# limitations under the License. """Sentiment Classification in Paddle Dygraph Mode. """ from __future__ import print_function import numpy as np import paddle.fluid as fluid from hapi.model import set_device, Model, CrossEntropy, Input from hapi.configure import Config from hapi.text.senta import SentaProcessor from hapi.metrics import Accuracy from models import CNN, BOW, GRU, BiGRU import json import os args = Config(yaml_file='./senta.yaml') args.build() args.Print() device = set_device("gpu" if args.use_cuda else "cpu") dev_count = fluid.core.get_cuda_device_count() if args.use_cuda else 1 def main(): if args.do_train: train() elif args.do_infer: infer() def train(): fluid.enable_dygraph(device)
def main(): config = Config(yaml_file="./bert.yaml") config.build() config.Print() device = set_device("gpu" if config.use_cuda else "cpu") fluid.enable_dygraph(device) bert_config = BertConfig(config.bert_config_path) bert_config.print_config() tokenizer = tokenization.FullTokenizer( vocab_file=config.vocab_path, do_lower_case=config.do_lower_case) def mnli_line_processor(line_id, line): if line_id == "0": return None uid = tokenization.convert_to_unicode(line[0]) text_a = tokenization.convert_to_unicode(line[8]) text_b = tokenization.convert_to_unicode(line[9]) label = tokenization.convert_to_unicode(line[-1]) if label not in ["contradiction", "entailment", "neutral"]: label = "contradiction" return BertInputExample( uid=uid, text_a=text_a, text_b=text_b, label=label) train_dataloader = BertDataLoader( "./data/glue_data/MNLI/train.tsv", tokenizer, ["contradiction", "entailment", "neutral"], max_seq_length=config.max_seq_len, batch_size=config.batch_size, line_processor=mnli_line_processor) test_dataloader = BertDataLoader( "./data/glue_data/MNLI/dev_matched.tsv", tokenizer, ["contradiction", "entailment", "neutral"], max_seq_length=config.max_seq_len, batch_size=config.batch_size, line_processor=mnli_line_processor, shuffle=False, phase="predict") trainer_count = fluid.dygraph.parallel.Env().nranks num_train_examples = len(train_dataloader.dataset) max_train_steps = config.epoch * num_train_examples // config.batch_size // trainer_count warmup_steps = int(max_train_steps * config.warmup_proportion) print("Trainer count: %d" % trainer_count) print("Num train examples: %d" % num_train_examples) print("Max train steps: %d" % max_train_steps) print("Num warmup steps: %d" % warmup_steps) inputs = [ Input( [None, None], 'int64', name='src_ids'), Input( [None, None], 'int64', name='pos_ids'), Input( [None, None], 'int64', name='sent_ids'), Input( [None, None, 1], 'float32', name='input_mask') ] labels = [Input([None, 1], 'int64', name='label')] cls_model = ClsModelLayer( config, bert_config, len(["contradiction", "entailment", "neutral"]), return_pooled_out=True) optimizer = make_optimizer( warmup_steps=warmup_steps, num_train_steps=max_train_steps, learning_rate=config.learning_rate, weight_decay=config.weight_decay, scheduler=config.lr_scheduler, model=cls_model, loss_scaling=config.loss_scaling, parameter_list=cls_model.parameters()) cls_model.prepare( optimizer, SoftmaxWithCrossEntropy(), Accuracy(topk=(1, 2)), inputs, labels, device=device) cls_model.bert_layer.load("./bert_uncased_L-12_H-768_A-12/bert", reset_optimizer=True) # do train cls_model.fit(train_data=train_dataloader.dataloader, epochs=config.epoch, save_dir=config.checkpoints) # do eval cls_model.evaluate( eval_data=test_dataloader.dataloader, batch_size=config.batch_size)
def main(): """ Main Function """ args = Config(yaml_file='./config.yaml') args.build() args.Print() if not (args.do_train or args.do_val or args.do_infer): raise ValueError("For args `do_train`, `do_val` and `do_infer`, at " "least one of them must be True.") place = set_device("gpu" if args.use_cuda else "cpu") fluid.enable_dygraph(place) processor = EmoTectProcessor(data_dir=args.data_dir, vocab_path=args.vocab_path, random_seed=args.random_seed) num_labels = args.num_labels if args.model_type == 'cnn_net': model = CNN(args.vocab_size, args.max_seq_len) elif args.model_type == 'bow_net': model = BOW(args.vocab_size, args.max_seq_len) elif args.model_type == 'lstm_net': model = LSTM(args.vocab_size, args.max_seq_len) elif args.model_type == 'gru_net': model = GRU(args.vocab_size, args.max_seq_len) elif args.model_type == 'bigru_net': model = BiGRU(args.vocab_size, args.batch_size, args.max_seq_len) else: raise ValueError("Unknown model type!") inputs = [Input([None, args.max_seq_len], 'int64', name='doc')] optimizer = None labels = None if args.do_train: train_data_generator = processor.data_generator( batch_size=args.batch_size, places=place, phase='train', epoch=args.epoch, padding_size=args.max_seq_len) num_train_examples = processor.get_num_examples(phase="train") max_train_steps = args.epoch * num_train_examples // args.batch_size + 1 print("Num train examples: %d" % num_train_examples) print("Max train steps: %d" % max_train_steps) labels = [Input([None, 1], 'int64', name='label')] optimizer = fluid.optimizer.Adagrad(learning_rate=args.lr, parameter_list=model.parameters()) test_data_generator = None if args.do_val: test_data_generator = processor.data_generator( batch_size=args.batch_size, phase='dev', epoch=1, places=place, padding_size=args.max_seq_len) elif args.do_val: test_data_generator = processor.data_generator( batch_size=args.batch_size, phase='test', epoch=1, places=place, padding_size=args.max_seq_len) elif args.do_infer: infer_data_generator = processor.data_generator( batch_size=args.batch_size, phase='infer', epoch=1, places=place, padding_size=args.max_seq_len) model.prepare(optimizer, CrossEntropy(), Accuracy(topk=(1, )), inputs, labels, device=place) if args.do_train: if args.init_checkpoint: model.load(args.init_checkpoint) elif args.do_val or args.do_infer: if not args.init_checkpoint: raise ValueError("args 'init_checkpoint' should be set if" "only doing validation or infer!") model.load(args.init_checkpoint, reset_optimizer=True) if args.do_train: model.fit(train_data=train_data_generator, eval_data=test_data_generator, batch_size=args.batch_size, epochs=args.epoch, save_dir=args.checkpoints, eval_freq=args.eval_freq, save_freq=args.save_freq) elif args.do_val: eval_result = model.evaluate(eval_data=test_data_generator, batch_size=args.batch_size) print("Final eval result: acc: {:.4f}, loss: {:.4f}".format( eval_result['acc'], eval_result['loss'][0])) elif args.do_infer: preds = model.predict(test_data=infer_data_generator) preds = np.array(preds[0]).reshape((-1, args.num_labels)) if args.output_dir: with open(os.path.join(args.output_dir, 'predictions.json'), 'w') as w: for p in range(len(preds)): label = np.argmax(preds[p]) result = json.dumps({ 'index': p, 'label': label, 'probs': preds[p].tolist() }) w.write(result + '\n') print('Predictions saved at ' + os.path.join(args.output_dir, 'predictions.json'))