support log_interval for TS

paddlets/models/classify/dl/paddle_base.py

@@ -75,18 +75,18 @@ class PaddleBaseClassifier(BaseClassifier):
         _callback_container(CallbackContainer): Container holding a list of callbacks.
     """
 
-    def __init__(
-            self,
-            loss_fn: Callable[..., paddle.Tensor]=F.cross_entropy,
-            optimizer_fn: Callable[..., Optimizer]=paddle.optimizer.Adam,
-            optimizer_params: Dict[str, Any]=dict(learning_rate=1e-3),
-            eval_metrics: List[str]=[],
-            callbacks: List[Callback]=[],
-            batch_size: int=32,
-            max_epochs: int=10,
-            verbose: int=1,
-            patience: int=4,
-            seed: Optional[int]=None, ):
+    def __init__(self,
+                 loss_fn: Callable[..., paddle.Tensor]=F.cross_entropy,
+                 optimizer_fn: Callable[..., Optimizer]=paddle.optimizer.Adam,
+                 optimizer_params: Dict[str, Any]=dict(learning_rate=1e-3),
+                 eval_metrics: List[str]=[],
+                 callbacks: List[Callback]=[],
+                 batch_size: int=32,
+                 max_epochs: int=10,
+                 verbose: int=1,
+                 patience: int=4,
+                 seed: Optional[int]=None,
+                 config: Dict[str, Any]=None):
         super(PaddleBaseClassifier, self).__init__()
         self._loss_fn = loss_fn
         self._optimizer_fn = optimizer_fn
@@ -146,7 +146,8 @@ def _check_params(self):
         if not self._eval_metrics:
             self._eval_metrics = ["acc"]
 
-    def _check_tsdatasets(self, tsdatasets: List[TSDataset],
+    def _check_tsdatasets(self,
+                          tsdatasets: List[TSDataset],
                           labels: np.ndarray):
         """Ensure the robustness of input data (consistent feature order), at the same time,
             check whether the data types are compatible. If not, the processing logic is as follows.
@@ -214,7 +215,8 @@ def _init_optimizer(self) -> Optimizer:
 
         else:
             return self._optimizer_fn(
-                **self._optimizer_params, parameters=self._network.parameters())
+                **self._optimizer_params,
+                parameters=self._network.parameters())
 
     def _init_fit_dataloaders(
             self,
@@ -259,8 +261,8 @@ def _init_fit_dataloaders(
                     valid_tsdatasets, valid_labels,
                     self._fit_params['input_lens'])
             else:
-                valid_dataset = data_adapter.to_paddle_dataset(valid_tsdatasets,
-                                                               valid_labels)
+                valid_dataset = data_adapter.to_paddle_dataset(
+                    valid_tsdatasets, valid_labels)
             valid_dataloader = data_adapter.to_paddle_dataloader(
                 valid_dataset, self._batch_size, shuffle=False)
 
@@ -282,8 +284,8 @@ def _init_predict_dataloader(
             tsdatasets = [tsdatasets]
         self._check_tsdatasets(tsdatasets, labels)
         data_adapter = ClassifyDataAdapter()
-        dataset = data_adapter.to_paddle_dataset(tsdatasets, labels,
-                                                 self._fit_params['input_lens'])
+        dataset = data_adapter.to_paddle_dataset(
+            tsdatasets, labels, self._fit_params['input_lens'])
         dataloader = data_adapter.to_paddle_dataloader(
             dataset, self._batch_size, shuffle=False)
         return dataloader
@@ -420,7 +422,8 @@ def predict(
         # np.save('probs',probs)
         rng = check_random_state(self._seed)
         return np.array([
-            self._classes_[int(rng.choice(np.flatnonzero(prob == prob.max())))]
+            self._classes_[int(
+                rng.choice(np.flatnonzero(prob == prob.max())))]
             for prob in probs
         ])
 

paddlets/models/common/callbacks/callbacks.py

@@ -375,14 +375,11 @@ def on_batch_end(self, batch: int, logs: Optional[Dict[str, Any]]=None):
         max_mem_reserved_str = ""
         max_mem_allocated_str = ""
         if paddle.device.is_compiled_with_cuda() and utils.print_mem_info:
-            if paddle.device.cuda.max_memory_reserved() / (1024**2) < 1:
-                max_mem_reserved_str = f", max_mem_reserved: {paddle.device.cuda.max_memory_reserved() // 1024} KB"
-                max_mem_allocated_str = f", max_mem_allocated: {paddle.device.cuda.max_memory_allocated() // 1024} KB"
-            else:
-                max_mem_reserved_str = f", max_mem_reserved: {paddle.device.cuda.max_memory_reserved() // (1024 ** 2)} MB"
-                max_mem_allocated_str = f", max_mem_allocated: {paddle.device.cuda.max_memory_allocated() // (1024 ** 2)} MB"
+            max_mem_reserved_str = f", max_mem_reserved: {paddle.device.cuda.max_memory_reserved() // (1024 ** 2)} MB"
+            max_mem_allocated_str = f", max_mem_allocated: {paddle.device.cuda.max_memory_allocated() // (1024 ** 2)} MB"
 
         msg += f"{max_mem_reserved_str}{max_mem_allocated_str}"
         total_time = int(time.time() - self._start_time)
         msg += f" | {str(datetime.timedelta(seconds=total_time)) + 's':<6}"
-        logger.info(msg)
+        if batch % utils.log_interval == 0:
+            logger.info(msg)

paddlets/utils/config.py

@@ -89,6 +89,14 @@ def seq_len(self) -> int:
     def epoch(self) -> int:
         return self.dic.get('epoch')
 
+    @property
+    def log_interval(self) -> int:
+        return self.dic.get('log_interval', 1)
+
+    @property
+    def print_mem_info(self) -> bool:
+        return self.dic.get('print_mem_info', False)
+
     @property
     def model(self) -> Dict:
         return self.dic.get('model', {}).copy()
@@ -157,9 +165,8 @@ def update_config_dict(
     if learning_rate:
         dic['model']['model_cfg']['optimizer_params'][
             'learning_rate'] = learning_rate
-    dic['model']['model_cfg']['optimizer_params'][
-            'learning_rate']  = float(dic['model']['model_cfg']['optimizer_params'][
-            'learning_rate'])
+    dic['model']['model_cfg']['optimizer_params']['learning_rate'] = float(dic[
+        'model']['model_cfg']['optimizer_params']['learning_rate'])
     if batch_size:
         dic['batch_size'] = batch_size
     if epoch:

paddlets/utils/utils.py

@@ -21,13 +21,19 @@
 logger = Logger(__name__)
 # Compatible with earlier versions
 print_mem_info = True
+log_interval = 1
 
 
 def set_print_mem_info(flag: bool):
     global print_mem_info
     print_mem_info = flag
 
 
+def set_log_interval(interval: int):
+    global log_interval
+    log_interval = interval
+
+
 def check_model_fitted(model: Trainable, msg: str=None):
     """
     check if model has fitted, Raise Exception if not fitted
@@ -182,7 +188,8 @@ def check_train_valid_continuity(train_data: TSDataset,
                                pd.to_timedelta(train_index.freq))
     elif isinstance(train_index, pd.RangeIndex):
         if isinstance(valid_index, pd.RangeIndex):
-            continuious = (valid_index[0] - train_index[-1] == train_index.step)
+            continuious = (
+                valid_index[0] - train_index[-1] == train_index.step)
     else:
         raise_log("Unsupport data index format")
 
@@ -317,7 +324,8 @@ def get_tsdataset_max_len(dataset: TSDataset) -> int:
     return len(all_index)
 
 
-def repr_results_to_tsdataset(reprs: np.array, dataset: TSDataset) -> TSDataset:
+def repr_results_to_tsdataset(reprs: np.array,
+                              dataset: TSDataset) -> TSDataset:
     """
     Convert representation model output to a TSDataset 
 
@@ -447,8 +455,9 @@ def build_ts_infer_input(tsdataset: TSDataset,
     #build sample base on DataAdapter
     data_adapter = DataAdapter()
     if json_data['model_type'] == 'forecasting':
-        raise_if_not(tsdataset.get_target() is not None,
-                     "The target of tsdataset can not be None for forecasting!")
+        raise_if_not(
+            tsdataset.get_target() is not None,
+            "The target of tsdataset can not be None for forecasting!")
         size_keys = ['in_chunk_len', 'out_chunk_len', 'skip_chunk_len']
         for key in size_keys:
             raise_if_not(
@@ -471,7 +480,8 @@ def build_ts_infer_input(tsdataset: TSDataset,
             raise_if_not(
                 key in json_data['size'],
                 f"The {key} in json_data['size'] can not be None for anomaly!")
-        dataset = data_adapter.to_sample_dataset(tsdataset, **json_data['size'])
+        dataset = data_adapter.to_sample_dataset(tsdataset,
+                                                 **json_data['size'])
     else:
         raise_log(ValueError(f"Invalid model_type: {json_data['model_type']}"))
 

tools/train.py

@@ -17,7 +17,7 @@
 from paddlets.utils import backtest
 from paddlets.utils.utils import convert_and_remove_types
 from paddlets.logger import Logger
-from paddlets.utils.utils import set_print_mem_info, update_train_results
+from paddlets.utils.utils import set_print_mem_info, set_log_interval, update_train_results
 from export import export
 
 logger = Logger(__name__)
@@ -45,7 +45,8 @@ def parse_args():
         type=str,
         default=None)
     # Runntime params
-    parser.add_argument('--seq_len', help='input length in training.', type=int)
+    parser.add_argument(
+        '--seq_len', help='input length in training.', type=int)
     parser.add_argument(
         '--predict_len', help='output length in training.', type=int)
     parser.add_argument('--epoch', help='Iterations in training.', type=int)
@@ -55,7 +56,10 @@ def parse_args():
 
     # Other params
     parser.add_argument(
-        '--seed', help='Set the random seed in training.', default=42, type=int)
+        '--seed',
+        help='Set the random seed in training.',
+        default=42,
+        type=int)
     parser.add_argument(
         '--opts', help='Update the key-value pairs of all options.', nargs='+')
 
@@ -84,6 +88,8 @@ def main(args):
 
     print_mem_info = cfg.dic.get('print_mem_info', True)
     set_print_mem_info(print_mem_info)
+    log_interval = cfg.dic.get('log_interval', 1)
+    set_log_interval(log_interval)
     batch_size = cfg.batch_size
     dataset = cfg.dataset
     predict_len = cfg.predict_len
@@ -231,7 +237,8 @@ def main(args):
             ts_train, ts_val, ts_test = get_dataset(dataset['name'], split,
                                                     seq_len, info_params)
         else:
-            ts_train = get_dataset(dataset['name'], split, seq_len, info_params)
+            ts_train = get_dataset(dataset['name'], split, seq_len,
+                                   info_params)
 
     if cfg.model['name'] in ['TimesNetModel', 'Nonstationary_Transformer'
                              ] and args.device == 'xpu':
@@ -240,7 +247,8 @@ def main(args):
     if cfg.model['name'] == 'PP-TS':
         from paddlets.ensemble import WeightingEnsembleForecaster
         estimators = []
-        for model_name, model_cfg in cfg.model['model_cfg']['Ensemble'].items():
+        for model_name, model_cfg in cfg.model['model_cfg']['Ensemble'].items(
+        ):
             model_cfg = Config(
                 model_cfg,
                 seq_len=seq_len,
@@ -311,8 +319,8 @@ def main(args):
             if dataset['name'] != 'TSDataset':
                 ts_all = get_dataset(dataset['name'])
                 ts_all = time_feature_generator.fit_transform(ts_all)
-                ts_train._known_cov = ts_all._known_cov[split['train'][0]:split[
-                    'train'][1]]
+                ts_train._known_cov = ts_all._known_cov[split['train'][0]:
+                                                        split['train'][1]]
                 if ts_val is not None:
                     ts_val._known_cov = ts_all._known_cov[split['val'][
                         0] - seq_len:split['val'][1]]