert-base-cased"]
+language: "cn"               # ["cn", "en"] 
+task_name: "ner"
+output_dir: "checkpoint"
+max_seq_length: 128
+do_train: True
+do_eval: True
+eval_on: "dev"
+do_lower_case: True
+train_batch_size: 32
+eval_batch_size: 8
+learning_rate: 5e-5
+num_train_epochs: 1            # the number of training epochs
+warmup_proportion: 0.1
+weight_decay: 0.01
+adam_epsilon: 1e-8
+max_grad_norm: 1.0
+no_cuda: False
+local_rank: -1
+seed: 42
+gradient_accumulation_steps: 1
+fp16: False
+fp16_opt_level: "01"
+loss_scale: 0.0

example/ner/standard/predict.py

@@ -16,6 +16,9 @@ import argparse
 import nltk
 nltk.data.path.insert(0,'./data/nltk_data')
 
+import hydra
+from hydra import utils
+
 
 class BertNer(BertForTokenClassification):
 
@@ -53,7 +56,8 @@ class Ner:
 
     def tokenize(self, text: str):
         """ tokenize input"""
-        words = word_tokenize(text)
+#         words = word_tokenize(text)
+        words = list(text)
         tokens = []
         valid_positions = []
         for i,word in enumerate(words):
@@ -113,7 +117,7 @@ class Ner:
         logits.pop()
 
         labels = [(self.label_map[label],confidence) for label,confidence in logits]
-        words = word_tokenize(text)
+        words = list(text)
         assert len(labels) == len(words)
 
         result = []
@@ -146,15 +150,10 @@ class Ner:
         return tag
 
 
-if __name__ == "__main__":
+@hydra.main(config_path="conf", config_name='config')
-    model = Ner("out_ner/")
+def main(cfg):
-
+    model = Ner(utils.get_original_cwd()+'/'+"checkpoint/")
-    parser = argparse.ArgumentParser()
+    text = cfg.text
-    parser.add_argument("--text",
-                  default="Irene, a master student in Zhejiang University, Hangzhou, is traveling in Warsaw for Chopin Music Festival.",
-                  type=str,
-                  help="The text to be NERed")
-    text = parser.parse_args().text
 
     print("The text to be NERed:")
     print(text)
@@ -172,3 +171,9 @@ if __name__ == "__main__":
                 print('Organization')
             elif k=='MISC':
                 print('Miscellaneous')
+
+    
+    
+    
+if __name__ == "__main__":
+    main()

example/ner/standard/run.py

@@ -1,6 +1,5 @@
 from __future__ import absolute_import, division, print_function
 
-import argparse
 import csv
 import json
 import logging
@@ -27,6 +26,9 @@ logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(messa
                     level = logging.INFO)
 logger = logging.getLogger(__name__)
 
+import hydra
+from hydra import utils
+
 class Ner(BertForTokenClassification):
 
     def forward(self, input_ids, token_type_ids=None, attention_mask=None, labels=None,valid_ids=None,attention_mask_label=None):
@@ -136,7 +138,7 @@ class DataProcessor(object):
 
 
 class NerProcessor(DataProcessor):
-    """Processor for the CoNLL-2003 data set."""
+    """Processor for the dataset."""
 
     def get_train_examples(self, data_dir):
         """See base class."""
@@ -233,17 +235,6 @@ def convert_examples_to_features(examples, label_list, max_seq_length, tokenizer
         assert len(valid) == max_seq_length
         assert len(label_mask) == max_seq_length
 
-        if ex_index < 5:
-            logger.info("*** Example ***")
-            logger.info("guid: %s" % (example.guid))
-            logger.info("tokens: %s" % " ".join(
-                    [str(x) for x in tokens]))
-            logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids]))
-            logger.info("input_mask: %s" % " ".join([str(x) for x in input_mask]))
-            logger.info(
-                    "segment_ids: %s" % " ".join([str(x) for x in segment_ids]))
-            # logger.info("label: %s (id = %d)" % (example.label, label_ids))
-
         features.append(
                 InputFeatures(input_ids=input_ids,
                               input_mask=input_mask,
@@ -253,150 +244,41 @@ def convert_examples_to_features(examples, label_list, max_seq_length, tokenizer
                               label_mask=label_mask))
     return features
 
-def main():
+@hydra.main(config_path="conf", config_name='config')
-    parser = argparse.ArgumentParser()
+def main(cfg):
-
-    ## Required parameters
-    parser.add_argument("--data_dir",
-                        default=None,
-                        type=str,
-                        required=True,
-                        help="The input data dir. Should contain the .tsv files (or other data files) for the task.")
-    parser.add_argument("--bert_model", default=None, type=str, required=True,
-                        help="Bert pre-trained model selected in the list: bert-base-uncased, "
-                        "bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased, "
-                        "bert-base-multilingual-cased, bert-base-chinese.")
-    parser.add_argument("--task_name",
-                        default=None,
-                        type=str,
-                        required=True,
-                        help="The name of the task to train.")
-    parser.add_argument("--output_dir",
-                        default=None,
-                        type=str,
-                        required=True,
-                        help="The output directory where the model predictions and checkpoints will be written.")
-
-    ## Other parameters
-    parser.add_argument("--cache_dir",
-                        default="",
-                        type=str,
-                        help="Where do you want to store the pre-trained models downloaded from s3")
-    parser.add_argument("--max_seq_length",
-                        default=128,
-                        type=int,
-                        help="The maximum total input sequence length after WordPiece tokenization. \n"
-                             "Sequences longer than this will be truncated, and sequences shorter \n"
-                             "than this will be padded.")
-    parser.add_argument("--do_train",
-                        action='store_true',
-                        help="Whether to run training.")
-    parser.add_argument("--do_eval",
-                        action='store_true',
-                        help="Whether to run eval or not.")
-    parser.add_argument("--eval_on",
-                        default="dev",
-                        help="Whether to run eval on the dev set or test set.")
-    parser.add_argument("--do_lower_case",
-                        action='store_true',
-                        help="Set this flag if you are using an uncased model.")
-    parser.add_argument("--train_batch_size",
-                        default=32,
-                        type=int,
-                        help="Total batch size for training.")
-    parser.add_argument("--eval_batch_size",
-                        default=8,
-                        type=int,
-                        help="Total batch size for eval.")
-    parser.add_argument("--learning_rate",
-                        default=5e-5,
-                        type=float,
-                        help="The initial learning rate for Adam.")
-    parser.add_argument("--num_train_epochs",
-                        default=3.0,
-                        type=float,
-                        help="Total number of training epochs to perform.")
-    parser.add_argument("--warmup_proportion",
-                        default=0.1,
-                        type=float,
-                        help="Proportion of training to perform linear learning rate warmup for. "
-                             "E.g., 0.1 = 10%% of training.")
-    parser.add_argument("--weight_decay", default=0.01, type=float,
-                        help="Weight deay if we apply some.")
-    parser.add_argument("--adam_epsilon", default=1e-8, type=float,
-                        help="Epsilon for Adam optimizer.")
-    parser.add_argument("--max_grad_norm", default=1.0, type=float,
-                        help="Max gradient norm.")
-    parser.add_argument("--no_cuda",
-                        action='store_true',
-                        help="Whether not to use CUDA when available")
-    parser.add_argument("--local_rank",
-                        type=int,
-                        default=-1,
-                        help="local_rank for distributed training on gpus")
-    parser.add_argument('--seed',
-                        type=int,
-                        default=42,
-                        help="random seed for initialization")
-    parser.add_argument('--gradient_accumulation_steps',
-                        type=int,
-                        default=1,
-                        help="Number of updates steps to accumulate before performing a backward/update pass.")
-    parser.add_argument('--fp16',
-                        action='store_true',
-                        help="Whether to use 16-bit float precision instead of 32-bit")
-    parser.add_argument('--fp16_opt_level', type=str, default='O1',
-                        help="For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']."
-                             "See details at https://nvidia.github.io/apex/amp.html")
-    parser.add_argument('--loss_scale',
-                        type=float, default=0,
-                        help="Loss scaling to improve fp16 numeric stability. Only used when fp16 set to True.\n"
-                             "0 (default value): dynamic loss scaling.\n"
-                             "Positive power of 2: static loss scaling value.\n")
-    parser.add_argument('--server_ip', type=str, default='', help="Can be used for distant debugging.")
-    parser.add_argument('--server_port', type=str, default='', help="Can be used for distant debugging.")
-    args = parser.parse_args()
-
-    if args.server_ip and args.server_port:
-        # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script
-        import ptvsd
-        print("Waiting for debugger attach")
-        ptvsd.enable_attach(address=(args.server_ip, args.server_port), redirect_output=True)
-        ptvsd.wait_for_attach()
-
     processors = {"ner":NerProcessor}
 
-    if args.local_rank == -1 or args.no_cuda:
+    if cfg.local_rank == -1 or cfg.no_cuda:
-        device = torch.device("cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu")
+        device = torch.device("cuda" if torch.cuda.is_available() and not cfg.no_cuda else "cpu")
         n_gpu = torch.cuda.device_count()
     else:
-        torch.cuda.set_device(args.local_rank)
+        torch.cuda.set_device(cfg.local_rank)
-        device = torch.device("cuda", args.local_rank)
+        device = torch.device("cuda", cfg.local_rank)
         n_gpu = 1
         # Initializes the distributed backend which will take care of sychronizing nodes/GPUs
         torch.distributed.init_process_group(backend='nccl')
     logger.info("device: {} n_gpu: {}, distributed training: {}, 16-bits training: {}".format(
-        device, n_gpu, bool(args.local_rank != -1), args.fp16))
+        device, n_gpu, bool(cfg.local_rank != -1), cfg.fp16))
 
-    if args.gradient_accumulation_steps < 1:
+    if cfg.gradient_accumulation_steps < 1:
         raise ValueError("Invalid gradient_accumulation_steps parameter: {}, should be >= 1".format(
-                            args.gradient_accumulation_steps))
+                            cfg.gradient_accumulation_steps))
 
-    args.train_batch_size = args.train_batch_size // args.gradient_accumulation_steps
+    cfg.train_batch_size = cfg.train_batch_size // cfg.gradient_accumulation_steps
 
-    random.seed(args.seed)
+    random.seed(cfg.seed)
-    np.random.seed(args.seed)
+    np.random.seed(cfg.seed)
-    torch.manual_seed(args.seed)
+    torch.manual_seed(cfg.seed)
 
-    if not args.do_train and not args.do_eval:
+    if not cfg.do_train and not cfg.do_eval:
         raise ValueError("At least one of `do_train` or `do_eval` must be True.")
 
-    if os.path.exists(args.output_dir) and os.listdir(args.output_dir) and args.do_train:
+    if os.path.exists(utils.get_original_cwd()+'/'+cfg.output_dir) and os.listdir(utils.get_original_cwd()+'/'+cfg.output_dir) and cfg.do_train:
-        raise ValueError("Output directory ({}) already exists and is not empty.".format(args.output_dir))
+        raise ValueError("Output directory ({}) already exists and is not empty.".format(utils.get_original_cwd()+'/'+cfg.output_dir))
-    if not os.path.exists(args.output_dir):
+    if not os.path.exists(utils.get_original_cwd()+'/'+cfg.output_dir):
-        os.makedirs(args.output_dir)
+        os.makedirs(utils.get_original_cwd()+'/'+cfg.output_dir)
 
-    task_name = args.task_name.lower()
+    task_name = cfg.task_name.lower()
 
     if task_name not in processors:
         raise ValueError("Task not found: %s" % (task_name))
@@ -405,27 +287,27 @@ def main():
     label_list = processor.get_labels()
     num_labels = len(label_list) + 1
 
-    tokenizer = BertTokenizer.from_pretrained(args.bert_model, do_lower_case=args.do_lower_case)
+    tokenizer = BertTokenizer.from_pretrained(cfg.bert_model, do_lower_case=cfg.do_lower_case)
 
     train_examples = None
     num_train_optimization_steps = 0
-    if args.do_train:
+    if cfg.do_train:
-        train_examples = processor.get_train_examples(args.data_dir)
+        train_examples = processor.get_train_examples(utils.get_original_cwd()+'/'+cfg.data_dir)
         num_train_optimization_steps = int(
-            len(train_examples) / args.train_batch_size / args.gradient_accumulation_steps) * args.num_train_epochs
+            len(train_examples) / cfg.train_batch_size / cfg.gradient_accumulation_steps) * cfg.num_train_epochs
-        if args.local_rank != -1:
+        if cfg.local_rank != -1:
             num_train_optimization_steps = num_train_optimization_steps // torch.distributed.get_world_size()
 
-    if args.local_rank not in [-1, 0]:
+    if cfg.local_rank not in [-1, 0]:
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab
 
     # Prepare model
-    config = BertConfig.from_pretrained(args.bert_model, num_labels=num_labels, finetuning_task=args.task_name)
+    config = BertConfig.from_pretrained(cfg.bert_model, num_labels=num_labels, finetuning_task=cfg.task_name)
-    model = Ner.from_pretrained(args.bert_model,
+    model = Ner.from_pretrained(cfg.bert_model,
               from_tf = False,
               config = config)
 
-    if args.local_rank == 0:
+    if cfg.local_rank == 0:
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab
 
     model.to(device)
@@ -433,39 +315,35 @@ def main():
     param_optimizer = list(model.named_parameters())
     no_decay = ['bias','LayerNorm.weight']
     optimizer_grouped_parameters = [
-        {'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay': args.weight_decay},
+        {'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay': cfg.weight_decay},
         {'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}
         ]
-    warmup_steps = int(args.warmup_proportion * num_train_optimization_steps)
+    warmup_steps = int(cfg.warmup_proportion * num_train_optimization_steps)
-    optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
+    optimizer = AdamW(optimizer_grouped_parameters, lr=cfg.learning_rate, eps=cfg.adam_epsilon)
     scheduler = WarmupLinearSchedule(optimizer, warmup_steps=warmup_steps, t_total=num_train_optimization_steps)
-    if args.fp16:
+    if cfg.fp16:
         try:
             from apex import amp
         except ImportError:
             raise ImportError("Please install apex from https://www.github.com/nvidia/apex to use fp16 training.")
-        model, optimizer = amp.initialize(model, optimizer, opt_level=args.fp16_opt_level)
+        model, optimizer = amp.initialize(model, optimizer, opt_level=cfg.fp16_opt_level)
 
     # multi-gpu training (should be after apex fp16 initialization)
     if n_gpu > 1:
         model = torch.nn.DataParallel(model)
 
-    if args.local_rank != -1:
+    if cfg.local_rank != -1:
-        model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.local_rank],
+        model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[cfg.local_rank],
-                                                          output_device=args.local_rank,
+                                                          output_device=cfg.local_rank,
                                                           find_unused_parameters=True)
 
     global_step = 0
     nb_tr_steps = 0
     tr_loss = 0
     label_map = {i : label for i, label in enumerate(label_list,1)}
-    if args.do_train:
+    if cfg.do_train:
         train_features = convert_examples_to_features(
-            train_examples, label_list, args.max_seq_length, tokenizer)
+            train_examples, label_list, cfg.max_seq_length, tokenizer)
-        logger.info("***** Running training *****")
-        logger.info("  Num examples = %d", len(train_examples))
-        logger.info("  Batch size = %d", args.train_batch_size)
-        logger.info("  Num steps = %d", num_train_optimization_steps)
         all_input_ids = torch.tensor([f.input_ids for f in train_features], dtype=torch.long)
         all_input_mask = torch.tensor([f.input_mask for f in train_features], dtype=torch.long)
         all_segment_ids = torch.tensor([f.segment_ids for f in train_features], dtype=torch.long)
@@ -473,14 +351,14 @@ def main():
         all_valid_ids = torch.tensor([f.valid_ids for f in train_features], dtype=torch.long)
         all_lmask_ids = torch.tensor([f.label_mask for f in train_features], dtype=torch.long)
         train_data = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids,all_valid_ids,all_lmask_ids)
-        if args.local_rank == -1:
+        if cfg.local_rank == -1:
             train_sampler = RandomSampler(train_data)
         else:
             train_sampler = DistributedSampler(train_data)
-        train_dataloader = DataLoader(train_data, sampler=train_sampler, batch_size=args.train_batch_size)
+        train_dataloader = DataLoader(train_data, sampler=train_sampler, batch_size=cfg.train_batch_size)
 
         model.train()
-        for _ in trange(int(args.num_train_epochs), desc="Epoch"):
+        for _ in trange(int(cfg.num_train_epochs), desc="Epoch"):
             tr_loss = 0
             nb_tr_examples, nb_tr_steps = 0, 0
             for step, batch in enumerate(tqdm(train_dataloader, desc="Iteration")):
@@ -489,21 +367,21 @@ def main():
                 loss = model(input_ids, segment_ids, input_mask, label_ids,valid_ids,l_mask)
                 if n_gpu > 1:
                     loss = loss.mean() # mean() to average on multi-gpu.
-                if args.gradient_accumulation_steps > 1:
+                if cfg.gradient_accumulation_steps > 1:
-                    loss = loss / args.gradient_accumulation_steps
+                    loss = loss / cfg.gradient_accumulation_steps
 
-                if args.fp16:
+                if cfg.fp16:
                     with amp.scale_loss(loss, optimizer) as scaled_loss:
                         scaled_loss.backward()
-                    torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm)
+                    torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), cfg.max_grad_norm)
                 else:
                     loss.backward()
-                    torch.nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm)
+                    torch.nn.utils.clip_grad_norm_(model.parameters(), cfg.max_grad_norm)
 
                 tr_loss += loss.item()
                 nb_tr_examples += input_ids.size(0)
                 nb_tr_steps += 1
-                if (step + 1) % args.gradient_accumulation_steps == 0:
+                if (step + 1) % cfg.gradient_accumulation_steps == 0:
                     optimizer.step()
                     scheduler.step()  # Update learning rate schedule
                     model.zero_grad()
@@ -511,30 +389,27 @@ def main():
 
         # Save a trained model and the associated configuration
         model_to_save = model.module if hasattr(model, 'module') else model  # Only save the model it-self
-        model_to_save.save_pretrained(args.output_dir)
+        model_to_save.save_pretrained(utils.get_original_cwd()+'/'+cfg.output_dir)
-        tokenizer.save_pretrained(args.output_dir)
+        tokenizer.save_pretrained(utils.get_original_cwd()+'/'+cfg.output_dir)
         label_map = {i : label for i, label in enumerate(label_list,1)}
-        model_config = {"bert_model":args.bert_model,"do_lower":args.do_lower_case,"max_seq_length":args.max_seq_length,"num_labels":len(label_list)+1,"label_map":label_map}
+        model_config = {"bert_model":cfg.bert_model,"do_lower":cfg.do_lower_case,"max_seq_length":cfg.max_seq_length,"num_labels":len(label_list)+1,"label_map":label_map}
-        json.dump(model_config,open(os.path.join(args.output_dir,"model_config.json"),"w"))
+        json.dump(model_config,open(os.path.join(utils.get_original_cwd()+'/'+cfg.output_dir,"model_config.json"),"w"))
         # Load a trained model and config that you have fine-tuned
     else:
         # Load a trained model and vocabulary that you have fine-tuned
-        model = Ner.from_pretrained(args.output_dir)
+        model = Ner.from_pretrained(utils.get_original_cwd()+'/'+cfg.output_dir)
-        tokenizer = BertTokenizer.from_pretrained(args.output_dir, do_lower_case=args.do_lower_case)
+        tokenizer = BertTokenizer.from_pretrained(utils.get_original_cwd()+'/'+cfg.output_dir, do_lower_case=cfg.do_lower_case)
 
     model.to(device)
 
-    if args.do_eval and (args.local_rank == -1 or torch.distributed.get_rank() == 0):
+    if cfg.do_eval and (cfg.local_rank == -1 or torch.distributed.get_rank() == 0):
-        if args.eval_on == "dev":
+        if cfg.eval_on == "dev":
-            eval_examples = processor.get_dev_examples(args.data_dir)
+            eval_examples = processor.get_dev_examples(utils.get_original_cwd()+'/'+cfg.data_dir)
-        elif args.eval_on == "test":
+        elif cfg.eval_on == "test":
-            eval_examples = processor.get_test_examples(args.data_dir)
+            eval_examples = processor.get_test_examples(utils.get_original_cwd()+'/'+cfg.data_dir)
         else:
             raise ValueError("eval on dev or test set only")
-        eval_features = convert_examples_to_features(eval_examples, label_list, args.max_seq_length, tokenizer)
+        eval_features = convert_examples_to_features(eval_examples, label_list, cfg.max_seq_length, tokenizer)
-        logger.info("***** Running evaluation *****")
-        logger.info("  Num examples = %d", len(eval_examples))
-        logger.info("  Batch size = %d", args.eval_batch_size)
         all_input_ids = torch.tensor([f.input_ids for f in eval_features], dtype=torch.long)
         all_input_mask = torch.tensor([f.input_mask for f in eval_features], dtype=torch.long)
         all_segment_ids = torch.tensor([f.segment_ids for f in eval_features], dtype=torch.long)
@@ -544,7 +419,7 @@ def main():
         eval_data = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids,all_valid_ids,all_lmask_ids)
         # Run prediction for full data
         eval_sampler = SequentialSampler(eval_data)
-        eval_dataloader = DataLoader(eval_data, sampler=eval_sampler, batch_size=args.eval_batch_size)
+        eval_dataloader = DataLoader(eval_data, sampler=eval_sampler, batch_size=cfg.eval_batch_size)
         model.eval()
         eval_loss, eval_accuracy = 0, 0
         nb_eval_steps, nb_eval_examples = 0, 0
@@ -583,7 +458,7 @@ def main():
 
         report = classification_report(y_true, y_pred,digits=4)
         logger.info("\n%s", report)
-        output_eval_file = os.path.join(args.output_dir, "eval_results.txt")
+        output_eval_file = os.path.join(utils.get_original_cwd()+'/'+cfg.output_dir, "eval_results.txt")
         with open(output_eval_file, "w") as writer:
             logger.info("***** Eval results *****")
             logger.info("\n%s", report)