Refine api of emotion detection and dialogue domain classification (#4308)

* Update README.md (#4267)

* test=develop (#4269)

* 3d use new api (#4275)

* PointNet++ and PointRCNN use new API

* Update Readme of Dygraph BERT (#4277)

Fix some typos.

* Update run_classifier_multi_gpu.sh (#4279)

remove the CUDA_VISIBLE_DEVICES

* Update README.md (#4280)

* 17 update api (#4294)

* update1.7 save/load & fluid.data

* update datafeed to dataloader

* Update resnet_acnet.py (#4297)

Bias attr of square conv should be "False" rather than None during training mode.

* test=develop
Co-authored-by: NKaipeng Deng <dengkaipeng@baidu.com>
Co-authored-by: Nzhang wenhui <frankwhzhang@126.com>
Co-authored-by: Nparap1uie-s <parap1uie-s@users.noreply.github.com>

PaddleCV/image_classification/models/resnet_acnet.py

@@ -172,7 +172,7 @@ class ResNetACNet(object):
             act=act if self.deploy else None,
             param_attr=ParamAttr(name=name + "_acsquare_weights"),
             bias_attr=ParamAttr(name=name + "_acsquare_bias")
-            if self.deploy else None,
+            if self.deploy else False,
             name=name + '.acsquare.conv2d.output.1')
 
         if self.deploy:

PaddleNLP/dialogue_domain_classification/utils.py

@@ -32,14 +32,13 @@ try:
 except ImportError:
     import ConfigParser as cp
 
-
 random_seed = 7
 logger = logging.getLogger()
 format = "%(asctime)s - %(name)s - %(levelname)s -%(filename)s-%(lineno)4d -%(message)s"
 # format = "%(levelname)8s: %(asctime)s: %(filename)s:%(lineno)4d %(message)s"
 logging.basicConfig(format=format)
 logger.setLevel(logging.INFO)
-logger = logging.getLogger('Paddle-DDC') 
+logger = logging.getLogger('Paddle-DDC')
 
 
 def str2bool(v):
@@ -77,6 +76,7 @@ class ArgumentGroup(object):
     Arguments:
         object {[type]} -- [description]
     """
+
     def __init__(self, parser, title, des):
         self._group = parser.add_argument_group(title=title, description=des)
 
@@ -107,6 +107,7 @@ class DataReader(object):
     Returns:
         [type] -- [description]
     """
+
     def __init__(self, char_vocab, intent_dict, max_len):
         self._char_vocab = char_vocab
         self._intent_dict = intent_dict
@@ -115,10 +116,10 @@ class DataReader(object):
         self.all_data = []
         self.max_len = max_len
         self.padding_id = 0
-    
+
     def _get_num_examples(self):
         return len(self.all_data)
-    
+
     def prepare_data(self, data_path, batch_size, mode):
         """
         prepare data
@@ -128,12 +129,17 @@ class DataReader(object):
         #     word_dict_path), "The given word dictionary dose not exist."
         assert os.path.exists(data_path), "The given data file does not exist."
         if mode == "train":
-            train_reader = fluid.io.batch(paddle.reader.shuffle(self.data_reader(data_path, self.max_len, shuffle=True),
-                                        buf_size=batch_size * 100), batch_size)
+            train_reader = fluid.io.batch(
+                paddle.reader.shuffle(
+                    self.data_reader(
+                        data_path, self.max_len, shuffle=True),
+                    buf_size=batch_size * 100),
+                batch_size)
             # train_reader = fluid.io.batch(self.data_reader(data_path), batch_size)                   
             return train_reader
         else:
-            test_reader = fluid.io.batch(self.data_reader(data_path, self.max_len), batch_size)
+            test_reader = fluid.io.batch(
+                self.data_reader(data_path, self.max_len), batch_size)
             return test_reader
 
     def data_reader(self, file_path, max_len, shuffle=False):
@@ -141,7 +147,7 @@ class DataReader(object):
         Convert query into id list
         use fixed voc
         """
-        
+
         for line in codecs.open(file_path, "r", encoding="utf8"):
             line = line.strip()
             if isinstance(line, six.binary_type):
@@ -150,7 +156,8 @@ class DataReader(object):
             char_id_list = list(map(lambda x: 0 if x not in self._char_vocab else int(self._char_vocab[x]), \
                             list(query)))
             if len(char_id_list) < max_len:
-                char_id_list.extend([self.padding_id] * (max_len - len(char_id_list)))
+                char_id_list.extend([self.padding_id] *
+                                    (max_len - len(char_id_list)))
             char_id_list = char_id_list[:max_len]
             intent_id_list = [self.padding_id] * self.intent_size
             for item in intent.split('\2'):
@@ -159,6 +166,7 @@ class DataReader(object):
         if shuffle:
             random.seed(random_seed)
             random.shuffle(self.all_data)
+
         def reader():
             """
             reader
@@ -166,6 +174,7 @@ class DataReader(object):
             for char_id_list, intent_id_list in self.all_data:
                 # print char_id_list, intent_id
                 yield char_id_list, intent_id_list
+
         return reader
 
 
@@ -178,6 +187,7 @@ class DataProcesser(object):
     Returns:
         [type] -- [description]
     """
+
     @staticmethod
     def read_dict(filename):
         """
@@ -211,7 +221,7 @@ class DataProcesser(object):
         char_dict = {}
         intent_dict = {}
         # readfile
-        for line in codecs.open(filename): 
+        for line in codecs.open(filename):
             line = line.strip()
             if isinstance(line, six.binary_type):
                 line = line.strip().decode("utf8", errors="ignore")
@@ -227,7 +237,8 @@ class DataProcesser(object):
                     intent_dict[intent] = 0
                 intent_dict[intent] += 1
         #   save char dict
-        with codecs.open("%s/char.dict" % save_dir, "w", encoding="utf8") as f_out:
+        with codecs.open(
+                "%s/char.dict" % save_dir, "w", encoding="utf8") as f_out:
             f_out.write("PAD\0020\n")
             f_out.write("OOV\0021\n")
             char_id = 2
@@ -238,7 +249,8 @@ class DataProcesser(object):
                     f_out.write("%s\002%d\n" % (key, char_id))
                     char_id += 1
         #   save intent dict
-        with codecs.open("%s/domain.dict" % save_dir, "w", encoding="utf8") as f_out:
+        with codecs.open(
+                "%s/domain.dict" % save_dir, "w", encoding="utf8") as f_out:
             f_out.write("SYS_OTHER\0020\n")
             intent_id = 1
             for key, value in intent_dict.items():
@@ -247,7 +259,6 @@ class DataProcesser(object):
                         key = key.encode("utf8")
                     f_out.write("%s\002%d\n" % (key, intent_id))
                     intent_id += 1
-        
 
 
 class ConfigReader(object):
@@ -282,49 +293,13 @@ class ConfigReader(object):
         return flow_data
 
 
-def init_pretraining_params(exe,
-                            pretraining_params_path,
-                            main_program,
-                            use_fp16=False):
-    """load params of pretrained model, NOT including moment, learning_rate"""
-    assert os.path.exists(pretraining_params_path
-                          ), "[%s] cann't be found." % pretraining_params_path
-
-    def _existed_params(var):
-        if not isinstance(var, fluid.framework.Parameter):
-            return False
-        return os.path.exists(os.path.join(pretraining_params_path, var.name))
-
-    fluid.io.load_vars(
-        exe,
-        pretraining_params_path,
-        main_program=main_program,
-        predicate=_existed_params)
-    print("Load pretraining parameters from {}.".format(
-        pretraining_params_path))
-
-
 def init_checkpoint(exe, init_checkpoint_path, main_program):
     """
     Init CheckPoint
     """
-    assert os.path.exists(
-        init_checkpoint_path), "[%s] cann't be found." % init_checkpoint_path
+    fluid.load(main_program, init_checkpoint_path, exe)
+    print("Load model from {}".format(init_checkpoint_path))
 
-    def existed_persitables(var):
-        """
-        If existed presitabels
-        """
-        if not fluid.io.is_persistable(var):
-            return False
-        return os.path.exists(os.path.join(init_checkpoint_path, var.name))
-
-    fluid.io.load_vars(
-        exe,
-        init_checkpoint_path,
-        main_program=main_program,
-        predicate=existed_persitables)
-    print ("Load model from {}".format(init_checkpoint_path))
 
 def print_arguments(args):
     """
@@ -350,5 +325,3 @@ def check_version(version='1.6.0'):
     except Exception as e:
         logger.error(err)
         sys.exit(1)
-
-

PaddleNLP/emotion_detection/run_classifier.py

@@ -11,7 +11,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
 """
 Emotion Detection Task
 """
@@ -38,9 +37,7 @@ import reader
 import utils
 
 
-def create_model(args,
-                 num_labels,
-                 is_prediction=False):
+def create_model(args, num_labels, is_prediction=False):
     """
     Create Model for Emotion Detection
     """
@@ -77,10 +74,17 @@ def create_model(args,
         raise ValueError("Unknown network type!")
 
     if is_prediction:
-        probs = network(data, seq_len, None, args.vocab_size, class_dim=num_labels, is_prediction=True)
+        probs = network(
+            data,
+            seq_len,
+            None,
+            args.vocab_size,
+            class_dim=num_labels,
+            is_prediction=True)
         return loader, probs, [data.name, seq_len.name]
 
-    avg_loss, probs = network(data, seq_len, label, args.vocab_size, class_dim=num_labels)
+    avg_loss, probs = network(
+        data, seq_len, label, args.vocab_size, class_dim=num_labels)
     num_seqs = fluid.layers.create_tensor(dtype='int64')
     accuracy = fluid.layers.accuracy(input=probs, label=label, total=num_seqs)
     return loader, avg_loss, accuracy, num_seqs
@@ -142,9 +146,10 @@ def main(args):
     exe = fluid.Executor(place)
 
     task_name = args.task_name.lower()
-    processor = reader.EmoTectProcessor(data_dir=args.data_dir,
-                                      vocab_path=args.vocab_path,
-                                      random_seed=args.random_seed)
+    processor = reader.EmoTectProcessor(
+        data_dir=args.data_dir,
+        vocab_path=args.vocab_path,
+        random_seed=args.random_seed)
     #num_labels = len(processor.get_labels())
     num_labels = args.num_labels
 
@@ -173,9 +178,7 @@ def main(args):
         with fluid.program_guard(train_program, startup_prog):
             with fluid.unique_name.guard():
                 train_loader, loss, accuracy, num_seqs = create_model(
-                    args,
-                    num_labels=num_labels,
-                    is_prediction=False)
+                    args, num_labels=num_labels, is_prediction=False)
 
                 sgd_optimizer = fluid.optimizer.Adagrad(learning_rate=args.lr)
                 sgd_optimizer.minimize(loss)
@@ -189,37 +192,27 @@ def main(args):
     if args.do_val:
         if args.do_train:
             test_data_generator = processor.data_generator(
-                batch_size=args.batch_size,
-                phase='dev',
-                epoch=1)
+                batch_size=args.batch_size, phase='dev', epoch=1)
         else:
             test_data_generator = processor.data_generator(
-                batch_size=args.batch_size,
-                phase='test',
-                epoch=1)
+                batch_size=args.batch_size, phase='test', epoch=1)
 
         test_prog = fluid.Program()
         with fluid.program_guard(test_prog, startup_prog):
             with fluid.unique_name.guard():
                 test_loader, loss, accuracy, num_seqs = create_model(
-                    args,
-                    num_labels=num_labels,
-                    is_prediction=False)
+                    args, num_labels=num_labels, is_prediction=False)
         test_prog = test_prog.clone(for_test=True)
 
     if args.do_infer:
         infer_data_generator = processor.data_generator(
-            batch_size=args.batch_size,
-            phase='infer',
-            epoch=1)
+            batch_size=args.batch_size, phase='infer', epoch=1)
 
         test_prog = fluid.Program()
         with fluid.program_guard(test_prog, startup_prog):
             with fluid.unique_name.guard():
                 infer_loader, probs, _ = create_model(
-                    args,
-                    num_labels=num_labels,
-                    is_prediction=True)
+                    args, num_labels=num_labels, is_prediction=True)
         test_prog = test_prog.clone(for_test=True)
 
     exe.run(startup_prog)
@@ -292,8 +285,9 @@ def main(args):
                     time_begin = time.time()
 
                 if steps % args.save_steps == 0:
-                    save_path = os.path.join(args.save_checkpoint_dir, "step_" + str(steps))
-                    fluid.io.save_persistables(exe, save_path, train_program)
+                    save_path = os.path.join(args.save_checkpoint_dir,
+                                             "step_" + str(steps))
+                    fluid.save(train_program, save_path)
 
                 if steps % args.validation_steps == 0:
                     # evaluate on dev set
@@ -306,11 +300,11 @@ def main(args):
                 print("final step: %d " % steps)
                 if args.do_val:
                     evaluate(test_exe, test_prog, test_loader,
-                        [loss.name, accuracy.name, num_seqs.name],
-                        "dev")
+                             [loss.name, accuracy.name, num_seqs.name], "dev")
 
-                save_path = os.path.join(args.save_checkpoint_dir, "step_" + str(steps))
-                fluid.io.save_persistables(exe, save_path, train_program)
+                save_path = os.path.join(args.save_checkpoint_dir,
+                                         "step_" + str(steps))
+                fluid.save(train_program, save_path)
                 train_loader.reset()
                 break
 
@@ -334,15 +328,12 @@ def main(args):
     if not args.do_train and args.do_val:
         print("Final test result:")
         evaluate(test_exe, test_prog, test_loader,
-                 [loss.name, accuracy.name, num_seqs.name],
-                 "test")
+                 [loss.name, accuracy.name, num_seqs.name], "test")
 
     # infer
     if args.do_infer:
         print("Final infer result:")
-        infer(test_exe, test_prog, infer_loader,
-             [probs.name],
-             "infer")
+        infer(test_exe, test_prog, infer_loader, [probs.name], "infer")
 
 
 def get_cards():

PaddleNLP/emotion_detection/run_ernie_classifier.py

@@ -11,7 +11,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
 """
 Emotion Detection Task, based on ERNIE
 """
@@ -350,7 +349,7 @@ def main(args):
 
                 if steps % args.save_steps == 0:
                     save_path = os.path.join(args.save_checkpoint_dir, "step_" + str(steps))
-                    fluid.io.save_persistables(exe, save_path, train_program)
+                    fluid.save(train_program, save_path)
 
                 if steps % args.validation_steps == 0:
                     # evaluate dev set
@@ -369,7 +368,7 @@ def main(args):
 
             except fluid.core.EOFException:
                 save_path = os.path.join(args.save_checkpoint_dir, "step_" + str(steps))
-                fluid.io.save_persistables(exe, save_path, train_program)
+                fluid.save(train_program, save_path)
                 train_pyreader.reset()
                 break
 

PaddleNLP/emotion_detection/utils.py

@@ -11,7 +11,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
 """
 EmoTect utilities.
 """
@@ -29,27 +28,13 @@ import paddle
 import paddle.fluid as fluid
 import numpy as np
 
+
 def init_checkpoint(exe, init_checkpoint_path, main_program):
     """
     Init CheckPoint
     """
-    assert os.path.exists(
-        init_checkpoint_path), "[%s] cann't be found." % init_checkpoint_path
-
-    def existed_persitables(var):
-        """
-        If existed presitabels
-        """
-        if not fluid.io.is_persistable(var):
-            return False
-        return os.path.exists(os.path.join(init_checkpoint_path, var.name))
 
-    fluid.io.load_vars(
-        exe,
-        init_checkpoint_path,
-        main_program=main_program,
-        predicate=existed_persitables)
-    print("Load model from {}".format(init_checkpoint_path))
+    fluid.load(main_program, init_checkpoint_path, exe)
 
 
 def word2id(word_dict, query):
@@ -57,8 +42,10 @@ def word2id(word_dict, query):
     Convert word sequence into id list
     """
     unk_id = len(word_dict)
-    wids = [word_dict[w] if w in word_dict else unk_id
-            for w in query.strip().split(" ")]
+    wids = [
+        word_dict[w] if w in word_dict else unk_id
+        for w in query.strip().split(" ")
+    ]
     return wids
 
 

PaddleRec/multi-task/MMoE/mmoe_train.py

@@ -114,7 +114,6 @@ loss, data_list = model(dict_dim, emb_dim)
 sgd = fluid.optimizer.SGD(learning_rate=args.base_lr)
 sgd.minimize(loss)
 place = fluid.CUDAPlace(0) if args.use_gpu else fluid.CPUPlace()
-feeder = fluid.DataFeeder(feed_list=data_list, place=place)
 exe = fluid.Executor(place)
 exe.run(fluid.default_startup_program())
 for batch_id in range(100):

PaddleRec/multiview_simnet/train.py

@@ -136,17 +136,19 @@ def start_train(args):
     startup_program = fluid.default_startup_program()
     loop_program = fluid.default_main_program()
 
-    feeder = fluid.DataFeeder(feed_list=all_slots, place=place)
     exe = fluid.Executor(place)
     exe.run(startup_program)
+    loader = fluid.io.DataLoader.from_generator(
+        feed_list=all_slots, capacity=10000, iterable=True)
+    loader.set_sample_list_generator(train_reader, places=place)
 
     total_time = 0
     ce_info = []
     for pass_id in range(args.epochs):
         start_time = time.time()
-        for batch_id, data in enumerate(train_reader()):
+        for batch_id, data in enumerate(loader()):
             loss_val, correct_val = exe.run(loop_program,
-                                            feed=feeder.feed(data),
+                                            feed=data,
                                             fetch_list=[avg_cost, correct])
             logger.info("TRAIN --> pass: {} batch_id: {} avg_cost: {}, acc: {}"
                         .format(pass_id, batch_id, loss_val,

PaddleRec/ssr/train.py

@@ -87,9 +87,12 @@ def train(args):
     optimizer.minimize(avg_cost)
 
     data_list = [var.name for var in train_input_data]
-    feeder = fluid.DataFeeder(feed_list=data_list, place=place)
+    print(data_list)
     exe = fluid.Executor(place)
     exe.run(fluid.default_startup_program())
+    loader = fluid.io.DataLoader.from_generator(
+        feed_list=train_input_data, capacity=10000, iterable=True)
+    loader.set_sample_list_generator(train_reader, places=place)
     if parallel:
         train_exe = fluid.ParallelExecutor(
             use_cuda=use_cuda, loss_name=avg_cost.name)
@@ -103,10 +106,10 @@ def train(args):
         print("epoch_%d start" % epoch_idx)
         t0 = time.time()
         i = 0
-        for batch_id, data in enumerate(train_reader()):
+        for batch_id, data in enumerate(loader()):
             i += 1
             loss_val, correct_val = train_exe.run(
-                feed=feeder.feed(data), fetch_list=[avg_cost.name, acc.name])
+                feed=data, fetch_list=[avg_cost.name, acc.name])
             ce_info.append(float(np.mean(correct_val)) / args.batch_size)
             if i % args.print_batch == 0:
                 logger.info(